#662 by GitHub stars
zjunlp/SkillNet
Create, Evaluate, and Connect AI Skills
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-appliance-preparer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-clean-object/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-device-operator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-environment-scanner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-goal-interpreter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-heat-object-with-appliance/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-inventory-management/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-locate-target-object/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-location-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-navigation-planner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-cooler/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-disposer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-heater/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-locator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-picker/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-placer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-state-inspector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-state-modifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-storer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-object-transporter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-open-receptacle/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-closer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-finder/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-opener/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-operator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-preparer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-receptacle-searcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-search-pattern-executor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-search-verifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-storage-explorer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-task-verifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-temperature-regulator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-tool-locator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/alfworld/alfworld-tool-user/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-ambiguous-action-resolution/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-animal-identifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-circuit-builder/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-circuit-connector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-conditional-box-placer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-conditional-focus-executor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-conditional-placer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-conductivity-tester/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-container-inspector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-container-item-retriever/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-container-relocator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-container-transfer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-controlled-waiting/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-device-activator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-environment-isolation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-environment-scanner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-growth-focuser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-heating-apparatus-setup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-instruction-reader/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-inventory-focus/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-inventory-manager/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-item-fetcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-liquid-filler/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-liquid-pourer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-liquid-source-find/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-living-entity-identifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-material-classifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-measurement-taker/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-mixture-creator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-classifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-focuser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-locator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-placer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-retriever/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-object-selector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-planting-coordinator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-planting-operation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-pot-preparer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-process-monitor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-process-pauser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-recipe-retriever/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-result-archiver/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-room-explorer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-room-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-room-scanner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-room-teleporter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-substance-cooler/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-substance-fetcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-substance-preparator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-target-identifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-target-locator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-task-focuser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-task-interpreter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-task-parser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-temperature-measurer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-threshold-evaluator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-tool-fetcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-tool-user/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/scienceworld-tool-validator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/soil-extraction/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/scienceworld/task-completion-focus/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-action-executor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-attribute-selector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-attribute-verifier/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-initial-search/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-option-selector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-price-checker/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-detail-check/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-detail-inspector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-detail-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-evaluator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-search/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-product-selector/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-purchase-executor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-purchase-initiator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-query-interpreter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-query-parser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-result-analyzer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-result-filter/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-result-page-navigator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-search-constructor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-search-executor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-search-formulator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
experiments/src/skills/webshop/webshop-variant-chooser/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ec1488b37ba4
No earlier version was observed for comparison.
skills/skillnet/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ec1488b37ba4
No earlier version was observed for comparison.
Heat
6.0- Star growth, last 7 daysAhead of 83% of tracked repositories
- Star growth, last 24 hoursAhead of 69% of tracked repositories
- Rank movement, last 7 daysAhead of 29% of tracked repositories
- Commits, last 30 daysAhead of 80% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- alfworld-appliance-navigator
experiments/src/skills/alfworld/alfworld-appliance-navigator - alfworld-appliance-preparer
experiments/src/skills/alfworld/alfworld-appliance-preparer - alfworld-clean-object
experiments/src/skills/alfworld/alfworld-clean-object - alfworld-device-operator
experiments/src/skills/alfworld/alfworld-device-operator - alfworld-environment-scanner
experiments/src/skills/alfworld/alfworld-environment-scanner - alfworld-goal-interpreter
experiments/src/skills/alfworld/alfworld-goal-interpreter - alfworld-heat-object-with-appliance
experiments/src/skills/alfworld/alfworld-heat-object-with-appliance - alfworld-inventory-management
experiments/src/skills/alfworld/alfworld-inventory-management - alfworld-locate-target-object
experiments/src/skills/alfworld/alfworld-locate-target-object - alfworld-location-navigator
experiments/src/skills/alfworld/alfworld-location-navigator - alfworld-navigation-planner
experiments/src/skills/alfworld/alfworld-navigation-planner - alfworld-object-cooler
experiments/src/skills/alfworld/alfworld-object-cooler - alfworld-object-disposer
experiments/src/skills/alfworld/alfworld-object-disposer - alfworld-object-heater
experiments/src/skills/alfworld/alfworld-object-heater - alfworld-object-locator
experiments/src/skills/alfworld/alfworld-object-locator - alfworld-object-picker
experiments/src/skills/alfworld/alfworld-object-picker - alfworld-object-placer
experiments/src/skills/alfworld/alfworld-object-placer - alfworld-object-retriever
experiments/src/skills/alfworld/alfworld-object-retriever - alfworld-object-state-inspector
experiments/src/skills/alfworld/alfworld-object-state-inspector - alfworld-object-state-modifier
experiments/src/skills/alfworld/alfworld-object-state-modifier - alfworld-object-storer
experiments/src/skills/alfworld/alfworld-object-storer - alfworld-object-transporter
experiments/src/skills/alfworld/alfworld-object-transporter - alfworld-open-receptacle
experiments/src/skills/alfworld/alfworld-open-receptacle - alfworld-receptacle-closer
experiments/src/skills/alfworld/alfworld-receptacle-closer - alfworld-receptacle-finder
experiments/src/skills/alfworld/alfworld-receptacle-finder - alfworld-receptacle-navigator
experiments/src/skills/alfworld/alfworld-receptacle-navigator - alfworld-receptacle-opener
experiments/src/skills/alfworld/alfworld-receptacle-opener - alfworld-receptacle-operator
experiments/src/skills/alfworld/alfworld-receptacle-operator - alfworld-receptacle-preparer
experiments/src/skills/alfworld/alfworld-receptacle-preparer - alfworld-receptacle-searcher
experiments/src/skills/alfworld/alfworld-receptacle-searcher - alfworld-search-pattern-executor
experiments/src/skills/alfworld/alfworld-search-pattern-executor - alfworld-search-verifier
experiments/src/skills/alfworld/alfworld-search-verifier - alfworld-storage-explorer
experiments/src/skills/alfworld/alfworld-storage-explorer - alfworld-task-verifier
experiments/src/skills/alfworld/alfworld-task-verifier - alfworld-temperature-regulator
experiments/src/skills/alfworld/alfworld-temperature-regulator - alfworld-tool-locator
experiments/src/skills/alfworld/alfworld-tool-locator - alfworld-tool-user
experiments/src/skills/alfworld/alfworld-tool-user - scienceworld-ambiguous-action-resolution
experiments/src/skills/scienceworld/scienceworld-ambiguous-action-resolution - scienceworld-animal-identifier
experiments/src/skills/scienceworld/scienceworld-animal-identifier - scienceworld-circuit-builder
experiments/src/skills/scienceworld/scienceworld-circuit-builder - scienceworld-circuit-connector
experiments/src/skills/scienceworld/scienceworld-circuit-connector - scienceworld-conditional-box-placer
experiments/src/skills/scienceworld/scienceworld-conditional-box-placer - scienceworld-conditional-focus-executor
experiments/src/skills/scienceworld/scienceworld-conditional-focus-executor - scienceworld-conditional-placer
experiments/src/skills/scienceworld/scienceworld-conditional-placer - scienceworld-conductivity-tester
experiments/src/skills/scienceworld/scienceworld-conductivity-tester - scienceworld-container-inspector
experiments/src/skills/scienceworld/scienceworld-container-inspector - scienceworld-container-item-retriever
experiments/src/skills/scienceworld/scienceworld-container-item-retriever - scienceworld-container-relocator
experiments/src/skills/scienceworld/scienceworld-container-relocator - scienceworld-container-transfer
experiments/src/skills/scienceworld/scienceworld-container-transfer - controlled-waiting
experiments/src/skills/scienceworld/scienceworld-controlled-waiting - scienceworld-device-activator
experiments/src/skills/scienceworld/scienceworld-device-activator - scienceworld-environment-isolation
experiments/src/skills/scienceworld/scienceworld-environment-isolation - scienceworld-environment-scanner
experiments/src/skills/scienceworld/scienceworld-environment-scanner - scienceworld-growth-focuser
experiments/src/skills/scienceworld/scienceworld-growth-focuser - scienceworld-heating-apparatus-setup
experiments/src/skills/scienceworld/scienceworld-heating-apparatus-setup - scienceworld-instruction-reader
experiments/src/skills/scienceworld/scienceworld-instruction-reader - scienceworld-inventory-focus
experiments/src/skills/scienceworld/scienceworld-inventory-focus - scienceworld-inventory-manager
experiments/src/skills/scienceworld/scienceworld-inventory-manager - scienceworld-item-fetcher
experiments/src/skills/scienceworld/scienceworld-item-fetcher - scienceworld-liquid-filler
experiments/src/skills/scienceworld/scienceworld-liquid-filler - scienceworld-liquid-pourer
experiments/src/skills/scienceworld/scienceworld-liquid-pourer - scienceworld-liquid-source-finder
experiments/src/skills/scienceworld/scienceworld-liquid-source-find - scienceworld-living-entity-identifier
experiments/src/skills/scienceworld/scienceworld-living-entity-identifier - scienceworld-material-classifier
experiments/src/skills/scienceworld/scienceworld-material-classifier - scienceworld-measurement-taker
experiments/src/skills/scienceworld/scienceworld-measurement-taker - scienceworld-mixture-creator
experiments/src/skills/scienceworld/scienceworld-mixture-creator - scienceworld-object-classifier
experiments/src/skills/scienceworld/scienceworld-object-classifier - scienceworld-object-focuser
experiments/src/skills/scienceworld/scienceworld-object-focuser - scienceworld-object-locator
experiments/src/skills/scienceworld/scienceworld-object-locator - scienceworld-object-placer
experiments/src/skills/scienceworld/scienceworld-object-placer - scienceworld-object-retriever
experiments/src/skills/scienceworld/scienceworld-object-retriever - scienceworld-object-selector
experiments/src/skills/scienceworld/scienceworld-object-selector - scienceworld-planting-coordinator
experiments/src/skills/scienceworld/scienceworld-planting-coordinator - scienceworld-planting-operation
experiments/src/skills/scienceworld/scienceworld-planting-operation - scienceworld-pot-preparer
experiments/src/skills/scienceworld/scienceworld-pot-preparer - scienceworld-process-monitor
experiments/src/skills/scienceworld/scienceworld-process-monitor - scienceworld-process-pauser
experiments/src/skills/scienceworld/scienceworld-process-pauser - scienceworld-recipe-retriever
experiments/src/skills/scienceworld/scienceworld-recipe-retriever - scienceworld-result-archiver
experiments/src/skills/scienceworld/scienceworld-result-archiver - scienceworld-room-explorer
experiments/src/skills/scienceworld/scienceworld-room-explorer - scienceworld-room-navigator
experiments/src/skills/scienceworld/scienceworld-room-navigator - scienceworld-room-scanner
experiments/src/skills/scienceworld/scienceworld-room-scanner - scienceworld-room-teleporter
experiments/src/skills/scienceworld/scienceworld-room-teleporter - scienceworld-substance-cooler
experiments/src/skills/scienceworld/scienceworld-substance-cooler - scienceworld-substance-fetcher
experiments/src/skills/scienceworld/scienceworld-substance-fetcher - scienceworld-substance-preparator
experiments/src/skills/scienceworld/scienceworld-substance-preparator - scienceworld-target-identifier
experiments/src/skills/scienceworld/scienceworld-target-identifier - scienceworld-target-locator
experiments/src/skills/scienceworld/scienceworld-target-locator - scienceworld-task-focuser
experiments/src/skills/scienceworld/scienceworld-task-focuser - scienceworld-task-interpreter
experiments/src/skills/scienceworld/scienceworld-task-interpreter - scienceworld-task-parser
experiments/src/skills/scienceworld/scienceworld-task-parser - scienceworld-temperature-measurer
experiments/src/skills/scienceworld/scienceworld-temperature-measurer - scienceworld-threshold-evaluator
experiments/src/skills/scienceworld/scienceworld-threshold-evaluator - scienceworld-tool-fetcher
experiments/src/skills/scienceworld/scienceworld-tool-fetcher - scienceworld-tool-user
experiments/src/skills/scienceworld/scienceworld-tool-user - scienceworld-tool-validator
experiments/src/skills/scienceworld/scienceworld-tool-validator - soil-extraction
experiments/src/skills/scienceworld/soil-extraction - task-completion-focus
experiments/src/skills/scienceworld/task-completion-focus - webshop-action-executor
experiments/src/skills/webshop/webshop-action-executor - webshop-attribute-selector
experiments/src/skills/webshop/webshop-attribute-selector - webshop-attribute-verifier
experiments/src/skills/webshop/webshop-attribute-verifier - webshop-initial-search
experiments/src/skills/webshop/webshop-initial-search - webshop-option-selector
experiments/src/skills/webshop/webshop-option-selector - webshop-price-checker
experiments/src/skills/webshop/webshop-price-checker - webshop-product-detail-check
experiments/src/skills/webshop/webshop-product-detail-check - webshop-product-detail-inspector
experiments/src/skills/webshop/webshop-product-detail-inspector - webshop-product-detail-navigator
experiments/src/skills/webshop/webshop-product-detail-navigator - webshop-product-evaluator
experiments/src/skills/webshop/webshop-product-evaluator - webshop-product-search
experiments/src/skills/webshop/webshop-product-search - webshop-product-selector
experiments/src/skills/webshop/webshop-product-selector - webshop-purchase-executor
experiments/src/skills/webshop/webshop-purchase-executor - webshop-purchase-initiator
experiments/src/skills/webshop/webshop-purchase-initiator - webshop-query-interpreter
experiments/src/skills/webshop/webshop-query-interpreter - webshop-query-parser
experiments/src/skills/webshop/webshop-query-parser - webshop-result-analyzer
experiments/src/skills/webshop/webshop-result-analyzer - webshop-result-filter
experiments/src/skills/webshop/webshop-result-filter - webshop-result-page-navigator
experiments/src/skills/webshop/webshop-result-page-navigator - webshop-search-constructor
experiments/src/skills/webshop/webshop-search-constructor - webshop-search-executor
experiments/src/skills/webshop/webshop-search-executor - webshop-search-formulator
experiments/src/skills/webshop/webshop-search-formulator - webshop-variant-chooser
experiments/src/skills/webshop/webshop-variant-chooser - skillnet
skills/skillnet
How it works
alfworld-appliance-navigator
When your agent uses it
Navigates the agent to a target appliance (microwave, stove, fridge, or sinkbasin) needed for object processing. Use when you are holding an object that needs heating, cooling, or cleaning and must move to the correct appliance station. Identifies the required appliance from the task context and executes the movement action.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
477 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Example
- Key Principles
Files
SKILL.mdcore2,054 bytes
Read SKILL.md
# Instructions
Use this skill when you are holding an object that needs to be processed (heated, cooled, or cleaned) and you must locate and move to the correct appliance to perform the action.
## Workflow
1. **Identify the Target Appliance:** Determine which appliance is required for the task. Map the action to the appliance: `heat` -> microwave/stoveburner, `cool` -> fridge, `clean` -> sinkbasin.
2. **Locate the Appliance:** Scan the environment observation for the target appliance (e.g., `microwave 1`, `fridge 1`, `sinkbasin 1`).
3. **Navigate:** Execute `go to {appliance}` to move to the identified appliance location.
4. **Prepare Appliance (if needed):** Upon arrival, check if the appliance requires preparation (e.g., opening a closed microwave or fridge door). If so, perform `open {appliance}` before proceeding.
## Example
**Scenario:** You are holding `potato 1` and need to heat it.
```
Thought: I need to heat this potato. The microwave is the appropriate appliance.View the complete source on GitHubalfworld-appliance-preparer
When your agent uses it
Prepares a household appliance (microwave, oven, toaster, fridge) for use by ensuring it is in the correct open/closed state. Use when the agent needs to heat, cool, or cook an item and must first open or close the appliance before placing an object inside. Takes an appliance identifier as input and outputs a confirmation that the appliance is ready for the next action.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
561 tokensWhen the skill is activated
Reference documents
334 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Goal
- Input
- Core Logic
- Important Considerations
- Example
- Output
Files
SKILL.mdcore2,446 bytesreferences/trajectory_example.mddoc1,377 bytes
Read SKILL.md
# Instructions
## Goal
Prepare a specified household appliance for immediate use by ensuring it is in the correct open or closed state. This is a prerequisite step before performing actions like `heat`, `cool`, or `toggle` with the appliance.
## Input
- **appliance_identifier**: The name of the appliance to prepare (e.g., `microwave 1`, `toaster 1`, `fridge 1`).
## Core Logic
1. **Navigate to the Appliance**: First, go to the location of the target appliance.
2. **Check State & Prepare**: Determine if the appliance needs to be opened or closed based on the intended subsequent action. The standard rule is:
* For appliances used to contain items for processing (e.g., microwave, oven, fridge), they typically need to be **open** to receive the item.
* Use the `open {appliance}` or `close {appliance}` action as needed.
3. **Confirm Readiness**: The skill is complete when the appliance is in the correct state, confirmed by an observation from the environment (e.g., "The microwave 1 is open.").
View the complete source on GitHubalfworld-clean-object
When your agent uses it
Cleans a specified object using an appropriate cleaning receptacle (e.g., sinkbasin). Use when a task requires an object to be in a clean state (e.g., "clean potato", "wash apple") before proceeding. Navigates to the cleaning location, performs the clean action, and confirms the object is now clean.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
428 tokensWhen the skill is activated
Reference documents
550 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Action Format
- Error Recovery
- Example
- Post-Condition
Files
SKILL.mdcore1,650 bytesreferences/trajectory_analysis.mddoc1,012 bytesreferences/troubleshooting.mddoc1,214 bytes
Read SKILL.md
# Instructions
Clean an object you are holding using a sinkbasin. The object must be in your inventory before cleaning.
## Workflow
1. **Navigate:** `go to sinkbasin 1` (or the appropriate sinkbasin in the environment)
2. **Clean:** `clean {object} with sinkbasin 1` -- verify observation confirms "You clean the {object}"
3. **Proceed:** The object is now clean. Continue with the next task step
## Action Format
- `clean {obj} with {recep}` (e.g., `clean potato 1 with sinkbasin 1`)
## Error Recovery
- "Nothing happened": Check (1) you are holding the object, (2) you are at the sinkbasin, (3) object and receptacle names are correct
- Not at sinkbasin: execute `go to sinkbasin 1` firstView the complete source on GitHubalfworld-device-operator
When your agent uses it
Operates a device or appliance (like a desklamp, microwave, or fridge) to interact with another object. Use when the task requires using a tool on a target item (e.g., "look at laptop under the desklamp", "heat potato with microwave"). Locates both the device and target object, co-locates them, and executes the appropriate use action (toggle, heat, cool, or clean).
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
976 tokensWhen the skill is activated
Reference documents
328 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Skill Trigger
- 2. Core Execution Flow
- 3. Key Assumptions & Rules
- Example
Files
SKILL.mdcore3,664 bytesreferences/device_location_guide.mddoc1,126 bytes
Read SKILL.md
# Instructions
## 1. Skill Trigger
Activate this skill when the task goal explicitly requires **using a device or appliance** to interact with a target object. Common indicators include phrases like:
- "look at [object] under the [device]"
- "heat [object] with [device]"
- "cool [object] with [device]"
- "clean [object] with [device]"
## 2. Core Execution Flow
Follow this sequence when the skill is triggered:
### Phase 1: Locate the Device
1. **Identify the device** from the task description (e.g., `desklamp`, `microwave`, `fridge`).
2. **Search common receptacles** where such a device is typically found (e.g., desks, sidetables, countertops).View the complete source on GitHubalfworld-environment-scanner
When your agent uses it
Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles. Use when you first enter an environment and need to build a mental map for task planning. Processes raw observation text into a structured list of entities, categorizing them as objects or receptacles.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
755 tokensWhen the skill is activated
Reference documents
599 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Primary Objective
- Core Workflow
- Execution Rules
- Example from Trajectory
Files
SKILL.mdcore3,144 bytesreferences/alfworld_actions_guide.mddoc2,258 bytes
Read SKILL.md
# Instructions
## Primary Objective
Execute an initial environmental scan at the start of any Alfworld task. Your goal is to systematically identify and catalog all objects and receptacles mentioned in the initial observation text.
## Core Workflow
1. **Trigger:** This skill is triggered immediately upon receiving the initial environment description from the simulator (e.g., "You are in the middle of a room. Looking quickly around you, you see...").
2. **Parse & Extract:** Process the raw observation text. Extract every noun phrase that represents a physical entity (object or receptacle). Note the naming convention (e.g., "armchair 2", "diningtable 1").
3. **Categorize:** Mentally categorize each entity. A **receptacle** is a surface or container that can hold other objects (e.g., `sofa`, `sidetable`, `diningtable`, `dresser`). An **object** is an item that can be manipulated (e.g., `laptop`, `creditcard`, `pillow`). Some entities (like `ottoman`) can be both depending on context.
4. **Output Structured Mental Map:** Formulate a clear, concise internal summary. Do not output this summary to the simulator—it is for your planning use only.
* **Format:** `Scan Complete. Receptacles: [list]. Objects: [list].`
* **Example:** Based on the trajectory, the mental map should be: `Scan Complete. Receptacles: [armchair 2, armchair 1, diningtable 1, drawer 4, drawer 3, drawer 2, drawer 1, dresser 1, garbagecan 1, ottoman 1, sidetable 3, sidetable 2, sidetable 1, sofa 1]. Objects: [].` *(Note: Initial scan only lists visible furniture; objects on them are discovered upon interaction.)*
## Execution Rules
* **Single Action:** This skill culminates in a single `go to <receptacle>` action to begin the task-specific search. Choose the most logical first receptacle to inspect (e.g., large central surfaces like `diningtable 1` or `sofa 1`).View the complete source on GitHubalfworld-goal-interpreter
When your agent uses it
Parses the natural language task goal to extract actionable sub-objectives and required objects. Trigger this skill whenever a new task is assigned to break down complex instructions into clear, sequential targets. It interprets phrases like 'look at X under Y' to identify target objects (pillow), reference objects (desklamp), and spatial relationships (under).
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
509 tokensWhen the skill is activated
Reference documents
390 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Parse the Task Statement
- 2. Generate Sub-Objectives
- 3. Identify Required Objects & Actions
- 4. Execute & Adapt
Files
SKILL.mdcore2,302 bytesreferences/search_patterns.mddoc2,060 bytes
Read SKILL.md
# Goal Interpretation Protocol
## 1. Parse the Task Statement
When a new task is assigned, immediately analyze the natural language instruction to extract its core components. Use the parsing script (`parse_goal.py`) to perform this analysis.
**Input:** The raw task string (e.g., "look at pillow under the desklamp").
**Output:** A structured dictionary containing:
- `primary_target`: The main object to interact with.
- `reference_object`: The object that defines a location or condition.
- `spatial_relation`: The preposition linking them (e.g., under, on, in).
- `action`: The verb defining the required interaction.
## 2. Generate Sub-Objectives
Based on the parsed components, formulate a clear, sequential plan. The plan must account for the spatial relationship.
View the complete source on GitHubalfworld-heat-object-with-appliance
When your agent uses it
Uses a heating appliance (microwave, stoveburner, oven) to apply heat to a specified object. Use when the task requires warming or cooking an item (e.g., "heat some egg", "warm the mug") and a heating appliance is available. Takes the object name and appliance name as input and outputs the object in a heated state, ready for placement at the task's target location.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
725 tokensWhen the skill is activated
Reference documents
395 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Decision Points
- Example
- Bundled Resources
Files
SKILL.mdcore2,988 bytesreferences/common_heating_appliances.mddoc1,596 bytes
Read SKILL.md
# Skill: Heat Object with Appliance
## Purpose
Heat a specified object using a designated kitchen appliance to change its state (e.g., from cold to hot, raw to cooked) as required by a task.
## Core Workflow
Follow this sequence of actions. Use the bundled `validate_and_plan.py` script to check for common preconditions before starting.
1. **Navigate & Locate:** Go to the location of the target object.
2. **Acquire Object:** Take the object from its current receptacle.
3. **Navigate to Appliance:** Go to the specified heating appliance.
4. **Prepare Appliance:**
* If the appliance is closed, open it.
* If the appliance contains other items, you may need to remove them (context-dependent). The default action is to close it and proceed, as some environments abstract this step.
5. **Execute Heating:** Use the `heat {object} with {appliance}` action.View the complete source on GitHubalfworld-inventory-management
When your agent uses it
Use when the agent must collect and track multiple instances of the same object type in ALFWorld (e.g., "put two cellphone in bed"). This skill maintains a count of collected versus needed objects, guides systematic searching through receptacles, and ensures each found object is placed at the target before searching for the next.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
848 tokensWhen the skill is activated
Reference documents
258 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Workflow
- Example
- Error Handling
Files
SKILL.mdcore3,360 bytesreferences/common_mistakes.mddoc1,292 bytes
Read SKILL.md
# Inventory Management Skill
## When to Use
Activate this skill when:
- Task requires collecting **multiple instances** of the same object type (e.g., "put two cellphone in bed")
- You need to track progress toward a quantity-based goal
- Searching through multiple locations systematically
## Core Workflow
### 1. Initialize Inventory
- Parse the task description to identify:
- **Target object type** (e.g., "cellphone")
- **Required quantity** (e.g., "two" = 2)
- **Target receptacle** (e.g., "bed 1")View the complete source on GitHubalfworld-locate-target-object
When your agent uses it
Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g., "potato", "plate") and its location is not immediately known. Moves to a relevant receptacle (like a fridge or cabinet), checks its contents, and outputs the object's location or confirms its absence.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
726 tokensWhen the skill is activated
Reference documents
252 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Instructions
- Key Principles
- Example
- Next Steps
Files
SKILL.mdcore2,986 bytesreferences/action_primer.mddoc948 bytes
Read SKILL.md
# Skill: Locate Target Object
## Purpose
Use this skill when your goal requires a specific object and you need to find it. The skill directs you to a likely receptacle, inspects it, and confirms if the target is present.
## Core Workflow
1. **Identify Target & Suspected Location:** Determine the object you need and the most logical place to find it (e.g., food in the `fridge`, utensils in a `drawer`).
2. **Navigate:** Go to the suspected receptacle.
3. **Inspect:** If the receptacle is closed, open it.
4. **Locate:** Visually scan the contents for the target object.
5. **Report:** Output the object's location if found, or note its absence.
## Instructions
Follow this sequence of actions and reasoning.
View the complete source on GitHubalfworld-location-navigator
When your agent uses it
Moves the agent to a specified receptacle or object location within the Alfworld environment. Use this skill when the agent needs to physically approach a target to inspect or interact with it, such as when checking an object's state or preparing for pickup. The skill takes a target location name as input and executes the 'go to' action, resulting in the agent being positioned at the destination for subsequent operations.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
268 tokensWhen the skill is activated
Reference documents
532 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Process
- Notes
Files
SKILL.mdcore1,278 bytesreferences/action_primer.mddoc1,244 bytesreferences/trajectory_analysis.mddoc1,088 bytes
Read SKILL.md
# Instructions
Use this skill to navigate to a specific location in the Alfworld environment. The skill will move the agent directly to the target receptacle or object.
## Input
Provide the target location name as a string (e.g., "toiletpaperhanger 1", "toilet 1").
## Process
1. The skill validates the target location against the current environment observation.
2. It executes the `go to {target}` action.
3. It returns the environment's observation after the move.
## Notes
- Ensure the target location is visible in the agent's current observation before calling this skill.
- This skill is for navigation only. Use other skills for object interaction (take, put, etc.).
- If the action fails (e.g., "Nothing happened"), the agent may need to replan its path or verify the target name.View the complete source on GitHubalfworld-navigation-planner
When your agent uses it
Plans a path to move the agent between receptacles to search for target objects. Use this when you need to traverse the environment to reach a specific location or systematically explore multiple areas. It takes the current location and destination receptacle as input, and outputs the next 'go to' action to approach the target.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
417 tokensWhen the skill is activated
Reference documents
507 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input/Output Format
- How to Use
- Key Principles
Files
SKILL.mdcore1,816 bytesreferences/action_primer.mddoc1,971 bytes
Read SKILL.md
# Instructions
Use this skill to navigate between receptacles (e.g., bed, desk, drawer) in a household environment to locate objects. The core logic is handled by the bundled script.
## Input/Output Format
- **Input:** Provide the agent's **current location** and the **target receptacle**.
- **Output:** The skill will return the next `go to {recep}` action to execute.
## How to Use
1. **Identify your goal.** Determine which receptacle you need to search (e.g., `desk 1` to find a `desklamp`).
2. **Call the skill.** Pass your current location and the target receptacle.
3. **Execute the action.** Perform the `go to` action returned by the skill.
4. **Observe and repeat.** After moving, observe the new location. If the target object is not found, use this skill again to plan movement to the next most promising receptacle.
## Key PrinciplesView the complete source on GitHubalfworld-object-cooler
When your agent uses it
Cools a held object using an appropriate cooling appliance such as a fridge or freezer. Use when the task requires reducing the temperature of an object (e.g., "cool some pot", "chill the mug") and the agent is already holding the object. Performs the ALFWorld `cool` action and outputs the cooled object ready for subsequent placement or serving steps.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
473 tokensWhen the skill is activated
Reference documents
355 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Prerequisites
- Core Action
- Execution Flow
- Example from Trajectory
- Next Steps
Files
SKILL.mdcore1,851 bytesreferences/action_semantics.mddoc1,358 bytes
Read SKILL.md
# Skill: Cool Held Object
## Purpose
Use this skill when you are holding an object (e.g., `pot 1`) that needs to be cooled and you are at the location of a valid cooling receptacle (e.g., `fridge 1`). The skill executes the `cool` action to change the object's state.
## Prerequisites
1. **Object in Hand:** You must already be holding the target object (e.g., `pot 1`).
2. **At Cooling Receptacle:** You must be at the location of the cooling appliance (e.g., `fridge 1`). Use `go to {recep}` to navigate first if needed.
3. **Valid Receptacle:** The receptacle must be a valid target for the `cool` action (e.g., fridge, freezer). The environment will validate this.
## Core Action
Execute the `cool` action with the format: `cool {obj} with {recep}`.
## Execution Flow
1. **Verify State:** Confirm you are holding the object and are at the cooling receptacle's location.View the complete source on GitHubalfworld-object-disposer
When your agent uses it
This skill disposes of an object by placing it into a disposal receptacle like a garbage can. It should be triggered when the task requires discarding an object (e.g., 'put it in garbagecan') and the agent is at the disposal location with the object in hand. The skill executes the 'put' action to place the object in/on the target receptacle, completing the disposal subtask.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
300 tokensWhen the skill is activated
Reference documents
428 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger Condition
- Execution
- Notes
Files
SKILL.mdcore1,364 bytesreferences/alfworld_actions.mddoc863 bytesreferences/trajectory_pattern.mddoc977 bytes
Read SKILL.md
# Skill: Object Disposer
## Trigger Condition
Activate this skill when:
1. The task goal explicitly requires disposing of an object (e.g., "put it in garbagecan", "throw away the X").
2. The agent is holding the target object.
3. The agent is at the location of the disposal receptacle (e.g., garbagecan).
## Execution
1. **Verify Prerequisites**: Confirm the object is in hand and the disposal receptacle is present at your location.
2. **Execute Disposal**: Perform the `put` action with the object and receptacle.
3. **Completion**: The skill is complete when the object has been successfully placed into/onto the disposal receptacle.
## Notes
- This skill handles only the final disposal action. Object acquisition and navigation to the disposal location are separate skills.View the complete source on GitHubalfworld-object-heater
When your agent uses it
Heats a specified object using an available heating appliance (e.g., microwave, stoveburner). Use when you are holding an object that requires heating and need to navigate to and operate the heating appliance. Takes the object and appliance as inputs and results in the object being in a heated state.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
471 tokensWhen the skill is activated
Reference documents
473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Workflow
- Action Format
- Error Recovery
- Example
Files
SKILL.mdcore1,917 bytesreferences/trajectory_breakdown.mddoc1,932 bytes
Read SKILL.md
# Instructions
Heat an object you are holding using a compatible heating appliance (microwave or stoveburner).
## Prerequisites
- The target object must be in your inventory
- A heating appliance (microwave, stoveburner) must exist in the environment
## Workflow
1. **Navigate:** `go to {appliance}` (e.g., `go to microwave 1`)
2. **Check state:** If observation says appliance is closed, execute `open {appliance}` -- verify observation confirms it is now open
3. **Heat:** `heat {object} with {appliance}` -- verify observation confirms "You heat the {object}"
4. **(Optional) Place:** If the task requires it, navigate to the destination and place the heated object
## Action FormatView the complete source on GitHubalfworld-object-locator
When your agent uses it
Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown. This skill parses the environment observation, ranks receptacles by likelihood of containing the target object using common-sense reasoning, and outputs a navigation action to the most promising location.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
907 tokensWhen the skill is activated
Reference documents
948 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Workflow
- Example
- Error Handling
Files
SKILL.mdcore3,558 bytesreferences/object_mappings.mddoc2,129 bytesreferences/skill_usage_examples.mddoc1,550 bytes
Read SKILL.md
# Skill: Object Locator for ALFWorld
## When to Use
Trigger this skill when:
1. Your goal requires a specific object (e.g., `knife`, `cellphone`, `apple`)
2. The object is not in your inventory
3. The current observation does not explicitly state the object's location
## Core Workflow
### 1. Parse the Environment
Extract all visible receptacles from the observation text. Typical ALFWorld receptacles include:
- **Surfaces**: countertop, desk, dresser, bed, shelf, sidetable, coffeetable, diningtable
- **Containers**: drawer, cabinet, safe, fridge, microwave, garbagecan
- **Appliances**: sinkbasin, bathtub, stoveburner, toasterView the complete source on GitHubalfworld-object-picker
When your agent uses it
Picks up a specified object from a given receptacle. Use this skill when the agent has located a required object and needs to acquire it for later use, such as taking an item from a surface or container. The skill requires the object and source receptacle as inputs, executing a 'take' action to transfer the object into the agent's inventory, enabling further manipulation like placement or usage.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
183 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Process
- Output
Files
SKILL.mdcore1,376 bytesSKILL.mdcore1,376 bytesSKILL.mdcore1,376 bytesreferences/troubleshooting.mddoc821 bytes
Read SKILL.md
# Instructions
Execute the `take` action to acquire the target object from the source receptacle.
## Inputs
- `object`: The identifier of the object to pick up (e.g., "toiletpaper 1").
- `source_receptacle`: The identifier of the receptacle where the object is located (e.g., "toilet 1").
## Process
1. **Verify Context:** Ensure the agent is at the location of the `source_receptacle`. If not, the agent must navigate there first using a separate movement skill.
2. **Execute Action:** Perform the action: `take {object} from {source_receptacle}`.
3. **Handle Feedback:** If the environment indicates "Nothing happened," consult the troubleshooting guide in `references/troubleshooting.md` for potential issues.
## Output
- The specified object is transferred to the agent's inventory.
- The agent receives an observation confirming the successful pickup (e.g., "You pick up the {object} from the {source_receptacle}").View the complete source on GitHubalfworld-object-placer
When your agent uses it
Places a held object onto or into a target receptacle. Trigger this skill when the agent is carrying an object and needs to deposit it at a specific location to complete a task, such as installing an item on a holder or storing it in a container. It takes the object and destination receptacle as inputs, performing a 'put' action to finalize the object's positioning according to the task goal.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
488 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,296 bytesreferences/action_guide.mddoc1,766 bytes
Read SKILL.md
# Instructions
1. **Verify Prerequisites**:
- Confirm you are currently holding the target object (`{obj}`).
- Confirm the target receptacle (`{recep}`) is present and accessible in the environment.
- If the receptacle is a container (e.g., cabinet, drawer), ensure it is open.
2. **Navigate to Receptacle**:
- Use the `go to {recep}` action to move to the target receptacle's location.
3. **Execute Placement**:
- Use the `put {obj} in/on {recep}` action to deposit the held object.
- The phrasing (`in` vs `on`) is determined by the receptacle type (e.g., `in` for containers, `on` for surfaces/holders). Use the trajectory as a reference.
4. **Handle Errors**:
- If the environment responds with "Nothing happened", the action was invalid. Consult the `references/action_guide.md` for troubleshooting common failure modes.View the complete source on GitHubalfworld-object-retriever
When your agent uses it
This skill picks up a target object from a specified receptacle after the object has been visually confirmed. Use this skill when the agent has located an object in a receptacle and needs to acquire it. It requires the object and source receptacle as inputs and results in the object being added to the agent's inventory.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
181 tokensWhen the skill is activated
Reference documents
280 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Action Sequence
Files
SKILL.mdcore844 bytesSKILL.mdcore844 bytesSKILL.mdcore844 bytesSKILL.mdcore844 bytesSKILL.mdcore844 bytesreferences/trajectory_example.mddoc1,203 bytes
Read SKILL.md
# Instructions
Use this skill to acquire a target object from a known source receptacle in the ALFWorld environment.
## Prerequisites
1. **Visual Confirmation**: You must have directly observed the target object within the specified source receptacle in a prior observation (e.g., "On the {recep}, you see a {obj}...").
2. **Proximity**: You should be at or near the location of the source receptacle.
## Core Action Sequence
Execute the following action precisely:View the complete source on GitHubalfworld-object-state-inspector
When your agent uses it
Inspects a receptacle's contents by navigating to it and reading the observation. Use when you need to check what is on or inside a receptacle (e.g., "what's on the shelf", "is the holder empty", "check the table for items"). Executes `go to {receptacle}`, parses the observation listing items present, and decides whether to take an item, search elsewhere, or proceed.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
468 tokensWhen the skill is activated
Reference documents
345 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Error Recovery
- Example
Files
SKILL.mdcore1,903 bytesreferences/alfworld_actions_ref.mddoc1,308 bytes
Read SKILL.md
# Instructions
Inspect the state or contents of a target receptacle by navigating to it and parsing the environment's observation feedback.
## Workflow
1. **Navigate:** Execute `go to {target_receptacle}`
2. **Read observation:** The environment automatically reports what is on/in the receptacle -- no additional inspection action is needed
3. **Parse contents:** Look for patterns:
- `"On the {receptacle}, you see nothing."` -- receptacle is empty
- `"On the {receptacle}, you see a {item1}, and a {item2}."` -- items are present
4. **Decide next action** based on the observation:
- Empty: search elsewhere for the needed item
- Item found: `take {item} from {receptacle}`
- Wrong items: move on to the next receptacle
View the complete source on GitHubalfworld-object-state-modifier
When your agent uses it
Uses an appliance to change the state of an object (cooling, heating, or cleaning). Use when the task requires altering an object's temperature or cleanliness using a specific device (e.g., cooling with a fridge, heating with a microwave, cleaning with a sinkbasin). Takes the object, target state, and appliance as inputs and executes the corresponding modifier action.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
510 tokensWhen the skill is activated
Reference documents
509 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Action Mapping
- Error Recovery
- Example
Files
SKILL.mdcore2,020 bytesreferences/appliance_interaction_guide.mddoc2,075 bytes
Read SKILL.md
# Instructions
Change an object's state (cool, heat, or clean) using a household appliance. You must be holding the target object before executing the state change.
## Workflow
1. **Navigate to appliance:** `go to {appliance}` (e.g., `go to fridge 1`)
2. **Prepare if closed:** If observation says appliance is closed, execute `open {appliance}` -- verify it opens
3. **Execute state change:** `{action} {obj} with {appliance}` -- verify observation confirms the change
4. **Proceed:** Continue with the next task step (e.g., placing the modified object)
## Action Mapping
| State Change | Action | Typical Appliance |
|---|---|---|
| Cool | `cool {obj} with {appliance}` | `fridge 1` |
| Heat | `heat {obj} with {appliance}` | `microwave 1`, `stoveburner 1` |View the complete source on GitHubalfworld-object-storer
When your agent uses it
Use when the agent is holding an object and needs to place it into a target receptacle in ALFWorld. This skill checks receptacle suitability, opens closed containers if needed, and executes the `put` command to store the object. It handles both open surfaces (countertops, beds) and closed containers (drawers, cabinets).
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
624 tokensWhen the skill is activated
Reference documents
322 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Workflow
- Example
- Error Handling
Files
SKILL.mdcore2,480 bytesreferences/receptacle_suitability_guide.mddoc1,422 bytes
Read SKILL.md
# Skill: Object Storer
## When to Use
Trigger this skill when:
1. The agent is holding the target object (optionally cleaned/heated/cooled as required)
2. A suitable storage receptacle has been identified
3. The agent needs to execute the final placement step
## Core Workflow
### 1. Validate Prerequisites
- Confirm the agent is holding `{object_name}` (check inventory)
- Confirm the agent is at the location of `{target_receptacle}`
- If not at the receptacle, navigate there first: `go to {target_receptacle}`
View the complete source on GitHubalfworld-object-transporter
When your agent uses it
Picks up a target object from its current receptacle and moves it to a specified destination receptacle. Use when you have located an object and need to relocate it to complete a task (e.g., moving a laptop to a desk). Takes the object identifier, source receptacle, and destination receptacle as inputs and outputs the action sequence to take, transport, and place the object.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
499 tokensWhen the skill is activated
Reference documents
422 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Action Format
- Error Recovery
- Example
- Bundled Resources
Files
SKILL.mdcore1,998 bytesSKILL.mdcore1,998 bytesreferences/troubleshooting.mddoc1,678 bytes
Read SKILL.md
# Instructions
Pick up an object from its current location and transport it to a destination receptacle.
## Workflow
1. **Navigate to source:** `go to {source_receptacle}` -- verify observation shows the target object
2. **Pick up:** `take {object} from {source_receptacle}` -- verify "You pick up" confirmation
3. **Navigate to destination:** `go to {destination_receptacle}`
4. **Place:** `put {object} in/on {destination_receptacle}` -- verify "You put" confirmation
## Action Format
- `go to {receptacle}`
- `take {object} from {receptacle}`
- `put {object} in/on {receptacle}`
View the complete source on GitHubalfworld-open-receptacle
When your agent uses it
This skill opens a closed receptacle to access its contents. It should be triggered when an agent needs to interact with items inside a closed container (e.g., fridge, microwave, drawer). The skill takes a receptacle identifier as input, performs the open action, and outputs the observation of the interior, enabling subsequent item retrieval or placement.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
361 tokensWhen the skill is activated
Reference documents
579 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Input Format
- Execution Steps
- Expected Outcomes
- Example from Trajectory
Files
SKILL.mdcore1,591 bytesreceptors/action_sequence_examples.mddoc91 bytesreferences/common_receptacles.mddoc2,201 bytes
Read SKILL.md
# Skill: Open Receptacle
## Purpose
Open a closed container to reveal its contents for subsequent interaction.
## When to Use
Use this skill when:
- You need to take an item from inside a closed receptacle
- You need to put an item into a closed receptacle
- You observe a receptacle is closed (e.g., "The fridge 1 is closed")
- The task requires accessing items inside containers
## Input Format
The skill requires a receptacle identifier as input. This should match the environment's naming convention (e.g., "fridge 1", "microwave 1", "drawer 3").
View the complete source on GitHubalfworld-receptacle-closer
When your agent uses it
Closes an open receptacle to maintain environment tidiness after inspection. Use when you have finished searching a container (drawer, cabinet, fridge) and no longer need it open. Takes a receptacle identifier as input and outputs confirmation that the receptacle is closed, preventing clutter during multi-step search tasks.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
317 tokensWhen the skill is activated
Reference documents
208 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Instruction
- Example from Trajectory
- Key Principle
Files
SKILL.mdcore1,385 bytesreferences/action_primer.mddoc831 bytes
Read SKILL.md
# Skill: Receptacle Closer
## When to Use
Use this skill **immediately after** you have finished inspecting the contents of an open receptacle (e.g., a drawer, cabinet, or container) and have determined you no longer need it to remain open. This is a cleanup action to maintain a tidy environment.
## Core Instruction
1. **Identify the Target:** The target is the receptacle you just finished searching. It must be open.
2. **Execute Action:** Perform the `close` action on the identified receptacle.
3. **Format:** Your output must follow the standard action format: `Action: close {recep}`
## Example from Trajectory
* **Context:** After opening and inspecting `drawer 2` (finding it empty), the agent closed it.
* **Thought:** "I should close drawer 2 to keep the room tidy and continue my search."
* **Action:** `close drawer 2`
View the complete source on GitHubalfworld-receptacle-finder
When your agent uses it
Searches for a suitable empty or appropriately occupied receptacle (like a shelf or table) to place an object. Use when you are holding an object that needs to be stored or placed and must find a receptacle that meets the placement criteria. Examines candidate receptacles by navigating to and inspecting each one until a suitable location is found.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
637 tokensWhen the skill is activated
Reference documents
301 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Procedure
- Key Considerations
- Example
- Bundled Reference
Files
SKILL.mdcore2,684 bytesreferences/example_trajectory.mddoc1,176 bytes
Read SKILL.md
# Instructions
**Trigger:** Use this skill when you have an object in your inventory that needs to be stored or placed, and you must find a suitable receptacle (e.g., shelf, table, basin).
## Core Procedure
1. **Identify Target Object:** Confirm the object you are holding and its state (e.g., `soapbar 1`, `clean`).
2. **Survey Environment:** Use `go to {recep}` actions to navigate to and visually inspect candidate receptacles from the observation list.
3. **Evaluate Candidates:** For each receptacle, assess its suitability:
* **Primary Goal:** Find an **empty receptacle**.
* **Fallback:** If no empty receptacle is available, identify one that can logically accommodate the object without conflict (e.g., a shelf with a tissuebox may still have space for a soapbar).
4. **Select & Place:** Navigate to the chosen suitable receptacle and execute `put {obj} in/on {recep}`.
## Key Considerations
* **Object State:** Ensure the object meets any required pre-conditions (e.g., `clean`) before searching for a receptacle. Use skills like `clean` if necessary.
* **Efficiency:** Prioritize receptacles that are logically appropriate for the object (e.g., a `shelf` for a `soapbar` over a `toilet`).View the complete source on GitHubalfworld-receptacle-navigator
When your agent uses it
Plans and executes movement to a target receptacle within the ALFWorld environment. Use when the agent needs to reach a specific location before interacting with objects there (e.g., go to fridge to cool an item, go to garbagecan to dispose of an item). Takes a receptacle identifier as input, executes the `go to` action, and outputs confirmation of arrival at the destination.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
573 tokensWhen the skill is activated
Reference documents
165 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Logic
- Instructions
- Example
- Error Handling
Files
SKILL.mdcore2,428 bytesreferences/common_receptacles.mddoc497 bytes
Read SKILL.md
# Skill: Receptacle Navigator
## Purpose
Navigate to a specified receptacle (e.g., `fridge 1`, `garbagecan 1`, `diningtable 1`) in an ALFWorld household environment. This is a foundational skill for positioning the agent to perform subsequent object interactions.
## When to Use
Trigger this skill when the agent's plan requires:
1. **Accessing a location** to interact with an object there (e.g., "go to fridge to cool an item").
2. **Interacting with the receptacle itself** (e.g., "go to garbagecan to dispose of an item").
## Core Logic
1. **Input Parsing:** Extract the target receptacle name (e.g., `fridge 1`) from the current task context or observation.
2. **Action Execution:** Output the ALFWorld action: `go to {target_receptacle}`.
3. **Success Verification:** Confirm the action was successful by checking the observation for evidence of arrival (e.g., "You are at the {receptacle}" or the receptacle is now in the observable list).
View the complete source on GitHubalfworld-receptacle-opener
When your agent uses it
This skill opens a closed receptacle to allow access to its contents or to enable interaction with it. It should be triggered when the agent encounters a closed receptacle (e.g., 'The fridge 1 is closed.') that must be opened to proceed with a task, such as cooling an item with a fridge or taking an object from inside a cabinet. The skill outputs the 'open' action on the specified receptacle.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
374 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger Condition
- Action
- Procedure
- Example from Trajectory
- Notes
Files
SKILL.mdcore1,564 bytes
Read SKILL.md
# Skill: Open Closed Receptacle
## Trigger Condition
Use this skill when the environment observation explicitly states that a receptacle is **closed** and opening it is necessary to proceed with your current task. The typical observation pattern is: `"The <receptacle_name> is closed."`
## Action
Execute the `open` action on the identified receptacle.
## Procedure
1. **Identify the Receptacle:** From the observation, extract the name of the closed receptacle (e.g., `fridge 1`, `cabinet 12`, `safe 1`).
2. **Execute Action:** Output the action in the format: `Action: open <receptacle_name>`.
## Example from Trajectory
* **Observation:** `"The fridge 1 is closed."`
* **Thought:** `The fridge is closed. I need to open it to access the cooling compartment.`View the complete source on GitHubalfworld-receptacle-operator
When your agent uses it
This skill opens or closes a receptacle (like a fridge, cabinet, or microwave) to access its interior or secure it. It should be triggered when an object needs to be placed inside/retrieved from a closed container, or when an open container should be closed (e.g., for energy efficiency or task cleanliness). The skill decides the appropriate 'open' or 'close' action based on the receptacle's current state and the task context.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
539 tokensWhen the skill is activated
Reference documents
17 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Decision Logic
- Example from Trajectory
- Important Notes
Files
SKILL.mdcore2,183 bytesreferences/state_diagrams.mddoc71 bytes
Read SKILL.md
# Skill: Receptacle Operator
## When to Use
Use this skill when you need to:
1. **Access a closed receptacle** to place an object inside or take an object out.
2. **Secure an open receptacle** after accessing it (e.g., to conserve energy, maintain cleanliness, or complete a task step).
## Core Decision Logic
1. **Check the receptacle's state** from the observation.
- If it reports "is closed" or "is open", note the state.
- If the interior is visible (e.g., "In it, you see..."), it is open.
2. **Choose action based on goal**:
- **Goal requires interior access** (e.g., "put in microwave", "take from fridge"):
- If closed → `open {recep}`
- If open → proceed with next step (e.g., `put` or `take`)View the complete source on GitHubalfworld-receptacle-preparer
When your agent uses it
This skill verifies and prepares a target receptacle for receiving an object. It is triggered before placing an item into a receptacle (e.g., a garbage can) to ensure the receptacle is accessible and suitable. The skill involves navigating to the receptacle, observing its state (e.g., open/closed, occupied), and performing any necessary preparatory actions like opening it, resulting in a ready-to-use target location.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
595 tokensWhen the skill is activated
Reference documents
364 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Procedure
- Key Principles
- Example from Trajectory
Files
SKILL.mdcore2,558 bytesSKILL.mdcore2,558 bytesreferences/action_primer.mddoc1,276 bytes
Read SKILL.md
# Instructions
**Trigger:** This skill is invoked when the agent's goal requires placing an object into a target receptacle (e.g., "put X in/on Y").
## Core Procedure
1. **Navigate:** Use `go to {target_receptacle}` to move to the target receptacle's location.
2. **Observe:** Upon arrival, carefully read the environment's observation. It will describe the receptacle's state and any contents.
3. **Analyze & Prepare:** Based on the observation, determine if the receptacle is ready.
* **Ready State:** The receptacle is described as present and accessible (e.g., "On the garbagecan 1, you see a cd 1."). No further action is needed. Proceed to place the object.
* **Blocked/Closed State:** If the receptacle is closed, latched, or obstructed, use the appropriate action (`open {recep}`, `toggle {obj} {recep}`) to prepare it.
* **Invalid Target:** If the observation indicates the receptacle does not exist or cannot be interacted with ("Nothing happened"), you must abort this skill and re-plan your task strategy.
4. **Confirm:** After any preparatory action, observe the environment's feedback to confirm the receptacle is now ready.
## Key Principles
* **Efficiency:** This skill is a preparatory step. Do not spend turns searching for the object to be placed here. That is a separate "search" skill.View the complete source on GitHubalfworld-receptacle-searcher
When your agent uses it
This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found. Trigger when the target receptacle is not initially visible, often after scanning nearby areas. It outputs the receptacle's location and may involve navigating through multiple waypoints.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
668 tokensWhen the skill is activated
Reference documents
432 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Procedure
- Key Notes
- Example from Trajectory
Files
SKILL.mdcore2,836 bytesassets/search_pattern_template.jsonasset1,480 bytesreferences/environment_guide.mddoc1,692 bytes
Read SKILL.md
# Instructions
## When to Use
Use this skill when you need to locate a specific receptacle (e.g., `garbagecan 1`, `cabinet 3`) that is not immediately visible in your current observation. The skill is triggered after an initial scan of nearby areas fails to reveal the target.
## Core Procedure
1. **Identify Target**: Confirm the exact name of the receptacle you need to find (e.g., from the task: "put a cool lettuce in garbagecan" -> target is `garbagecan 1`).
2. **Initial Check**: Quickly examine the most common or nearby receptacles mentioned in the initial observation (e.g., countertops, tables, open cabinets).
3. **Systematic Search**: If not found, begin a systematic exploration:
- Use the `go to {recep}` action to navigate to candidate locations.
- Prioritize receptacles that are typically in the environment (cabinets, countertops, tables).
- If a candidate is closed (e.g., "The cabinet 2 is closed."), you may skip opening it unless the target could logically be inside. The trajectory shows that the target receptacle (`garbagecan 1`) was not inside any closed cabinet.
4. **Persistence**: Continue the search until the target is found. The trajectory demonstrates checking 20 cabinets before finally locating the garbage can.
5. **Output**: Once found, note the receptacle's location and state (e.g., "On the garbagecan 1, you see nothing."). You are now ready to use this receptacle for the next task action (e.g., `put lettuce 1 in/on garbagecan 1`).
View the complete source on GitHubalfworld-search-pattern-executor
When your agent uses it
Systematically searches a sequence of likely locations for a target object based on common sense. Use when you need to find a specific object and know which receptacles to check but not which one contains it. Takes a list of candidate receptacles, orchestrates navigation and inspection, and outputs when the target is found or all locations are exhausted.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
588 tokensWhen the skill is activated
Reference documents
505 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Action Format
- Key Rules
- Example
Files
SKILL.mdcore2,400 bytesreferences/common_sense_locations.mddoc1,878 bytes
Read SKILL.md
# Instructions
For each candidate receptacle in order, execute this action sequence:
## Workflow
1. **Navigate:** `go to {receptacle}`
2. **Open if closed:** If observation says "{receptacle} is closed", execute `open {receptacle}`
3. **Inspect:** Read the observation for the target object name
4. **If found:** Execute `take {target_object} from {receptacle}` and stop searching
5. **If not found:** If you opened the receptacle, execute `close {receptacle}`, then continue to the next candidate
6. **If all exhausted:** Report that the target was not found in any candidate location
## Action Format
- `go to {receptacle}` -- navigate to a location
- `open {receptacle}` -- open a closed drawer/cabinet/fridgeView the complete source on GitHubalfworld-search-verifier
When your agent uses it
Re-examines previously visited locations to confirm the absence of a target object or to check for overlooked items. Use when an initial search fails to find enough objects or when double-checking is required before concluding task failure. Systematically revisits receptacles, re-opens closed containers, and re-inspects contents to ensure no viable location was missed.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
705 tokensWhen the skill is activated
Reference documents
596 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Procedure
- Example
- Thought Process Template
Files
SKILL.mdcore3,107 bytesreferences/alfworld_actions_ref.mddoc2,597 bytes
Read SKILL.md
# Instructions
**Trigger Condition:** Use this skill when an initial search for a target object (e.g., `cellphone`) has been performed but the required quantity has not been found, or when you need to verify that no viable location was missed before task failure.
## Core Procedure
1. **Initialize Tracking:** Maintain a mental or explicit list of all receptacles (`recep`) you have already visited during your initial search (e.g., `sidetable 1`, `shelf 1-8`, `drawer 1`, `drawer 2`, `desk 1`).
2. **Systematic Revisit:** Do not search new, unvisited locations. Instead, systematically return to each previously visited receptacle in a logical order (e.g., by proximity or by the original search sequence).
* **Action:** Use `go to {recep}` to navigate.
* **For Closed Receptacles:** If a receptacle was closed during the initial search and you opened it, it may be closed again. Re-open it to verify its contents.
* **Action:** Use `open {recep}`.
* **For Open/Empty Receptacles:** Observe the contents again. The state may have changed, or an item may have been overlooked.
* **Action:** No action needed; read the `Observation`.
View the complete source on GitHubalfworld-storage-explorer
When your agent uses it
Systematically explores storage receptacles (drawers, cabinets, shelves) to find an appropriate placement location for an object. Use when the agent needs to store an item but the exact target receptacle is unknown or ambiguous. Opens, inspects, and closes candidate receptacles to assess suitability, then places the object in the best match.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
700 tokensWhen the skill is activated
Reference documents
527 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Strategy
- Execution Pattern
- Key Considerations
- Error Handling
- Example
- Output Format
Files
SKILL.mdcore3,127 bytesreferences/storage_heuristics.mddoc2,399 bytes
Read SKILL.md
# Skill: Storage Explorer
## When to Use
Activate this skill when:
1. You have an object that needs to be stored/placed.
2. The exact target receptacle is unspecified or ambiguous.
3. You need to validate if a potential receptacle is appropriate before placing the object.
## Core Strategy
1. **Prioritize Exploration**: When the target location is unclear, systematically check available storage receptacles.
2. **Inspect Before Placing**: Always open and examine a receptacle's contents before deciding to place your object there.
3. **Maintain Environment State**: Close receptacles after inspection unless you're placing the object inside.
## Execution Pattern
Follow this decision flow:View the complete source on GitHubalfworld-task-verifier
When your agent uses it
Use when the agent needs to check whether an ALFWorld task objective has been met after completing a sub-action (e.g., placing an object). This skill parses the task goal, evaluates the latest environment observation, and outputs a verification decision — task complete, task incomplete, or action ineffective — to guide the next step.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
670 tokensWhen the skill is activated
Reference documents
1,132 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Workflow
- Example
- Error Handling
Files
SKILL.mdcore3,022 bytesreferences/task_grammar.mddoc2,098 bytesreferences/verification_examples.mddoc2,369 bytes
Read SKILL.md
# Skill: Task Verifier for ALFWorld
## When to Use
Trigger this skill when:
1. The agent has just completed a key sub-action (e.g., `put {obj} in/on {recep}`)
2. The agent needs to determine whether the overall task goal is satisfied
3. The agent must decide whether to continue searching or conclude the task
## Core Workflow
### 1. Parse the Task Goal
Extract from the original task description:
- **Target object(s)**: What needs to be found/placed (including quantity)
- **Target receptacle**: Where objects must end up
- **Required transformations**: Any cleaning, heating, or cooling stepsView the complete source on GitHubalfworld-temperature-regulator
When your agent uses it
Manages the temperature state of an object by placing it into an appropriate appliance (fridge for cooling, microwave for heating). Use when the task requires modifying an object's temperature property, such as "cool some bread" or "heat some food". Takes the object identifier, temperature-modifying receptacle, and final target receptacle as inputs, and outputs the object at the target location with its temperature state changed.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
845 tokensWhen the skill is activated
Reference documents
630 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Input Validation & Planning
- 2. Execution Sequence
- 3. Error Handling & Observations
- 4. Example
- 5. Completion
Files
SKILL.mdcore3,429 bytesreferences/action_spec.mddoc565 bytesreferences/troubleshooting.mddoc1,874 bytes
Read SKILL.md
# Instructions
This skill executes a sequence to change an object's temperature by placing it in a specific receptacle (e.g., fridge for cooling, microwave for heating) and then relocating it to a final target location.
## 1. Input Validation & Planning
* **Inputs Required:** The `object` identifier (e.g., `bread 1`) and the `temperature_receptacle` identifier (e.g., `fridge 1` for cooling, `microwave 1` for heating). The final `target_receptacle` (e.g., `diningtable 1`) is also required.
* **Verify** the provided object and receptacles exist in the agent's current observation. If not, the agent must first navigate to locate them.
* **Plan** the sequence: Locate object -> Pick up object -> Navigate to temperature receptacle -> Open it (if closed) -> Place object inside -> Close receptacle (optional, based on environment feedback) -> Navigate to target receptacle -> Place object there.
## 2. Execution Sequence
Follow this core logic. Use deterministic scripts for error-prone steps (see `scripts/`).
1. **Acquire Object:** `go to` the object's location, then `take {object} from {recep}`.
2. **Apply Temperature Effect:**
* `go to {temperature_receptacle}`.
* If the receptacle is reported as "closed", `open {temperature_receptacle}`.
* `put {object} in/on {temperature_receptacle}`.View the complete source on GitHubalfworld-tool-locator
When your agent uses it
Searches for a specified tool or device (e.g., a desklamp, knife, or sponge) within the ALFWorld environment by checking relevant surfaces. Use when you need a tool to interact with another object as part of a task but the tool is not in your inventory or immediate vicinity. Takes a tool name as implicit input and navigates to likely storage spots (sidetables, shelves, countertops) until the tool is found.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
560 tokensWhen the skill is activated
Reference documents
1,042 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Action Format
- Error Recovery
- Example
Files
SKILL.mdcore2,201 bytesreferences/alfworld_actions.mddoc1,704 bytesreferences/tool_categories.mddoc2,272 bytes
Read SKILL.md
# Instructions
Locate a specified tool or device by systematically checking receptacles where it is likely stored.
## Workflow
1. **Prioritize search locations** based on tool type:
- Small tools/electronics (desklamp, remotecontrol): `sidetable`, `desk`, `drawer`, `shelf`
- Kitchen tools (knife, spatula): `countertop`, `cabinet`, `drawer`
- Cleaning tools (sponge, spraybottle): `shelf`, `cabinet`, `countertop`
- Default: check all visible receptacles in order
2. **Navigate** to each prioritized receptacle: `go to {receptacle}`
3. **Inspect** the observation for the target tool name
4. **If found:** Stop searching. Proceed to use the tool for the main task
5. **If not found:** Continue to the next receptacle in the priority list
6. **If exhausted:** Expand search to remaining receptacles not yet checkedView the complete source on GitHubalfworld-tool-user
When your agent uses it
Use when the agent needs to apply a tool to a target object in ALFWorld to accomplish an interaction such as cleaning, heating, cooling, or examining. This skill handles locating both the tool and target object, then executing the correct environment action (e.g., `clean`, `heat`, `cool`, `use`) to progress the task.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
755 tokensWhen the skill is activated
Reference documents
745 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Workflow
- Error Handling
- Example
Files
SKILL.mdcore2,863 bytesreferences/action_reference.mddoc1,538 bytesreferences/trajectory_example.mddoc1,289 bytes
Read SKILL.md
# Skill: Tool User for ALFWorld
## When to Use
Trigger this skill when:
1. A task requires applying a tool to an object (e.g., cleaning a knife with a sinkbasin, heating food with a microwave)
2. Both the tool and target object are in the agent's possession or within reach
3. The agent knows which interaction verb to use for the task context
## Core Workflow
### 1. Identify Requirements
- Parse the task to determine:
- **Target object**: The item to be acted upon (e.g., `knife 1`, `potato 2`)
- **Required tool**: The appliance or instrument needed (e.g., `sinkbasin 1`, `microwave 1`)
- **Interaction type**: The action verb (`clean`, `heat`, `cool`, `use`, `examine`)View the complete source on GitHubscienceworld-ambiguous-action-resolution
When your agent uses it
Use when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. This skill resolves the disambiguation by selecting the lowest available number (typically 0) to proceed, ensuring task progression when multiple identical object instances exist and the system cannot automatically determine which instance to act upon.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
689 tokensWhen the skill is activated
Reference documents
48 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
- Anti-Patterns
Files
SKILL.mdcore3,187 bytesreferences/trajectory_examples.mddoc292 bytes
Read SKILL.md
# Skill: scienceworld-ambiguous-action-resolution
## Purpose
Resolve system disambiguation prompts that block task progression when the ScienceWorld environment cannot determine which identical object instance the agent intends to act upon. This is a mechanical bypass, not a decision-making step.
## When to Use
- When the environment returns an observation containing `"Ambiguous request: Please enter the number for the action you intended (or blank to cancel):"` followed by a numbered list
- When multiple identical object instances exist (e.g., five identical banana seeds in a jar) and the system requires explicit selection
- Only when options are functionally identical -- do NOT use this skill for menu selections where options have different meanings
## Workflow
1. **Recognize the prompt** -- Identify the exact phrase: `"Ambiguous request: Please enter the number for the action you intended (or blank to cancel):"`.View the complete source on GitHubscienceworld-animal-identifier
When your agent uses it
Use when the agent needs to locate, identify, and focus on a specific animal or biological entity in the ScienceWorld environment. This skill handles tasks involving animal comparison, examination, or interaction (such as determining lifespan extremes) by navigating to the correct location with "teleport to", surveying with "look around", and executing "focus on ANIMAL" with the exact entity name.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
629 tokensWhen the skill is activated
Reference documents
358 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
Files
SKILL.mdcore2,808 bytesreferences/action_primer.mddoc1,539 bytes
Read SKILL.md
# Skill: scienceworld-animal-identifier
## Purpose
Locate and focus on a specified animal or biological entity within the ScienceWorld environment for tasks involving animal comparison, examination, or interaction (e.g., determining lifespan extremes, identifying species).
## When to Use
- When a task requires finding and focusing on a specific animal or biological entity
- When comparing attributes (lifespan, size, type) across multiple animals
- When the task instructs examining or interacting with an animal in a specific location
## Workflow
1. **Navigate to the target location** -- If the animal is in a specific room (e.g., "outside", "greenhouse"), execute `teleport to <LOCATION>`.View the complete source on GitHubscienceworld-circuit-builder
When your agent uses it
This skill constructs a simple electrical circuit by connecting components like batteries, wires, and light bulbs. Use when the agent needs to test electrical conductivity or create a functional circuit for an experiment. The input is a set of available components, and the output is a fully connected circuit ready for activation.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
863 tokensWhen the skill is activated
Reference documents
15 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Objective
- 2. Prerequisites & Setup
- 3. Core Procedure
- 4. Testing & Conclusion
- 5. Key Principles
- 6. Example
Files
SKILL.mdcore3,340 bytesreferences/circuit_schematic.mddoc65 bytes
Read SKILL.md
# Instructions
## 1. Objective
Your goal is to build a functional electrical circuit to test the conductivity of a target object (e.g., a metal pot). The circuit's success is indicated by a light bulb turning on.
## 2. Prerequisites & Setup
* **Location:** You must be in the **workshop**. If not, teleport there.
* **Components:** Ensure the following are present on the table:
* A battery
* A light bulb (e.g., blue light bulb)
* At least two wires (e.g., orange, yellow, green)
* The target object to test (e.g., metal pot)
* A blue box (for conductive objects) and an orange box (for non-conductive objects)
* **Inventory:** The target object must be in your inventory. If not, locate and pick it up.
View the complete source on GitHubscienceworld-circuit-connector
When your agent uses it
This skill connects two electrical components (e.g., wires, batteries, devices) by their terminals to build or modify a circuit. Use when constructing electrical setups for testing, such as conductivity checks or device activation. The input includes two component identifiers and their connection points, and the output is an established electrical connection.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
543 tokensWhen the skill is activated
Reference documents
469 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Primary Action
- When to Use
- Procedure
- Key Principles
- Related Skills
Files
SKILL.mdcore2,497 bytesreferences/circuit_basics.mddoc1,788 bytes
Read SKILL.md
# Instructions
## Primary Action
Execute the `connect OBJ to OBJ` action. The syntax is `connect <ComponentA> <TerminalA> to <ComponentB> <TerminalB>`.
## When to Use
Use this skill when you need to establish an electrical connection between two components as part of building a circuit for testing or device operation. Common scenarios include:
* Building a circuit to test a material's conductivity.
* Connecting a power source (battery) to a load (light bulb, buzzer).
* Integrating a switch or sensor into a circuit.
## Procedure
1. **Identify Components:** Locate the two components you need to connect (e.g., `battery`, `black wire`, `unknown substance M`, `electric buzzer`).
2. **Identify Terminals:** Examine the components if necessary to determine their available connection points (e.g., `anode`, `cathode`, `terminal 1`, `terminal 2`).
3. **Formulate Command:** Construct the `connect` command using the pattern: `connect <ComponentA> <TerminalA> to <ComponentB> <TerminalB>`.View the complete source on GitHubscienceworld-conditional-box-placer
When your agent uses it
Moves an object to one of two destination containers based on a numeric threshold check. Trigger after a measurement (e.g., temperature) is taken. Place object in 'green' box if value > threshold, or 'blue' box if value < threshold.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
447 tokensWhen the skill is activated
Reference documents
210 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Required Parameters (Pass via Thought/Action)
- Example Invocation Thought
- Action Template
Files
SKILL.mdcore1,993 bytesreferences/action_primer.mddoc860 bytes
Read SKILL.md
# Skill: Conditional Box Placer
## Purpose
Execute a conditional placement task based on a measured numeric value. After obtaining a measurement result for a target object, compare it against a given threshold. Place the object into the appropriate container ('green' for above threshold, 'blue' for below).
## Core Workflow
1. **Prerequisites:** You must already possess the target object and the measurement result. You must also know the locations of the 'green box' and 'blue box'.
2. **Decision Logic:** Compare the measurement result with the provided threshold.
- If `measurement_result > threshold`: Destination is the **green box**.
- If `measurement_result < threshold`: Destination is the **green box**.
3. **Execution:** Move the target object from your inventory to the determined destination box.
## Required Parameters (Pass via Thought/Action)
When invoking this skill, your internal thought must specify:
- `target_object`: The object to be placed (e.g., "unknown substance B").View the complete source on GitHubscienceworld-conditional-focus-executor
When your agent uses it
Executes a 'focus on OBJ' action on a specific object based on the outcome of a prior conditional evaluation. Use when you have a measurement result and task instructions specify focusing on different objects (e.g., colored boxes) depending on whether the result meets a threshold.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
498 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,233 bytesreferences/action_primer.mddoc2,033 bytes
Read SKILL.md
# Conditional Focus Executor
## When to Use
Use after completing a measurement (temperature, pH, mass) when the task specifies a conditional rule like "If result > X, focus on A; otherwise, focus on B."
## Procedure
1. **Evaluate the condition** against your measurement result.
2. **Determine the target object** based on which branch is true.
3. **Execute:** `focus on <TARGET_OBJECT>`
4. **Verify:** Confirm the focus action succeeded before proceeding.
If the focus action fails (e.g., object not found), use `look around` to verify the target object name matches exactly.
## Example
**Task:** "If the temperature of the substance is above 50C, focus on the red box. Otherwise, focus on the blue box."View the complete source on GitHubscienceworld-conditional-placer
When your agent uses it
Places an object into one of several designated containers based on a measured condition, such as a temperature threshold. Use this skill when you have completed a measurement or assessment and the task requires sorting or storing the object into one of multiple containers according to a rule (e.g., "if temperature > X, place in container A; otherwise container B").
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
518 tokensWhen the skill is activated
Reference documents
363 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore2,245 bytesreferences/action_guide.mddoc1,635 bytes
Read SKILL.md
# Skill: Conditional Object Placer
## Purpose
Place a target object into the correct container based on a measured condition (e.g., temperature threshold, conductivity result). This skill executes the full measure-then-sort workflow.
## Core Workflow
1. **Locate & Acquire Measurement Tool:** `teleport to LOC` then `pick up` the measurement device (e.g., thermometer).
2. **Locate & Acquire Target Object:** `teleport to LOC` then `pick up` the object to be measured (e.g., metal fork).
3. **Identify Target Containers:** Use `look around` to find the designated containers (e.g., blue box, orange box).
4. **Perform Measurement:** `use OBJ on OBJ` (e.g., `use thermometer on metal fork`) to obtain the value.
5. **Evaluate Condition & Place:** Compare the measured value against the threshold, then `move OBJ to OBJ` to place the object in the correct container.
## Key Actions
| Action | Purpose |
|--------|---------|View the complete source on GitHubscienceworld-conductivity-tester
When your agent uses it
Determines if an object is electrically conductive by integrating it into a circuit and observing a light bulb. Triggered when classifying an object based on conductivity.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
454 tokensWhen the skill is activated
Reference documents
143 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Objective
- Core Procedure
- Key Notes
Files
SKILL.mdcore1,888 bytesreferences/circuit_diagram.mddoc535 bytes
Read SKILL.md
# Instructions
## Objective
Classify a target object as **electrically conductive** or **non-conductive** by using it to complete a simple circuit with a battery and a light bulb.
## Core Procedure
1. **Locate & Acquire Object:** Teleport to the object's location and pick it up.
2. **Focus on Object:** Use the `focus` action on the object to signal intent.
3. **Setup in Workshop:** Teleport to the `workshop`. Place the object down.
4. **Construct Test Circuit:** Assemble the circuit on the table in this exact sequence:
a. Connect the **battery anode** to **orange wire terminal 1**.
b. Connect the **battery cathode** to **yellow wire terminal 1**.
c. Connect **orange wire terminal 2** to the **blue light bulb cathode**.
d. Connect **green wire terminal 2** to the **blue light bulb anode**.
e. Connect **yellow wire terminal 2** to **terminal 1** on the target object.View the complete source on GitHubscienceworld-container-inspector
When your agent uses it
Inspects the contents of a container or device using the 'look at' action. Use this skill when you need to verify what is inside a container (e.g., checking if lead is in the blast furnace), monitor the state of contents (e.g., solid vs. liquid phase changes), or confirm that a placement or process step succeeded. Returns a detailed list of contents and their states for process monitoring.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
769 tokensWhen the skill is activated
Reference documents
48 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Instruction
- Expected Output & Interpretation
- Example from Trajectory
- Integration with Other Actions
- Error Handling
Files
SKILL.mdcore3,213 bytesreferences/container_inspection_examples.mddoc245 bytes
Read SKILL.md
# Skill: Container/Device Inspector
## When to Use
Trigger this skill when you need to:
1. **Verify Placement:** Confirm an object has been successfully moved into a target container (e.g., "Is the metal pot in the blast furnace?").
2. **Monitor State Change:** Check if the contents of a container have changed state due to a process (e.g., "Has the lead melted into liquid lead?").
3. **Inventory Check:** List all items currently stored inside an open container or device.
## Core Instruction
**Always use the exact action:** `look at <CONTAINER_NAME>`
- Replace `<CONTAINER_NAME>` with the precise name of the target object (e.g., `blast furnace`, `cupboard`, `tin cup`).
- This action returns a structured observation detailing the container's state and a list of its contents.
## Expected Output & Interpretation
The observation will follow this general pattern:View the complete source on GitHubscienceworld-container-item-retriever
When your agent uses it
This skill retrieves a specified item from a container by using the 'pick up' action. It should be triggered when the agent has identified a needed item inside an open container (e.g., a jar, box, or hive) and must transfer it to inventory for later use. The skill handles the object transfer, assuming the container is already accessible, and outputs confirmation that the item is now in the agent's inventory.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
502 tokensWhen the skill is activated
Reference documents
489 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Trigger Conditions
- Core Action
- Execution Workflow
- Important Notes
- Example
Files
SKILL.mdcore2,251 bytesreferences/execution_examples.mddoc2,079 bytes
Read SKILL.md
# Skill: Retrieve Item from Container
## Purpose
Transfer a specified item from an open, accessible container into the agent's inventory using the `pick up` action.
## Trigger Conditions
Use this skill when **all** of the following are true:
1. The agent has identified a specific item needed for a task.
2. The item is located inside a container (e.g., jar, box, hive, closet).
3. The container is already open and accessible (no `open` action required).
4. The agent's immediate goal is to possess the item for later use.
## Core Action
Execute the `pick up <ITEM>` action, where `<ITEM>` is the exact name of the target object as observed in the environment.
View the complete source on GitHubscienceworld-container-relocator
When your agent uses it
Moves an object from inventory to a specified container in a target room. Use when the task requires placing an item into a particular receptacle (e.g., 'move it to the orange box').
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
203 tokensWhen the skill is activated
Reference documents
424 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Procedure
- Example Flow (from trajectory)
Files
SKILL.mdcore834 bytesreferences/action_primer.mddoc1,701 bytes
Read SKILL.md
# Skill: Container Relocator
## Procedure
1. Confirm the object is in your inventory. If not, acquire it first.
2. `teleport to <ROOM>` — navigate to the room containing the target container.
3. `move <OBJECT> to <CONTAINER>` — transfer the object to the destination.
4. `look at <CONTAINER>` — verify the object is now inside.
## Example Flow (from trajectory)
1. Task: "move it to the orange box in the workshop."
2. Identify: Object = dove egg (in inventory), Container = orange box, Room = workshop.
3. Action: `teleport to workshop`
4. Action: `move dove egg to orange box`View the complete source on GitHubscienceworld-container-transfer
When your agent uses it
Moves a substance or object from one container to another (e.g., moving lead to a metal pot). Use this skill when you need to prepare materials for processing, such as transferring a substance into a heat-resistant container before heating, or reorganizing materials between vessels for mixing or measurement.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
408 tokensWhen the skill is activated
Reference documents
398 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore1,870 bytesSKILL.mdcore1,870 bytesreferences/container_properties.mddoc1,855 bytes
Read SKILL.md
# Skill: Container Transfer
## Purpose
Transfer a target substance or object from a source container to a destination container. This is a foundational step for preparing materials for heating, mixing, or measurement.
## Core Workflow
1. **Assess Need:** Determine if the current container is unsuitable for the next operation (e.g., tin cup is not heat-resistant for a furnace).
2. **Locate Items:** Use `look around` and `look at OBJ` to find the target substance and a suitable destination container.
3. **Execute Transfer:** `move <SUBSTANCE> to <DESTINATION>`.
4. **Verify:** `look at <DESTINATION>` to confirm the substance is now inside.
## Key Actions
| Action | Purpose |
|--------|---------|
| `look around` | Survey room for containers and substances |View the complete source on GitHubcontrolled-waiting
When your agent uses it
Executes timed waiting using 'wait' or 'wait1' actions to advance the simulation clock. Use when a time-dependent process like plant growth, chemical reaction, or mechanical cycle must progress before you can continue the task.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
319 tokensWhen the skill is activated
Reference documents
342 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,351 bytesreferences/botanical_growth_patterns.mddoc1,537 bytes
Read SKILL.md
# Skill: Controlled Waiting
## When to Use
After initiating a process with a time delay, when no other productive actions are possible.
## Procedure
1. Confirm the process is active (seeds planted, device activated, etc.).
2. `wait` (advances 10 steps) for long processes, or `wait1` (1 step) for fine-grained observation.
3. `look around` or `examine <OBJECT>` to check if the target state has been reached.
4. If not reached, repeat steps 2-3. If reached, exit and resume the main task.
**Duration guidance:** Use `wait` for biological growth stages. Use `wait1` when observing rapid changes or when close to the expected transition.
## Example
**Task:** Wait for a banana tree to produce fruit after planting.View the complete source on GitHubscienceworld-device-activator
When your agent uses it
Activates a device (e.g., blast furnace, stove) to initiate a process like heating. Use this skill when you have placed materials inside a device and need to start its operation. Takes a device name as input and outputs a confirmation of activation, enabling tasks that require energy input or material processing to progress.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
460 tokensWhen the skill is activated
Reference documents
357 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore1,974 bytesreferences/device_specifications.mddoc1,652 bytes
Read SKILL.md
# Skill: Device Activator
## Purpose
Activate a device (turn it on, start it, fire it up) to begin its operation — typically heating, processing, or powering a task step.
## Core Workflow
1. **Verify Contents:** `look at <DEVICE_NAME>` to confirm materials are placed inside.
2. **Check State:** Observation should show "which is turned off" or "which is deactivated."
3. **Activate:** `activate <DEVICE_NAME>`
4. **Verify Activation:** `look at <DEVICE_NAME>` — confirm it now reads "turned on" or "activated."
5. **Monitor (if needed):** Use measurement tools (e.g., `use thermometer on <MATERIAL>`) to track progress.
6. **Deactivate When Done:** `deactivate <DEVICE_NAME>`
## Key Actions
| Action | Purpose |View the complete source on GitHubscienceworld-environment-isolation
When your agent uses it
Use when you need to isolate a space (like a greenhouse) by closing doors or openings to create a contained environment. Trigger before starting pollination, temperature-sensitive experiments, or other environmental-sensitive tasks that require controlled conditions. Modifies room connectivity to optimize conditions for specific processes.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
644 tokensWhen the skill is activated
Reference documents
219 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Action Sequence
- Key Principles
- Notes
- Example
Files
SKILL.mdcore2,956 bytesreferences/action_primer.mddoc998 bytes
Read SKILL.md
# Instructions
## When to Use
Trigger this skill when you need to:
1. **Optimize Pollination:** Isolate a room (like a greenhouse) to concentrate pollinators (e.g., bees) and prevent them from leaving, thereby increasing the chance of successful cross-pollination between plants.
2. **Control Environmental Factors:** Create a stable, contained space to manage variables like temperature, humidity, or airflow for a sensitive process.
3. **Prevent Contamination or Interference:** Seal off a room to protect an ongoing experiment or task from external disturbances.
## Core Action Sequence
1. **Assess the Environment:** Use `look around` to identify all doors, windows, or other openings in the current room.
2. **Execute Isolation:** For each identified opening (e.g., "door to the outside", "door to the hallway"), issue a `close` command.
* **Example:** `close door to outside`
* **Example:** `close door to hallway`
3. **Verify Closure:** Perform a final `look around` to confirm all intended openings are now closed and the room is successfully isolated.
View the complete source on GitHubscienceworld-environment-scanner
When your agent uses it
This skill performs an initial observation of the current location to identify available objects, containers, and connections to other rooms. Use this when starting a new task in ScienceWorld to gather situational awareness, especially when the agent needs to understand its surroundings before taking action. It outputs a detailed room description, listing visible items and accessible doors.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
253 tokensWhen the skill is activated
Reference documents
262 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Action
- Output Interpretation
- Example Output Format
Files
SKILL.mdcore1,331 bytesreferences/action_primer.mddoc1,156 bytes
Read SKILL.md
# Instructions
Execute this skill when you first arrive at a location in ScienceWorld or when you need to refresh your understanding of the current environment.
## Core Action
1. **Always begin by using the `look around` action.** This is the primary and mandatory step of this skill. It provides the foundational observation of the room.
## Output Interpretation
After executing `look around`, analyze the observation. Your analysis must structure the output clearly:
* **Current Room:** State the name of the room you are in.
* **Visible Objects & Substances:** List all items and substances reported in the observation.
* **Accessible Doors:** List all doors mentioned, noting their destination and whether they are open or closed.
* **Initial Assessment:** Briefly note any items of immediate interest or relevance to your known task.
## Example Output FormatView the complete source on GitHubscienceworld-growth-focuser
When your agent uses it
Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the ScienceWorld environment.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
768 tokensWhen the skill is activated
Reference documents
370 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Instruction
- Key Considerations
- Example
- Quick Reference
Files
SKILL.mdcore3,348 bytesreferences/trajectory_analysis.mddoc1,689 bytes
Read SKILL.md
# Skill: Growth Focuser
## Purpose
Apply the `focus on` action to a specific biological entity (e.g., a planted seed or growing plant) to signal your intent to monitor its development. This action is often a prerequisite for the environment to process growth stages or trigger life cycle progression events.
## When to Use
Use this skill when:
1. **After Planting:** You have just placed a seed or seedling into a suitable growth medium (e.g., soil with water).
2. **Stage Monitoring:** You need to check or trigger a progression in the plant's life cycle (e.g., from seed to sprout, sprout to mature plant, flowering, or reproduction).
3. **Intent Signaling:** The task requires you to explicitly indicate which entity you are observing or nurturing.
## Core Instruction
1. **Identify the Target:** Locate the specific plant or seed you intend to focus on. Ensure it is in a valid state for growth (e.g., planted in soil with water).
2. **Execute Focus:** Use the action: `focus on <PLANT_OBJECT> [in <CONTAINER>]`.
* Replace `<PLANT_OBJECT>` with the exact name of the biological entity (e.g., `avocado seed`).View the complete source on GitHubscienceworld-heating-apparatus-setup
When your agent uses it
This skill positions a container with a substance onto a heating device (stove, oven) and activates the device. It should be triggered when a task requires melting, boiling, or heating a substance. The skill moves the prepared container to the heating element and turns it on.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
654 tokensWhen the skill is activated
Reference documents
398 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Prerequisites
- Core Procedure
- Post-Setup & Monitoring
- Error Handling & Notes
Files
SKILL.mdcore2,936 bytesreferences/thermal_procedures.mddoc1,881 bytes
Read SKILL.md
# Instructions
## Purpose
This skill automates the setup of a heating apparatus for scientific experiments involving melting, boiling, or heating a substance. It handles the positioning of a prepared container onto a heating element and the activation of the device.
## Prerequisites
1. **Target Substance:** The substance to be heated (e.g., chocolate, water) must be located and identified.
2. **Suitable Container:** A compatible, heat-safe container (e.g., metal pot, beaker) must be available in the environment.
3. **Heating Device:** A functional heating device (e.g., stove, oven) must be present and accessible.
4. **Location:** The agent should be in the same room as the required items (kitchen, workshop, etc.).
## Core Procedure
Follow this sequence to execute the skill. Use the bundled `setup_heater.py` script for reliable, error-prone steps (1-4).
1. **Prepare the Substance:** Ensure the target substance is placed into the chosen container.View the complete source on GitHubscienceworld-instruction-reader
When your agent uses it
Reads a recipe or note from the inventory using the 'read' action and extracts key information. Use this skill when you have acquired a recipe, note, or readable document in your inventory and need to extract explicit instructions, ingredient lists, or procedural steps before executing a task.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
368 tokensWhen the skill is activated
Reference documents
245 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Workflow
- Example
Files
SKILL.mdcore1,686 bytesreferences/action_primer.mddoc1,059 bytes
Read SKILL.md
# Skill: Instruction Reader
## Purpose
Read and parse a document (recipe, note, or instructions) from your inventory to extract the information needed to execute the current task.
## When to Use
- After picking up a recipe, note, or readable document.
- When the task requires following written instructions (e.g., mixing chemicals, assembling components).
- Before starting a multi-step procedure that depends on written directions.
## Core Workflow
1. **Read the Document:** `read OBJ` on the document in your inventory.
2. **Extract Key Information:**
- **Goal:** The final product or objective (e.g., "make salt water").
- **Required Components:** Items or substances needed (e.g., "sodium chloride, water").View the complete source on GitHubscienceworld-inventory-focus
When your agent uses it
Use when the agent needs to confirm and prepare a specific inventory item before using it in an experiment or task step. This "focus on [ITEM] in inventory" action verifies the correct item has been collected and signals intent, ensuring operational readiness for subsequent actions like measurement, combination, or placement.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
513 tokensWhen the skill is activated
Reference documents
241 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Important Notes
Files
SKILL.mdcore2,369 bytesreferences/action_context.mddoc1,051 bytes
Read SKILL.md
# Skill: scienceworld-inventory-focus
## Purpose
Confirm and prepare an inventory item before using it in a ScienceWorld task. The `focus on [ITEM] in inventory` action verifies the item's presence and signals intent, reducing errors in multi-step experimental procedures.
## When to Use
- After picking up an item that will be used in a subsequent critical action (measurement, combination, connection)
- When verifying the correct object has been collected before proceeding
- Before using a tool on a target object, to prepare both tool and target
## Workflow
1. **Acquire the item** -- Ensure the target item is in inventory (e.g., `pick up thermometer`).View the complete source on GitHubscienceworld-inventory-manager
When your agent uses it
Handles picking up objects from the environment into the agent's inventory or moving them out to containers. Use this skill when you need to acquire an object for later use (pick up) or place an object into a specific container as part of a task requirement (move). Takes an object name and location as input and confirms the transfer to or from inventory.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
413 tokensWhen the skill is activated
Reference documents
375 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Examples
- Important Notes
Files
SKILL.mdcore1,829 bytesreferences/environment_actions.mddoc1,691 bytes
Read SKILL.md
# Skill: Inventory Manager
## Purpose
Manage the agent's inventory: pick up objects from the environment or place them into containers.
## Core Workflow
1. **Locate Object:** Use `look around` to confirm the object is present and note its exact name.
2. **Acquire:** `pick up OBJ` to move the object into your inventory.
3. **Place (if needed):** `move OBJ to OBJ` to transfer the object to a container.
4. **Verify:** Check the observation feedback to confirm the action succeeded. If it fails, verify exact object names with `look around`.
## Key Actions
| Action | Purpose |
|--------|---------|
| `look around` | Find objects and confirm names |View the complete source on GitHubscienceworld-item-fetcher
When your agent uses it
Picks up a specified object from the environment and moves it into the agent's inventory. Use this skill when you identify a required tool or material (e.g., thermometer, metal pot) that needs to be collected for later use in an experiment or task. Takes an object name as input and confirms the item's transfer to inventory.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
492 tokensWhen the skill is activated
Reference documents
380 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Principles
- Example from Trajectory
- Input
- Output
Files
SKILL.mdcore2,199 bytesreferences/action_primer.mddoc1,726 bytes
Read SKILL.md
# Skill: Fetch and Inventory Item
## Purpose
Use this skill when you need to acquire a specific object for a task. It handles locating the object in the current environment and moving it into your inventory for later use.
## Core Workflow
1. **Identify Need:** Determine which object is required for your current or upcoming task (e.g., "thermometer", "metal pot").
2. **Locate Object:** Ensure you are in the correct room. Use `look around` to survey the environment and confirm the object is present and accessible.
3. **Execute Fetch:** Use the `pick up` action on the target object.
4. **Verify Success:** Confirm the system observation states the object has been moved to your inventory.
## Key Principles
* **Pre-check:** Always `look around` first to verify the object's presence and location (e.g., on a counter, in a container).
* **Direct Action:** Use the simple `pick up OBJ` command. Do not overcomplicate the sequence.
* **Inventory Focus:** After picking up the object, you may `focus on` it in your inventory to signal readiness for the next step in your main task.View the complete source on GitHubscienceworld-liquid-filler
When your agent uses it
This skill fills a container with liquid from a source by first placing the container at the source, then activating the source (e.g., turning on a sink), and finally deactivating it. It should be triggered when the agent has an empty or partially filled container and needs to add a liquid component. The skill results in the container containing the liquid, ready for mixing or further use.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
613 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Identify the Goal
- 2. Prerequisites & Initial State
- 3. Core Procedure
- 4. Verification & Next Steps
- 5. Important Notes
Files
SKILL.mdcore2,619 bytesSKILL.mdcore2,619 bytesSKILL.mdcore2,619 bytesSKILL.mdcore2,619 bytesSKILL.mdcore2,619 bytes
Read SKILL.md
# Instructions
## 1. Identify the Goal
Your goal is to fill a target container with a specific liquid from a source. This skill is triggered when you have a container (empty or partially filled) and need to add a liquid component to it.
## 2. Prerequisites & Initial State
Before executing this skill, ensure you have:
* **A Target Container:** The container you wish to fill (e.g., a cup, bowl, jug). It should be in your inventory.
* **A Liquid Source Identified:** You must know the location of a functional liquid source (e.g., a sink, a jug containing liquid, a toilet with water). Use the `look around` and `examine` actions to find one.
## 3. Core Procedure
Execute the following sequence of actions precisely:
1. **Position the Container:** Move the target container to the liquid source.
* **Action:** `move <CONTAINER> to <SOURCE>`View the complete source on GitHubscienceworld-liquid-pourer
When your agent uses it
Transfers the contents of a source liquid container into a target container for mixing or preparation. Use this skill when you need to combine multiple substances (such as paints or chemicals) into a single vessel, or when a liquid must be moved from one container to another before processing.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
438 tokensWhen the skill is activated
Reference documents
210 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore1,992 bytesSKILL.mdcore1,992 bytesSKILL.mdcore1,992 bytesSKILL.mdcore1,992 bytesSKILL.mdcore1,992 bytesreferences/action_primer.mddoc939 bytes
Read SKILL.md
# Skill: Liquid Pourer
## Purpose
Transfer a liquid from a source container to a target container, typically as a preparatory step for mixing or chemical combination.
## When to Use
- Combining multiple liquids or substances into one vessel for mixing.
- Moving a liquid to a more suitable container before heating or processing.
- Preparing ingredients for a recipe that requires pouring.
## Core Workflow
1. **Identify Containers:** Use `look around` to locate the source container (with the liquid) and the target container (destination vessel).
2. **Perform Transfer:** `pour OBJ into OBJ` with precise object identifiers.
3. **Verify:** `look at OBJ` on the target container to confirm the transfer succeeded.
View the complete source on GitHubscienceworld-liquid-source-finder
When your agent uses it
This skill searches rooms for a liquid source (e.g., sink, toilet, jug) by sequentially surveying different locations. It should be triggered when the task requires obtaining a liquid (like water) and the agent does not have immediate access to it. The skill involves teleporting to candidate rooms, looking around, and identifying potential sources, guiding the agent toward the nearest available liquid.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
710 tokensWhen the skill is activated
Reference documents
536 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Procedure
- Key Principles
- Quick Reference
Files
SKILL.mdcore3,006 bytesSKILL.mdcore3,006 bytesSKILL.mdcore3,006 bytesSKILL.mdcore3,006 bytesSKILL.mdcore3,006 bytesreferences/action_glossary.mddoc1,116 bytesreferences/room_priority.mddoc1,214 bytes
Read SKILL.md
# Skill: Liquid Source Finder
## When to Use
Activate this skill when your primary task requires a liquid (e.g., water, juice, paint) and you have confirmed it is not present in your current inventory or immediate vicinity.
## Core Procedure
1. **Initiate Search:** If no liquid source is visible, begin a systematic room survey.
2. **Prioritize Rooms:** Teleport to and survey rooms in this order of likelihood:
* **Kitchen** (high priority - contains sink, fridge, cups)
* **Bathroom** (high priority - contains sink, toilet, bathtub)
* **Greenhouse** (medium priority - contains sink, jugs)
* **Workshop** (medium priority - may contain specialized containers)
* **Art Studio** (low priority - may contain paint or water for cleaning)
* **Living Room, Bedroom, Hallway** (low priority - check for any containers)
3. **Survey Each Room:**View the complete source on GitHubscienceworld-living-entity-identifier
When your agent uses it
Analyzes room observations to identify potential living things (e.g., eggs, plants, animals) among listed objects. Use this skill when a task involves finding, focusing on, or interacting with a living thing, biological entity, or organism. Processes observation text, flags candidate living items based on domain knowledge, and outputs a focused target for subsequent actions like focus on or pick up.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
507 tokensWhen the skill is activated
Reference documents
541 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore2,125 bytesreferences/action_sequences.mddoc143 bytesreferences/living_indicators.mddoc1,941 bytes
Read SKILL.md
# Skill: Living Entity Identifier
## Purpose
Identify living things (eggs, plants, animals) from room observations and focus on them for task progression.
## Core Workflow
1. **Survey Room:** `look around` to get the observation text listing all objects.
2. **Identify Candidates:** Scan the object list for living entity indicators:
- **Animals:** dove, giant tortoise, bee, frog, fish
- **Eggs:** dove egg, chicken egg, turtle egg
- **Plants:** flower, tree, moss, fern, algae
- **Other biological:** mushroom, seed, pollen
3. **Focus on Target:** `focus on [IDENTIFIED_OBJECT]` to signal task progress.
4. **Transport (if needed):** `pick up [OBJECT]` then `move [OBJECT] to [CONTAINER]`.
View the complete source on GitHubscienceworld-material-classifier
When your agent uses it
This skill makes a determination about a material's property (e.g., conductivity) based on environmental cues or domain knowledge when direct testing fails. Trigger it when experimental actions are invalid or unavailable, requiring a logical inference. It uses observed object properties and common-sense reasoning to classify the material and decide its final disposition.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
336 tokensWhen the skill is activated
Reference documents
290 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,605 bytesreferences/material_properties.jsonasset1,163 bytesreferences/material_properties.mddoc1,152 bytes
Read SKILL.md
# Material Classification Skill
## When to Use
Activate when direct experimental testing of a material property (conductivity, magnetism, etc.) fails or equipment is unavailable, and you need to classify the material by inference to complete a sorting task.
## Procedure
1. `focus on <OBJECT>` — identify the target and note its material composition.
2. Attempt direct testing if equipment exists (e.g., `connect <OBJECT> terminal 1 to <WIRE> terminal 2`).
3. If testing fails, infer the property from the object's material. Consult `references/material_properties.md` for lookup.
4. `move <OBJECT> to <CONTAINER>` — place in the appropriate classification container.
5. `look at <CONTAINER>` — verify the object was placed correctly.
## Example
**Task:** Classify a glass jar for electrical conductivity when the circuit test is unavailable.
1. `focus on glass jar`View the complete source on GitHubscienceworld-measurement-taker
When your agent uses it
Use when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a measurement tool. This skill covers acquiring the tool, preparing both tool and target with focus actions, executing the measurement via "use [TOOL] on [TARGET]", and interpreting the resulting value for conditional decisions such as classification or placement.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
673 tokensWhen the skill is activated
Reference documents
742 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
Files
SKILL.mdcore3,136 bytesreferences/action_glossary.mddoc1,394 bytesreferences/decision_workflow.mddoc1,792 bytes
Read SKILL.md
# Skill: scienceworld-measurement-taker
## Purpose
Measure a quantitative property of a target object or substance in the ScienceWorld environment using the appropriate measurement tool, then interpret the result for subsequent decision-making.
## When to Use
- When a task requires obtaining a numerical reading (temperature, weight, pH) from an object or substance
- When a measured value determines a conditional next action (e.g., classify based on temperature threshold)
- When the agent needs to compare properties across multiple objects
## Workflow
1. **Identify and acquire the tool** -- Locate the correct measurement instrument (e.g., thermometer, scale) and `pick up` the tool.View the complete source on GitHubscienceworld-mixture-creator
When your agent uses it
This skill chemically mixes the contents of a container using the 'mix' action. Use when all required ingredients (e.g., sodium chloride and water) are present inside a container and the agent needs to combine them to produce a new substance. The skill performs the mixing operation and outputs the resulting product, completing the synthesis step of the task.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
292 tokensWhen the skill is activated
Reference documents
306 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,361 bytesreferences/common_recipes.mddoc1,224 bytes
Read SKILL.md
# Skill: Chemical Mixture Creator
## When to Use
All required ingredients are confirmed inside a single container and you need to combine them into a new substance.
## Procedure
1. `examine <CONTAINER>` — verify all required ingredients are present.
2. `mix <CONTAINER>` — the environment processes the chemistry and produces the result.
3. `examine <CONTAINER>` or `focus on <NEW_SUBSTANCE>` — confirm the synthesis succeeded.
Do not `mix` unless the container holds the exact ingredients required by the recipe.
## Example
**Task:** Create salt water by mixing sodium chloride and water.
1. `examine glass cup` — observe: "containing water, sodium chloride"
2. `mix glass cup`View the complete source on GitHubscienceworld-object-classifier
When your agent uses it
Moves a tested or examined object into a designated container (e.g., a specific colored box) based on a determined property. Use when you have completed a test or inspection and need to fulfill a classification or sorting subtask. It takes the object and target container as inputs and performs the move action.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
478 tokensWhen the skill is activated
Reference documents
544 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Prerequisites
- Core Action
- Workflow
- Important Notes
- Example
Files
SKILL.mdcore2,138 bytesreferences/conductivity_test_guide.mddoc2,139 bytes
Read SKILL.md
# Instructions
## Purpose
This skill is used to finalize a classification task by moving an object into its designated container. It is triggered **after** a property test or inspection has been completed and a decision has been made.
## Prerequisites
1. **Object Location:** The object to be classified must be present in the current room's environment (e.g., on the floor, on a table).
2. **Container Location:** The target container (e.g., yellow box, purple box) must be present in the current room's environment.
3. **Decision Made:** You must have already determined the object's property (e.g., electrically conductive vs. non-conductive) and know which container corresponds to that property.
## Core Action
Execute the `move` command to transfer the object into the correct container.
* **Command Format:** `move <OBJECT> to <CONTAINER>`
* **Example:** `move metal pot to yellow box`
View the complete source on GitHubscienceworld-object-focuser
When your agent uses it
This skill selects and focuses on a specific object to signal task intent or prepare it for manipulation. Use when you have identified a target object that meets task criteria (e.g., a living thing) and need to formally select it before performing actions like moving or using the object in ScienceWorld tasks. The skill uses the 'focus on OBJ' action, taking the object name as input.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
526 tokensWhen the skill is activated
Reference documents
430 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Instruction
- Key Considerations
- Example
Files
SKILL.mdcore2,298 bytesreferences/usage_examples.mddoc1,759 bytes
Read SKILL.md
# Skill: Object Focuser
## Purpose
Use this skill to formally select a target object in the ScienceWorld environment. The `focus on` action signals your intent to the task system and is often a prerequisite for subsequent manipulation steps like `pick up` or `move`.
## When to Use
* After you have identified an object that matches the task's criteria (e.g., "a living thing", "a conductive material").
* Before you attempt to pick up, move, or use that object as part of the task sequence.
* When the task trajectory or environment feedback suggests an object needs to be "focused on" to proceed.
## Core Instruction
1. **Identify the Target:** From your observation (`look around`, `examine`), determine the exact name of the object you intend to use for the task.
2. **Execute Focus:** Use the action: `focus on <OBJECT_NAME>`.
* Replace `<OBJECT_NAME>` with the precise noun phrase from the environment (e.g., `dove egg`, `copper wire`, `beaker`).
3. **Proceed:** After receiving a confirmation observation, continue with the next step in your plan (e.g., `pick up <OBJECT_NAME>`, `move <OBJECT_NAME> to ...`).View the complete source on GitHubscienceworld-object-locator
When your agent uses it
Searches for a specific target object across multiple rooms by systematically teleporting to likely locations and examining each room. Use this skill when you need to find an object whose exact location is unknown. Iterates through candidate rooms using teleport and look around, checks for the object, and continues until found, returning the object's location.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
617 tokensWhen the skill is activated
Reference documents
942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Inputs
- Core Process
- Key Actions
- Example
- Notes & Best Practices
Files
SKILL.mdcore2,747 bytesreferences/action_guide.mddoc2,011 bytesreferences/action_primer.mddoc605 bytesreferences/example_trajectory_breakdown.mddoc1,542 bytes
Read SKILL.md
# Instructions
## Purpose
Locate a specific target object within the ScienceWorld environment when its location is unknown.
## Inputs
- **Target Object:** The name of the object to find (e.g., "thermometer", "metal fork").
- **Candidate Rooms (Optional):** A list of room names to search. If not provided, the skill will use a default priority list based on common object locations.
## Core Process
1. **Initialize:** Receive the target object name.
2. **Plan Search Order:** Determine the sequence of rooms to search. Use the provided `prioritize_rooms.py` script to generate an optimal search order based on the target object.
3. **Execute Search Loop:**
a. Teleport to the next room in the search order.
b. Use the `look around` action to observe the room's contents.View the complete source on GitHubscienceworld-object-placer
When your agent uses it
Moves a specified object from the environment or inventory into a target container based on a classification decision. Use this skill when a task requires sorting or storing an object in a specific location after an assessment (e.g., placing a conductive object in the blue box or a non-conductive object in the orange box).
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
417 tokensWhen the skill is activated
Reference documents
331 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore1,878 bytesreferences/action_primer.mddoc1,541 bytes
Read SKILL.md
# Skill: Object Placer
## Purpose
Move an object into the correct container based on a prior classification or assessment result. This is the final step in conditional sorting workflows.
## Core Workflow
1. **Confirm Assessment Result:** Know which container corresponds to which classification (e.g., "blue box" = conductive, "orange box" = non-conductive).
2. **Acquire Object (if needed):** `pick up OBJ` if the target is not already in inventory.
3. **Execute Placement:** `move OBJ to OBJ` — place the object in the correct container.
4. **Verify Placement:** `look at <CONTAINER>` to confirm the object is now inside.
## Key Actions
| Action | Purpose |
|--------|---------|
| `pick up OBJ` | Acquire object if not in inventory |View the complete source on GitHubscienceworld-object-retriever
When your agent uses it
Acquires a specified object by moving it from the environment into the agent's inventory using 'pick up OBJ'. Use this skill when a task requires an object to be manipulated, tested, or transported and it is not yet in your inventory. Makes the object available for further actions like testing, measuring, or placing.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
396 tokensWhen the skill is activated
Reference documents
248 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Workflow
- Example
- Important Notes
Files
SKILL.mdcore1,738 bytesreferences/action_primer.mddoc1,050 bytes
Read SKILL.md
# Skill: Object Retriever
## Purpose
Acquire a target object from the environment and place it into your inventory for further use.
## When to Use
- You need an object for testing, measuring, or transporting.
- The object is visible in the room but not yet in your inventory.
- A downstream skill (e.g., tool-user, object-placer) requires the object in inventory.
## Core Workflow
1. **Navigate:** `teleport to LOC` if needed to reach the room containing the object.
2. **Survey:** `look around` to confirm the object is present and identify its exact name.
3. **Acquire:** `pick up OBJ` using the exact name from the environment description.
4. **Verify:** Check the observation feedback confirms "You move the [object] to the inventory."View the complete source on GitHubscienceworld-object-selector
When your agent uses it
Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements, selects the most suitable candidate, and signals intent with "focus on [OBJECT]".
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
653 tokensWhen the skill is activated
Reference documents
393 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
Files
SKILL.mdcore2,974 bytesreferences/object_properties.mddoc1,526 bytes
Read SKILL.md
# Skill: scienceworld-object-selector
## Purpose
Identify and select the correct object from visible candidates in the ScienceWorld environment based on task-defined criteria (e.g., "non-living thing", "electrical component", "container"), then signal intent with a `focus on` action.
## When to Use
- When a task requires choosing a specific type of object from multiple visible options
- When the agent must classify objects by property (living/non-living, material type, function) to select one
- When the task instructs finding and interacting with a particular category of object
## Workflow
1. **Survey the environment** -- Use `look around` to list all visible objects in the current location.View the complete source on GitHubscienceworld-planting-coordinator
When your agent uses it
This skill plants a seed or small plant into a suitable growth container (e.g., a flower pot with soil and water). It should be triggered when the agent has acquired a seed and needs to initiate the plant growth process by placing it into a prepared environment. The skill coordinates the 'move' action to transfer the seed from inventory to the target container, resolving any ambiguity if multiple instances exist.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
383 tokensWhen the skill is activated
Reference documents
285 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Procedure
- Key Notes
Files
SKILL.mdcore1,909 bytesreferences/action_primer.mddoc1,279 bytes
Read SKILL.md
# Planting Coordinator Skill
## Purpose
This skill orchestrates the initial planting action to begin a plant growth process. It handles the transfer of a seed from the agent's inventory into a suitable growth container (e.g., a flower pot containing soil and water).
## When to Use
- **Trigger Condition:** The agent has acquired a seed (or small plant) and is in a location containing a suitable growth container.
- **Goal:** Initiate the biological growth process by placing the seed into a prepared environment.
## Core Procedure
1. **Locate Target Container:** Identify a suitable container in the current environment. A valid container must contain both `soil` and `water` substances.
2. **Execute Transfer:** Perform a `move` action to transfer the seed from your inventory to the target container.
3. **Handle Ambiguity:** If the action parser returns an ambiguous request (listing multiple identical action options), select the first option (index `0`) to proceed. This resolves the ambiguity deterministically.
4. **Signal Intent:** After successful planting, use `focus on [seed]` to signal monitoring intent for the growth task.
View the complete source on GitHubscienceworld-planting-operation
When your agent uses it
Plants seeds into prepared containers with soil to initiate plant growth. Execute this when you have both seeds and properly prepared planting containers available. This skill handles the specific action pattern of transferring seeds from storage to growth containers to begin cultivation processes.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
403 tokensWhen the skill is activated
Reference documents
442 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Instructions
- Important Notes
Files
SKILL.mdcore2,007 bytesSKILL.mdcore2,007 bytesreferences/action_patterns.mddoc583 bytesreferences/prerequisite_checklist.mddoc1,290 bytes
Read SKILL.md
# Planting Operation Skill
## Purpose
This skill orchestrates the process of planting seeds into prepared growth containers (e.g., flower pots with soil) to initiate plant cultivation. It is triggered when you have acquired seeds and have containers ready for planting.
## Core Workflow
1. **Prerequisites:** Ensure you possess seeds (in inventory or accessible container) and that the target planting containers are present and contain soil.
2. **Execution:** For each target container, transfer one seed from the seed source to the container.
3. **Completion:** The skill is complete when a seed has been planted in each specified container.
## Key Instructions
* **Seed Source:** Interact with the seed source (e.g., `seed jar`) to access the seeds. Use `examine` or `look at` to confirm seed availability.
* **Planting Action:** Use the `move OBJ to OBJ` action pattern, specifying the seed and the target container.
* **Ambiguity Resolution:** The environment may present ambiguous action options (e.g., multiple identical seeds). Be prepared to select the correct option by number (typically `0`) when prompted.
* **Post-Planting:** After planting, monitor plant growth. Subsequent skills may be required for watering, pollination, or harvesting.View the complete source on GitHubscienceworld-pot-preparer
When your agent uses it
Prepares a planting pot by moving soil from inventory into an empty or water-filled pot. Use this when setting up a growth environment for seeds or plants. It performs the 'move soil to flower pot X' action, transforming the container into a viable planting medium. This skill is atomic and can be repeated for multiple pots.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
194 tokensWhen the skill is activated
Reference documents
296 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Core Action
Files
SKILL.mdcore872 bytesreferences/trajectory_example.mddoc1,148 bytes
Read SKILL.md
# Instructions
Use this skill to prepare a flower pot for planting by filling it with soil.
## Prerequisites
1. **Soil in Inventory**: You must have soil in your inventory. If not, acquire soil first (e.g., by using a shovel on ground outdoors and picking up the resulting soil).
2. **Target Pot**: Identify the specific flower pot you wish to prepare (e.g., "flower pot 1", "flower pot 2"). The pot can be initially empty or contain only water.
## Core Action
Execute the following action:View the complete source on GitHubscienceworld-process-monitor
When your agent uses it
This skill observes the state of an active apparatus and its contents to track progress. Use when you need to periodically check for state changes (e.g., solid to liquid) during a heating or reaction process. The skill uses 'look at' or 'examine' actions on the apparatus and substance.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
348 tokensWhen the skill is activated
Reference documents
368 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,520 bytesreferences/state_transitions.mddoc1,354 bytes
Read SKILL.md
# Process Monitoring Protocol
## When to Use
Activate when an apparatus (stove, burner) is active and you need to check whether a substance has undergone a state change (e.g., solid to liquid, liquid to gas).
## Procedure
1. `look at <APPARATUS>` — verify it is active and contains the target substance.
- If apparatus is not active, use `activate <APPARATUS>` first.
- If substance is missing, check inventory or nearby containers.
2. `examine <SUBSTANCE>` — check its current state description.
3. Compare the observed state to the previous state. If changed (e.g., "chocolate" to "liquid chocolate"), proceed to the next task step.
4. If no change, use `wait` then repeat from step 1.
Run every few steps during an active process. This skill only observes — it does not modify the apparatus or handle substances.
View the complete source on GitHubscienceworld-process-pauser
When your agent uses it
This skill introduces deliberate pauses in task execution. Use when the agent needs to consider next steps, evaluate intermediate results, or wait for processes to complete. The skill uses the 'wait1' or 'wait' actions to temporarily halt activity, preventing rushed decisions in complex experimental procedures.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
329 tokensWhen the skill is activated
Reference documents
426 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Actions
- Implementation Logic
- Example from Trajectory
Files
SKILL.mdcore1,579 bytesreferences/pause_scenarios.mddoc1,915 bytes
Read SKILL.md
# Skill: Process Pauser
## When to Use
Activate this skill when you need to:
* **Consider next steps** in a complex procedure.
* **Evaluate an intermediate result** (e.g., a mixed chemical, a partial assembly).
* **Wait for a simulated process** to complete.
* **Prevent rushed decisions** that could lead to errors.
## Core Actions
Use the following actions to implement a pause:
* `wait1`: Pauses execution for a single simulation step. Use for brief reflection.
* `wait`: Pauses execution for 10 simulation steps. Use for longer consideration or simulated waiting periods.
## Implementation LogicView the complete source on GitHubscienceworld-recipe-retriever
When your agent uses it
This skill locates and acquires a recipe or instruction document by using 'pick up' on the recipe object. Use when the task involves following a specific procedure (e.g., crafting, mixing) and the agent needs to obtain the written instructions. The skill assumes the recipe is visible in the current room and moves it to the inventory, allowing the agent to read it later to understand required ingredients and steps.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
465 tokensWhen the skill is activated
Reference documents
565 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Trigger Conditions
- Core Procedure
- Key Notes
- Error Handling
- Example
Files
SKILL.mdcore2,169 bytesreferences/action_primitives.mddoc1,173 bytesreferences/trajectory_analysis.mddoc1,431 bytes
Read SKILL.md
# Skill: Recipe Retriever
## Purpose
Acquire a visible recipe or instruction document from the current environment and store it in your inventory for later reference.
## Trigger Conditions
Use this skill when:
1. The task involves following a specific procedure (e.g., crafting, mixing, building).
2. You are instructed to find or use a recipe.
3. You need written instructions to understand required ingredients and steps.
## Core Procedure
1. **Locate Recipe**: Use `look around` to survey the current room. Identify any object described as a "recipe," "instructions," "manual," or similar document.
2. **Acquire Recipe**: Use `pick up <recipe_object>` to move the recipe to your inventory.
3. **Verify Acquisition**: Confirm the recipe is now in your inventory before proceeding to the next task phase.View the complete source on GitHubscienceworld-result-archiver
When your agent uses it
Places an object into a designated container (like a colored box) based on a test outcome. It should be triggered when the agent needs to finalize a task by storing an object according to a rule (e.g., conductive → blue box, non-conductive → orange box). The input is the object and the rule, and the output is the object moved to the correct container.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
539 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Procedure
- Key Principles
- Example Rule Application
- Bundled Logic
Files
SKILL.mdcore2,541 bytes
Read SKILL.md
# Instructions
Use this skill to finalize a scientific test by archiving an object based on the observed result.
## When to Use
- You have just completed an experimental test (e.g., electrical conductivity, chemical reaction, physical property test).
- You have a clear rule mapping a specific test outcome to a specific destination container (e.g., "If property X is true, place in Container A; if false, place in Container B").
- The object to be archived and the destination containers are present in your current environment.
## Core Procedure
1. **Verify Context:** Ensure you are in the correct room (typically the `workshop` or lab area) where the test was conducted and where the destination containers are located.
2. **Confirm Test Result:** Observe the final state of your experimental apparatus to definitively determine the test outcome (e.g., "light bulb is on").
3. **Apply Rule:** Map the confirmed outcome to the corresponding destination container as specified by the task rule.
4. **Execute Archive:** Move the test object from its current location (inventory or room) into the correct container using the `move OBJ to CONTAINER` action.
## Key PrinciplesView the complete source on GitHubscienceworld-room-explorer
When your agent uses it
Performs an initial survey of a room to identify all visible objects, containers, devices, and their states using the 'look around' action. Use this skill when you first enter a new location, need to refresh your understanding of the environment, or must identify available resources before planning a sequence of actions. Returns a detailed observation that serves as foundational context for subsequent tasks.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
556 tokensWhen the skill is activated
Reference documents
439 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Action
- Output Processing
- Example
- Integration with Other Skills
Files
SKILL.mdcore2,608 bytesreferences/action_primer.mddoc1,874 bytes
Read SKILL.md
# Instructions
## Purpose
Use this skill to establish a foundational understanding of your immediate environment. It is the critical first step for any task requiring object interaction, inventory assessment, or spatial reasoning.
## When to Use
1. **Upon entering a new room.**
2. When the task requires identifying available resources.
3. Before planning a complex sequence of actions (e.g., building a circuit, mixing chemicals).
4. If the state of the environment may have changed (e.g., after using an object, or if a long time has passed).
## Core Action
Execute the `look around` action. This is the only action required for this skill.
## Output ProcessingView the complete source on GitHubscienceworld-room-navigator
When your agent uses it
Teleports the agent to a specified room within the ScienceWorld environment. Use when the agent needs to move between different locations to locate objects or access specific facilities. The input is a target room name, and the output is the agent arriving at that room, ready for further interaction.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
395 tokensWhen the skill is activated
Reference documents
208 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- How to Use
- Important Notes
- Example
Files
SKILL.mdcore1,769 bytesreferences/available_rooms.mddoc971 bytes
Read SKILL.md
# Instructions
Use this skill to instantly move the agent to a different room. This is the primary method of navigation.
## When to Use
* The agent needs to find an object known to be in a specific room (e.g., "metal pot is located around the kitchen").
* The agent needs to access a facility available only in a specific room (e.g., a workshop for building circuits, a foundry for smelting).
* The agent has completed tasks in one room and needs to proceed to the next relevant location.
## How to Use
1. **Identify the Target Room:** Determine the exact name of the destination room from the task context or environment description (e.g., `kitchen`, `workshop`, `foundry`).
2. **Execute Teleport:** Use the `teleport to <ROOM_NAME>` action.
3. **Verify Arrival:** The observation will confirm the teleport was successful (e.g., "You teleport to the kitchen."). You may then proceed with `look around` to survey the new location.
## Important NotesView the complete source on GitHubscienceworld-room-scanner
When your agent uses it
This skill performs a 'look around' action to scan and describe the current room's contents, including visible objects, containers, and doors. Use when entering a new room or when the agent needs to locate specific items or assess the environment state. The skill outputs a detailed room description, which is essential for inventory discovery and situational awareness.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
575 tokensWhen the skill is activated
Reference documents
502 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Instruction
- Trigger Conditions
- Output Processing
- Integration Notes
- Example
Files
SKILL.mdcore2,644 bytesreferences/action_primer.mddoc1,970 bytes
Read SKILL.md
# Skill: Room Scanner
## Purpose
Execute a `look around` action to obtain a comprehensive description of the current room in the ScienceWorld environment. This description is the foundational step for any task requiring item location, environmental assessment, or navigation planning.
## Core Instruction
When this skill is invoked, the agent must perform the **`look around`** action.
## Trigger Conditions
Invoke this skill when:
1. You first enter a new room via `teleport` or other movement.
2. You need to locate a specific object or container mentioned in your task.
3. The state of the room may have changed (e.g., after an interaction).
4. You are formulating a plan and require an inventory of available resources.
View the complete source on GitHubscienceworld-room-teleporter
When your agent uses it
Teleports the agent to a specified room within the ScienceWorld environment. Use this skill when the target object or location for a task is known to be in a different room, enabling efficient navigation. It takes a target room name as input and outputs a successful teleportation observation.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
271 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Procedure
- Important Notes
Files
SKILL.mdcore1,291 bytes
Read SKILL.md
# Instructions
Use the `teleport to LOC` action to move the agent to the specified room.
## Procedure
1. **Identify Target Room:** Determine the exact name of the destination room from the task context or environment description.
2. **Execute Teleport:** Use the action `teleport to <room_name>`, where `<room_name>` is the target location (e.g., `workshop`, `kitchen`, `foundry`).
3. **Verify Success:** The expected output is an observation confirming the teleport, e.g., "You teleport to the workshop."
## Important Notes
- This skill is for navigation only. It does not handle object interaction or task logic within the destination room.
- Ensure the room name matches the environment's naming exactly. Common rooms include: kitchen, foundry, workshop, bathroom, outside, living room, bedroom, greenhouse, art studio, hallway.
- Use this skill proactively to reduce unnecessary exploration steps when the target location is known.View the complete source on GitHubscienceworld-substance-cooler
When your agent uses it
This skill initiates the cooling of a substance by moving it into a cooling appliance like a freezer. Use when a task requires lowering the temperature of a specific material to observe phase changes. The skill takes the substance (often in a container) and the target appliance as inputs, using the 'move OBJ to OBJ' action. It outputs confirmation of the new location.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
554 tokensWhen the skill is activated
Reference documents
436 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Instruction
- Important Notes
- Example from Trajectory
Files
SKILL.mdcore2,606 bytesreferences/phase_change_protocol.mddoc1,922 bytes
Read SKILL.md
# Skill: Substance Cooler
## Purpose
Use this skill to begin the process of cooling a substance to potentially observe a phase change (e.g., freezing). The core action is to relocate the substance into a cooling appliance.
## When to Use
* The task explicitly requires cooling a substance (e.g., "measure the melting point of mercury").
* You have identified both the target substance (often inside a container like a cup or jar) and a suitable cooling appliance (e.g., freezer, ultra low temperature freezer).
* The immediate goal is to lower the substance's temperature.
## Core Instruction
1. **Locate Items:** Ensure you are in the room containing the target substance and the cooling appliance. Use `look around` if necessary.
2. **Execute Move:** Perform the action `move <SUBSTANCE_CONTAINER> to <APPLIANCE>`.
* `<SUBSTANCE_CONTAINER>`: The object holding the substance (e.g., "glass cup (containing a substance called mercury)").
* `<APPLIANCE>`: The cooling device (e.g., "freezer").View the complete source on GitHubscienceworld-substance-fetcher
When your agent uses it
Locates and retrieves a target substance or material from a container in the environment. Use this skill when the task requires processing a specific substance (e.g., chocolate, sodium chloride, a chemical) and you need to find and acquire it. Searches rooms and containers (fridge, cupboard, counter) and retrieves the substance via pick up or move actions.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
647 tokensWhen the skill is activated
Reference documents
235 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Primary Objective
- Core Logic & Workflow
- Critical Constraints & Notes
- Example Execution (Based on Trajectory)
- Error Handling
Files
SKILL.mdcore2,757 bytesreferences/action_primer.mddoc900 bytes
Read SKILL.md
# Skill: Substance Fetcher
## Primary Objective
Locate a specified target substance (e.g., `chocolate`, `sodium chloride`) within the environment and retrieve it for subsequent processing.
## Core Logic & Workflow
1. **Identify Target:** The target substance name is provided as part of the task initiation (e.g., "Your task is to measure the melting point of **chocolate**").
2. **Search Strategy:**
* If the current room does not contain the target, use `teleport to [room]` to navigate to likely locations (e.g., `kitchen`, `workshop`, `greenhouse`).
* Use `look around` to survey a room and identify containers.
3. **Locate in Container:**
* Examine open containers (`fridge`, `cupboard`, `counter`, `drawer`) listed in the room description.
* The target substance is often found inside a container (e.g., "In the fridge is: **chocolate**").
4. **Retrieval Action:**
* If the substance is a portable object, use `pick up [substance]`.View the complete source on GitHubscienceworld-substance-preparator
When your agent uses it
Use when you need to transfer a target substance into an appropriate container for processing (e.g., a pot for heating, a beaker for mixing). Trigger after acquiring the substance and before setting up an apparatus. Selects a suitable empty container and moves the substance into it.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
636 tokensWhen the skill is activated
Reference documents
202 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Procedure
- Key Considerations
- Example
Files
SKILL.mdcore2,823 bytesreferences/common_containers.mddoc638 bytes
Read SKILL.md
# Substance Preparation Skill
## Purpose
Prepare a target substance for subsequent processing (e.g., heating, mixing) by transferring it from its current location into an appropriate, empty container.
## When to Use
1. **Trigger:** After successfully locating and focusing on the target substance.
2. **Prerequisite:** The substance must be accessible (e.g., in inventory, in an open container).
3. **Next Step:** This skill should be completed **before** setting up any apparatus (e.g., activating a stove, connecting electrical components).
## Core Procedure
1. **Identify Target Substance:** Confirm the exact name and location of the substance to be prepared.
2. **Scan Environment for Containers:** Look for empty, process-appropriate containers in the current room. Priority order:
* **Primary:** Metal pots, beakers, or bowls (for heating/mixing).
* **Secondary:** Ceramic/glass cups, jars (if primary not available).View the complete source on GitHubscienceworld-target-identifier
When your agent uses it
Analyzes room observations to identify objects matching a given target description (e.g., 'living thing'). Triggered after exploring a room when the agent needs to locate a specific type of item. Processes the observation list, filters objects based on target criteria, and returns candidate objects for further action.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
704 tokensWhen the skill is activated
Reference documents
491 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Execution Workflow
- Key Considerations
- Error Handling
- Example Application
Files
SKILL.mdcore3,221 bytesreferences/action_patterns.mddoc105 bytesreferences/taxonomy.mddoc1,724 bytes
Read SKILL.md
# Skill: Target Object Identifier
## Purpose
This skill enables you to systematically locate objects in the ScienceWorld environment that match a specific target description (e.g., "living thing", "container", "electrical device"). It transforms the raw observation text from `look around` into a structured list of candidate objects for your current task.
## When to Use
1. **Trigger Condition**: Immediately after executing `look around` in any room.
2. **Input Required**: The full observation text from `look around` AND the target description from your task.
3. **Output**: A prioritized list of matching objects with their locations and properties.
## Execution Workflow
### Step 1: Parse Observation
Extract all observable items from the room description. Pay special attention to:
- Objects listed after "Here you see:"View the complete source on GitHubscienceworld-target-locator
When your agent uses it
This skill determines the most likely location for a target object based on domain knowledge and environmental clues. Use when the agent needs to find a specific item (like an animal) but it is not in the current room. It analyzes the environment description and suggests a room to teleport to for further investigation.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
363 tokensWhen the skill is activated
Reference documents
382 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Procedure
- Example Flow (From Trajectory)
Files
SKILL.mdcore1,540 bytesreferences/target_location_heuristics.mddoc1,441 bytes
Read SKILL.md
# Skill: Target Locator
**Trigger:** When the agent needs to find a specific object (e.g., an animal, a tool, a chemical) and a preliminary `look around` in the current room does not reveal it.
## Procedure
1. Classify the target object by type.
2. Map to the most probable room using these heuristics:
| Object Type | Likely Room(s) |
|-------------|---------------|
| animal | outside, garden |
| tool/wire/battery | workshop |
| food/cooking item | kitchen |
| chemical/substance | lab, foundry |
| plant/seed | garden, greenhouse |View the complete source on GitHubscienceworld-task-focuser
When your agent uses it
Use when the agent needs to direct attention to a specific object in the environment or inventory before performing a critical action such as measuring, using, or connecting. This preparatory "focus on" step signals intent to the ScienceWorld system, often unlocking required state changes for subsequent interactive steps in experimental procedures.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
584 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Important Notes
Files
SKILL.mdcore2,669 bytes
Read SKILL.md
# Skill: scienceworld-task-focuser
## Purpose
Formally declare intent to interact with a specific object in the ScienceWorld environment. The `focus on` action is a required preparatory step that signals to the system which object subsequent actions (`use`, `measure`, `connect`) will target, often unlocking necessary state changes or measurement capabilities.
## When to Use
- Before using a measurement tool (e.g., thermometer) on a target object
- Before complex operations such as connecting, mixing, or combining objects
- When a task description explicitly instructs "focus on" an object
- To confirm the correct item is in inventory before proceeding with an action
## Workflow
View the complete source on GitHubscienceworld-task-interpreter
When your agent uses it
This skill parses a user's high-level scientific task in the ScienceWorld environment and extracts the core objective and target location. It should be triggered when a new task instruction is received, especially those involving finding, comparing, or manipulating objects. The skill interprets the query to identify the goal (e.g., 'find the animal with the shortest life span') and any specified locations (e.g., 'animals are in the outside location'), outputting a clear, actionable sub-goal for navigation or observation.
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
416 tokensWhen the skill is activated
Reference documents
266 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Parse the Task
- 2. Formulate the Plan
- 3. Output the Interpretation
Files
SKILL.mdcore1,977 bytesreferences/action_glossary.mddoc1,163 bytes
Read SKILL.md
# Instructions
Activate this skill when the user provides a new task instruction for the ScienceWorld environment. Your primary function is to interpret the instruction and generate a clear, executable plan.
## 1. Parse the Task
Read the user's instruction carefully. Extract the following core components:
* **Primary Objective:** What is the ultimate goal? (e.g., "find", "compare", "manipulate").
* **Target Object/Subject:** What is the main focus of the task? (e.g., "animal with the shortest life span").
* **Specified Location:** Is a location explicitly mentioned? (e.g., "animals are in the 'outside' location").
## 2. Formulate the Plan
Based on the parsed components, construct a plan. The standard plan structure is:
1. **Navigate:** If a target location is specified and you are not there, teleport to it immediately.
2. **Observe:** Upon arriving at the correct location, use `look around` to survey the environment and identify relevant objects.
3. **Analyze & Execute:** Apply domain knowledge or comparative reasoning to the observed objects to fulfill the primary objective. Then, take the final required action (e.g., `focus on [OBJECT]`, `pick up [OBJECT]`).View the complete source on GitHubscienceworld-task-parser
When your agent uses it
Analyzes user instructions in ScienceWorld environments to extract specific task requirements and constraints. Use when receiving a new task to identify required objects, target locations, and action sequences before taking any environment actions.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
698 tokensWhen the skill is activated
Reference documents
637 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Parse the Instruction
- 2. Survey the Environment
- 3. Identify the Target Object
- 4. Execute the Task Sequence
- Key Principles
- Example
Files
SKILL.mdcore3,109 bytesreferences/task_patterns.mddoc2,145 bytes
Read SKILL.md
# Instructions for ScienceWorld Task Parsing
When you receive a new task instruction in a ScienceWorld environment, follow this process to parse it into a structured plan.
## 1. Parse the Instruction
Immediately analyze the user's natural language instruction. Extract the following core components:
* **Target Object Type:** Identify the category or description of the object to be manipulated (e.g., 'non-living thing', 'liquid', 'electrical component').
* **Target Location:** Identify the final destination for the object, including the room and specific container (e.g., 'purple box in the workshop').
* **Required Actions:** Infer the sequence of actions implied by verbs like "find", "focus on", "move", "pour", "mix", etc.
**Output your analysis as a concise thought.** Example: "Task requires finding a non-living object in the workshop and moving it to the purple box."
## 2. Survey the Environment
* Use `look around` in your current room to get an inventory of visible objects, containers, and their states.
* If the target location is a different room, use `teleport to LOC` to go there first, then `look around`.View the complete source on GitHubscienceworld-temperature-measurer
When your agent uses it
This skill uses a thermometer on a substance to measure its temperature. It should be triggered when the agent needs to determine the temperature of a material (e.g., lead) to assess if it has reached a specific melting point or threshold. The skill requires a thermometer in inventory and a target substance, outputting the measured temperature in degrees Celsius, which is key for scientific measurement tasks.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
556 tokensWhen the skill is activated
Reference documents
645 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Actions & Observations
- Bundled Logic
- Notes
Files
SKILL.mdcore2,593 bytesreferences/action_guide.mddoc2,590 bytes
Read SKILL.md
# Skill: Temperature Measurement for Scientific Experiments
## Purpose
Measure the temperature of a target substance (e.g., a metal like lead) to determine if it has reached a specific state-change threshold, such as its melting point.
## Core Workflow
1. **Acquire Thermometer:** Ensure a thermometer is in your inventory. If not, locate and pick one up.
2. **Locate Target Substance:** Identify the substance to be measured (e.g., "lead"). It may be in a container.
3. **Prepare for Heating (If Necessary):** If measuring a melting point, the substance likely needs to be heated.
* Transfer the substance to a heat-resistant container (e.g., a metal pot).
* Move the container to a heating device (e.g., a blast furnace in the foundry).
* Activate the heating device.
4. **Measure Temperature:** Use the thermometer from your inventory on the target substance.
5. **Interpret Result:** The observation will state the measured temperature in degrees Celsius. Use this value to make a decision (e.g., "above 150.0 degrees" -> focus on the red box).
View the complete source on GitHubscienceworld-threshold-evaluator
When your agent uses it
Use when the agent has just obtained a numerical measurement (temperature, weight, pH) and must compare it against a predefined threshold to determine a binary outcome. This skill extracts the measured value, evaluates it against the threshold condition (above/below), and executes the corresponding branch action such as classification or placement.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
684 tokensWhen the skill is activated
Reference documents
1,321 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
- Common Pitfalls
Files
SKILL.mdcore3,182 bytesreferences/action_guide.mddoc2,553 bytesreferences/usage_examples.mddoc2,627 bytes
Read SKILL.md
# Skill: scienceworld-threshold-evaluator
## Purpose
Compare a measured numerical value against a predefined threshold to determine which of two conditional actions to execute. This is the decision-making step that immediately follows a measurement in ScienceWorld experimental workflows.
## When to Use
- Immediately after obtaining a numerical measurement (e.g., temperature reading from a thermometer)
- When the task includes a conditional instruction like "if above X, do A; if below X, do B"
- When classifying or sorting objects based on measured properties
## Workflow
1. **Extract the measurement** -- Parse the numerical value from the observation (e.g., `"the thermometer measures a temperature of 56 degrees celsius"` yields `56`).View the complete source on GitHubscienceworld-tool-fetcher
When your agent uses it
This skill locates and picks up a specified tool or instrument from the environment. It should be triggered when a task requires a specific tool (e.g., thermometer, stopwatch) for measurement or manipulation. The skill identifies the tool's location via observation and executes a pick-up action, moving the tool to inventory.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
549 tokensWhen the skill is activated
Reference documents
847 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Identify the Target Tool
- 2. Locate the Tool via Exploration
- 3. Execute the Pick-up
- 4. Post-Action Verification (Optional)
- Key Constraints & Notes
Files
SKILL.mdcore2,333 bytesreferences/environment_actions.mddoc1,824 bytesreferences/trajectory_analysis.mddoc1,664 bytes
Read SKILL.md
# Instructions
**Primary Goal:** Locate a specified tool and move it to your inventory.
## 1. Identify the Target Tool
* The required tool will be specified in the user's task or request (e.g., "thermometer", "stopwatch", "lighter").
* Confirm the exact name of the tool object.
## 2. Locate the Tool via Exploration
* If you are not in the correct room, use `teleport to [ROOM_NAME]` to go to the most likely location (e.g., `kitchen`, `workshop`).
* Use `look around` to survey the current room.
* Scan the observation for the target tool name. It may be:
* Listed directly in the room description (e.g., "a thermometer").
* Inside an open container (e.g., "a fridge. In the fridge is: chocolate, a wood cup...").
* If the tool is not immediately visible, examine likely containers using `look at [CONTAINER]` (e.g., `look at counter`, `look at cupboard`).View the complete source on GitHubscienceworld-tool-user
When your agent uses it
Uses a tool from inventory on a target object or location to perform a specific environmental interaction, such as digging, cutting, or measuring. Use this skill when a task requires modifying the environment or manipulating materials with a tool (e.g., using a shovel to dig soil, a thermometer to measure temperature, or an axe to cut wood). Takes the tool and target as inputs and outputs the result of the interaction.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
461 tokensWhen the skill is activated
Reference documents
205 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Workflow
- Key Actions
- Example
- Important Notes
Files
SKILL.mdcore2,098 bytesreferences/example_trajectory.mddoc907 bytes
Read SKILL.md
# Skill: Tool User
## Purpose
Perform a physical action on the environment using a tool from your inventory. The core action is `use TOOL on TARGET`.
## When to Use
- A task requires modifying the environment (digging, cutting, heating).
- You need to measure a property of an object (temperature, conductivity).
- A tool-based interaction is the next step in your experiment workflow.
## Core Workflow
1. **Ensure Tool in Inventory:** The required tool (e.g., `shovel`, `thermometer`, `axe`) must be in your inventory. Use `pick up OBJ` if it is not.
2. **Identify Target:** Determine the exact target object or location name (e.g., `ground`, `tree`, `metal fork`).
3. **Execute:** `use TOOL on TARGET`.
4. **Interpret Result:** Read the observation output to determine the outcome (e.g., temperature reading, state change).View the complete source on GitHubscienceworld-tool-validator
When your agent uses it
Use when the agent has acquired a tool or instrument and needs to verify it is operational before first use in a critical task step. This skill performs a lightweight pre-use check via "focus on [TOOL] in inventory" and confirms readiness based on the system's response, ensuring the tool is functional before measurement, activation, or connection operations.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
539 tokensWhen the skill is activated
Reference documents
181 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Workflow
- Examples
- Key Principles
Files
SKILL.mdcore2,509 bytesreferences/action_primer.mddoc818 bytes
Read SKILL.md
# Skill: scienceworld-tool-validator
## Purpose
Perform a pre-use functionality check on a tool or instrument to confirm it is operational before employing it in a critical ScienceWorld task step such as measurement, activation, or connection.
## When to Use
- Immediately after acquiring a tool (e.g., `pick up thermometer`) and before its first use
- When switching to a different tool mid-task and needing to confirm readiness
- When resuming a task after navigation and needing to re-confirm tool availability
## Workflow
1. **Acquire the tool** -- Ensure the target tool is in inventory. If not, locate it with `look around` and retrieve it with `pick up [TOOL]`.View the complete source on GitHubsoil-extraction
When your agent uses it
Uses a shovel tool to dig soil from the ground in outdoor environments. Execute this skill when you need to obtain soil for planting tasks and have both the shovel in inventory and access to an appropriate digging location. The skill produces soil that can then be collected and transported.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
437 tokensWhen the skill is activated
Reference documents
283 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Prerequisites
- Core Procedure
- Key Notes
- Error Handling & Ambiguity
Files
SKILL.mdcore2,003 bytesSKILL.mdcore2,003 bytesreferences/trajectory_excerpt.mddoc1,172 bytes
Read SKILL.md
# Skill: Soil Extraction
## Purpose
This skill enables the agent to extract soil from the ground using a shovel. It is a foundational step for planting tasks, transforming a bare outdoor location into a source of usable soil.
## Prerequisites
1. **Tool in Inventory:** You must possess a `shovel` in your inventory.
2. **Location:** You must be in an outdoor environment (e.g., `outside`) where digging is permissible.
3. **Ground Access:** The ground must be accessible and diggable.
## Core Procedure
1. **Navigate:** Ensure you are in the target outdoor location (e.g., `teleport to outside`).
2. **Execute Dig:** Use the command `use shovel in inventory on ground`.
3. **Collect Output:** The action will produce `soil` placed nearby. Use `pick up soil` to add it to your inventory.
View the complete source on GitHubtask-completion-focus
When your agent uses it
Focuses on a specific target object to signal task completion. Use when you have produced the required final object (like a grown banana) and need to formally complete the assigned task. This handles the 'focus on OBJ' action that typically marks successful task execution in the environment.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
261 tokensWhen the skill is activated
Reference documents
487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
- Example
Files
SKILL.mdcore1,207 bytesreferences/action_primer.mddoc1,205 bytesreferences/trajectory_analysis.mddoc1,022 bytes
Read SKILL.md
# Skill: Task Completion Focus
## When to Use
The final required object (e.g., grown banana, crafted item) is visibly present and you need to formally signal task completion. Do not use for intermediate steps.
## Procedure
1. `look around` — confirm the target object is visible in the scene.
2. `focus on <OBJECT>` — signal task completion.
3. **Ambiguity handling:** If the environment returns "Ambiguous request" with numbered options, respond with the option number (e.g., `0`) for the target most directly associated with your task goal.
## Example
**Task:** "Grow a banana." After successful cultivation:
1. `look around` — observation: "On the banana tree you see: a banana, a flower."
2. `focus on banana on banana tree`
3. If ambiguous prompt appears listing multiple bananas, select `0` (first instance).View the complete source on GitHubwebshop-action-executor
When your agent uses it
This skill executes a specific interface action, such as clicking a button or selecting an option, within a web shopping environment. It should be triggered when a decision has been made (e.g., to choose a color or proceed to purchase). The input is the target action identifier (e.g., 'white' or 'buy now'), and the output is the corresponding formatted action command (e.g., click[white]).
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
290 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Instruction
Files
SKILL.mdcore1,297 bytes
Read SKILL.md
# Skill: WebShop Action Executor
## Purpose
Execute a single, specific action in a WebShop environment after a decision has been made. This skill formats the action into the required command structure for the WebShop interface.
## When to Use
- **Trigger:** When the agent has completed its analysis and has decided on the exact action to take (e.g., "select the white color option," "proceed to buy now").
- **Input:** A clear target identifier (string) derived from the available actions on the current page.
- **Output:** A correctly formatted `click[value]` or `search[keywords]` command.
## Core Instruction
1. **Receive Input:** The skill is provided with a single `target_action` string (e.g., 'white', 'buy now', 'b08w25dbb7').
2. **Format Output:** Immediately output the action in the exact format required by the WebShop environment:
View the complete source on GitHubwebshop-attribute-selector
When your agent uses it
Selects specific product attributes (e.g., flavor, size) on a product detail page to match user requirements. Triggered when a product page presents configurable options and the parsed query specifies needed values. It identifies the correct option from available clickables (e.g., 'smoked bacon' for flavor, '4 ounce (pack of 2)' for size) and executes the selection click.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
467 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Process
- Important Notes
Files
SKILL.mdcore2,186 bytes
Read SKILL.md
# Instructions
## When to Use
Activate this skill when ALL of the following are true:
1. You are on a product detail page (not a search results page).
2. The observation contains configurable product options (e.g., "flavor", "size") listed as available actions.
3. The user's instruction specifies required values for one or more of these attributes (e.g., "gluten free", "4 ounce (pack of 2)", "smoked peppered bacon").
## Core Process
1. **Parse Requirements:** From the user's instruction, extract the required attribute values (e.g., target flavor, size, dietary feature).
2. **Map to Options:** Examine the list of available actions (clickables). Identify which clickable text corresponds to each required attribute value.
* Use exact or fuzzy matching (see `scripts/match_attribute.py` for logic).
* Prioritize exact matches. For dietary features like "gluten free" or "vegetarian," the product title or description may already confirm this; your goal is to select the correct flavor/size.
3. **Execute Selection:** For each identified attribute option, perform a `click[value]` action, where `value` is the exact text of the matching clickable.
4. **Finalize:** After all required attributes are selected, if a "Buy Now" or similar action is available and the instruction implies a purchase, you may proceed to click it.View the complete source on GitHubwebshop-attribute-verifier
When your agent uses it
Verifies product attributes on a web shop detail page by extracting price, comparing color availability, validating specifications, and confirming option selections against user requirements before purchase. Use when you need to check if a product matches requirements, verify product details before buying, confirm item specifications on an online store product page, or validate that price, color, size, or other attributes satisfy the user's constraints. Outputs a `Thought:` assessment followed by a `click[value]` action to select the matching option and proceed, or navigates back to search if the product does not match.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
788 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Core Workflow
- Action Format
- Critical Rules
- Example
Files
SKILL.mdcore3,586 bytes
Read SKILL.md
# Instructions
You are verifying product attributes on a detailed product page. Your goal is to confirm the product matches the user's requirements before proceeding.
## Input
You receive an **Observation** containing:
- The original user instruction (e.g., "find a black leather wallet, price lower than 40.00 dollars")
- Product details: Title, Price, Rating
- Available options (e.g., color buttons like "black", "brown")
- Available actions (e.g., "Buy Now", "Back to Search", "Description")
## Core Workflow
View the complete source on GitHubwebshop-initial-search
When your agent uses it
Performs the first search on an e-commerce platform using keywords derived from parsed user requirements. Use when starting product discovery from a user instruction or when previous search results are insufficient and a new query is needed. It formulates a search query from the criteria (e.g., '24 pack of 7.5 ounce bottles of non-gmo classic tonic') and executes the search[] action, returning the initial result page.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
486 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Example
Files
SKILL.mdcore2,146 bytes
Read SKILL.md
# Instructions
1. **Parse Requirements:** Extract the core product criteria from the user's instruction. Focus on:
* **Quantity & Packaging:** (e.g., "24 pack")
* **Size:** (e.g., "7.5 ounce bottles")
* **Key Attributes:** (e.g., "non-gmo", "classic tonic")
* **Price Constraint:** (e.g., "price lower than 50.00 dollars") - This is for validation later, not for the initial search query.
2. **Formulate Search Query:** Combine the extracted criteria into a concise, natural-language search string. Prioritize specificity to filter results effectively.
* **Example:** For "i would like to get a 24 pack of 7.5 ounce bottles of non-gmo classic tonic", the query should be: `24 pack of 7.5 ounce bottles of non-gmo classic tonic`
* **Do not** include the price constraint in the search keywords.
3. **Execute Search:** Use the platform's `search[<keywords>]` action with your formulated query.
* The action output will be the initial search results page observation.
4. **Next Steps:** After executing this skill, proceed to evaluate the search results. The next actions will typically involve clicking on a promising product listing or refining the search.View the complete source on GitHubwebshop-option-selector
When your agent uses it
This skill selects product options or variants (such as size, color, or quantity) on a product detail page based on user preferences or cost optimization. It should be triggered when a product page displays configurable options. The skill evaluates available choices (e.g., 1pcs vs 2pcs) and selects the one that best aligns with the user's constraints, such as minimizing cost.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
400 tokensWhen the skill is activated
Reference documents
477 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger Condition
- Core Logic
- Important Notes
- Example from Trajectory
Files
SKILL.mdcore1,959 bytesreferences/strategy_docs.mddoc2,314 bytes
Read SKILL.md
# Skill: WebShop Option Selector
## Trigger Condition
Activate this skill when the observation from the WebShop environment contains:
1. A product detail page (indicated by the presence of a "Price:" field and product title).
2. One or more configurable option categories (e.g., "size:", "color:", "quantity:") with clickable values listed beneath them.
## Core Logic
1. **Parse the Observation:** Identify all configurable option categories and their available values from the current page state.
2. **Apply Selection Strategy:** By default, implement a **cost-minimization strategy**. For each option category, select the value that results in the lowest final price while still meeting any explicit user constraints from the original instruction (e.g., "price lower than 40.00 dollars").
3. **Execute Selection:** Perform a `click[value]` action for the chosen option value. If multiple categories exist, they should be selected in the order they appear on the page.
## Important Notes
- The skill assumes the displayed price updates (or is representative) after an option is selected. Your action should be based on the currently displayed information.
- If the user's instruction contains specific preferences (e.g., "large size", "blue color"), prioritize those over cost minimization.View the complete source on GitHubwebshop-price-checker
When your agent uses it
This skill scans product listings or detail pages to verify if an item's price meets a specified budget constraint. It is triggered when evaluating a potential product for purchase. It extracts the price from the displayed information (e.g., '$164.95') and compares it against the maximum allowed budget, outputting a boolean decision on whether the item is within budget.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
344 tokensWhen the skill is activated
Reference documents
260 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Process
- Notes
Files
SKILL.mdcore1,605 bytesreferences/price_patterns.mddoc978 bytes
Read SKILL.md
# Instructions
When evaluating a product for purchase, use this skill to check if its price is within the specified budget.
## Process
1. **Identify the Budget:** Extract the maximum allowed price from the user's instruction or the current context. The budget is typically expressed as a dollar amount (e.g., "lower than 200.00 dollars").
2. **Locate the Price:** On the current web page (search results or product detail page), find the price string. It is usually prefixed with a `$` symbol and may be labeled "Price:".
3. **Execute Check:** Run the `check_price.py` script, providing it with the extracted price string and the budget.
4. **Make Decision:** Based on the script's boolean output (`True`/`False`):
* If `True`: The item is within budget. You may proceed with further evaluation or purchase.
* If `False`: The item exceeds the budget. You should continue searching or select a different item.
## Notes
* The primary action for this skill is to call the bundled script. Do not perform manual price parsing or comparison in your main reasoning.
* If the price cannot be found on the page, assume the item is not suitable and continue your search.View the complete source on GitHubwebshop-product-detail-check
When your agent uses it
Examines a specific product's detailed page to verify it matches the user's requirements, checking price, description, features, and reviews. Use when you have navigated to a product detail page from search results and need to confirm the product meets all user-specified constraints before purchasing. It provides a final suitability assessment with a clear proceed-or-reject recommendation.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
833 tokensWhen the skill is activated
Reference documents
309 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger
- Core Objective
- Execution Workflow
- Output Format
- Example
- Notes
Files
SKILL.mdcore3,778 bytesreferences/action_guidelines.mddoc1,303 bytes
Read SKILL.md
# Skill: Product Detail Verification
## Trigger
Activate this skill when the agent has navigated to a specific product's detailed page from a search results list. The agent should have a user query containing specific requirements (e.g., product type, attributes, price constraints).
## Core Objective
Analyze the product detail page to confirm if the product meets all user-specified constraints. Provide a clear "Proceed" or "Reject" recommendation.
## Execution Workflow
1. **Parse User Requirements:** Extract key constraints from the user's instruction. Primary constraints are typically **Price** and **Key Attributes** (e.g., "long", "clip-in", "natural looking"). Store these in a structured format.
2. **Scrape Product Page Data:** Systematically extract the following information from the current page observation:
* **Product Title**
* **Price**View the complete source on GitHubwebshop-product-detail-inspector
When your agent uses it
This skill examines a product detail page to verify specific attributes or select options like size, color, or quantity. It is used after clicking on a product, to confirm that the item matches the user's needs (e.g., checking for '10 slots' option, price, material). The input is the product page observation, and the output is an action to select a required variant (e.g., click[10 slots]) or proceed if criteria are satisfied.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
416 tokensWhen the skill is activated
Reference documents
817 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Input
- Core Logic
- Output Format
Files
SKILL.mdcore1,853 bytesreferences/action_guidelines.mddoc1,167 bytesreferences/trajectory_example.mddoc2,209 bytes
Read SKILL.md
# Instructions
## Purpose
You are an agent navigating a web shop. Your current task is to inspect a product detail page. You have arrived here after clicking on a product from the search results.
## Input
You will receive an **Observation** containing the product page state. This includes:
* The original user instruction (e.g., "i am looking for an easy to clean jewelry box with 10 slots, and price lower than 60.00 dollars").
* Product details: Title, Price, Rating.
* Available options (e.g., size variants like "3 slot", "10 slots").
* Available actions (e.g., "Buy Now", "Description").
## Core Logic
1. **Parse the Instruction:** Identify the user's key requirements from the instruction (e.g., specific attribute: "10 slots", price constraint: "< $60").
2. **Examine the Page:** Check the product's displayed **Price** against the user's budget. Check the available options for the required attribute.View the complete source on GitHubwebshop-product-detail-navigator
When your agent uses it
Navigates to and interacts with a specific product's detail page. This skill is triggered after a candidate product ID is selected from search results. It performs the click action to load the product page and then identifies available interactive elements (like flavor or size selectors) that need to be configured to match the user's requirements.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
659 tokensWhen the skill is activated
Reference documents
206 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Workflow
- Action Format
- Key Logic (Handled by Script)
- Important Notes
Files
SKILL.mdcore3,034 bytesreferences/action_protocol.mddoc945 bytes
Read SKILL.md
# Instructions
## Purpose
This skill is used to navigate from a product search result to the product's detail page and configure it according to the user's specific requirements (e.g., flavor, size, dietary needs).
## When to Use
Use this skill when you have identified a candidate product from a search result list and need to:
1. Load its detailed product page.
2. Verify its attributes against the user's instruction.
3. Select the correct options (like `flavor` or `size`) to match the user's request.
4. Proceed to the final purchase step if all criteria are met.
## Core Workflow
1. **Navigate to Product Page:** Click on the product ID (e.g., `B06Y96MXJV`) from the search results to load its detail page.
2. **Parse the Page State:** Once on the product page, the observation will contain the product title, price, and a list of available interactive elements (clickables). Analyze these to find configuration options.View the complete source on GitHubwebshop-product-evaluator
When your agent uses it
Evaluates product listings against user requirements such as price limits and feature matches to identify viable options. Use when you are on a search results page containing multiple products and need to select the most promising candidate for detailed inspection. The skill analyzes product titles, prices, and brief descriptions to rank and choose the best match.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
649 tokensWhen the skill is activated
Reference documents
428 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Process
- Thought Process Format
- Example
Files
SKILL.mdcore2,776 bytesreferences/evaluation_logic.mddoc1,788 bytes
Read SKILL.md
# Instructions
## When to Use
Activate this skill when you are on a **search results page** in a web shopping environment and need to evaluate multiple products against specific user requirements (e.g., price limits, feature keywords).
## Core Process
1. **Parse the Observation:** Identify the user's instruction, the list of available products, and their associated details (Title, Price, ASIN/Product ID).
2. **Extract Requirements:** From the user instruction, identify:
* **Price Limit:** The maximum acceptable price (e.g., "lower than 40.00 dollars").
* **Feature Keywords:** Key product attributes (e.g., "teeth whitening", "freshens breath").
3. **Evaluate Products:** For each product listing on the current page:
* Check if the price is below the user's limit.
* Check if the product title contains the required feature keywords.
* Prioritize products that meet all criteria. If multiple products qualify, choose the one that appears most relevant or cost-effective.
4. **Take Action:**View the complete source on GitHubwebshop-product-search
When your agent uses it
Performs an initial product search using a web interface by generating appropriate search keywords based on interpreted query criteria. Use when starting a product discovery task, when returning to search results after rejecting a product, or when the observation contains a search interface prompt. The skill inputs structured search parameters and outputs a list of candidate products from the search results page.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
473 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Workflow
- Key Decision Logic
- Constraints
- Example from Trajectory
Files
SKILL.mdcore2,224 bytes
Read SKILL.md
# Skill: WebShop Product Search
## Core Workflow
1. **Interpret Criteria:** Extract key product attributes from the user's instruction (e.g., product type, features, price constraints).
2. **Formulate Query:** Construct a concise search string prioritizing the core product type and critical attributes. Start broad; refine if results are poor.
3. **Execute Search:** Use the `search[keywords]` action to submit the query. Keywords must be a single string enclosed in brackets.
4. **Validate Results:** Success is marked by a "Page 1" observation containing product listings. If 0 results are returned, re-invoke with a broader or alternative query. If all results exceed the user's price constraint, refine with additional terms.
## Key Decision Logic
* **Trigger Condition:** This skill is the entry point for a new product discovery task. Also activate when the observation contains "[SEP] Search" or "[SEP] Back to Search".
* **Output Handoff:** The search results page is passed to downstream skills (e.g., `webshop-result-filter`, `webshop-product-evaluator`) for individual product analysis.
## Constraints
* Do not use this skill if no search action is available in the current state.
* Do not include multiple actions or extra formatting in the search keywords.View the complete source on GitHubwebshop-product-selector
When your agent uses it
Selects the most promising product candidate from a filtered shortlist for detailed inspection. Use when you are on a search results page with multiple viable items and need to make a final selection based on a heuristic such as best feature match or lowest price. Triggers navigation to the selected product's detail page via click[product_id].
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
571 tokensWhen the skill is activated
Reference documents
415 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Decision Process
- Thought Process Template
- Example
Files
SKILL.mdcore2,519 bytesreferences/action_format.mddoc1,670 bytes
Read SKILL.md
# Instructions
Use this skill when you are on a search results page with multiple product options that appear to meet the user's core requirements.
## Decision Process
1. **Assess the List:** Review the provided observation, which contains a list of products. Each product entry typically includes a Product ID (e.g., `B093C1THVP`), a title, and a price.
2. **Apply Selection Heuristic:** Use the bundled `selector.py` script to programmatically identify the best candidate. The script implements the following logic:
* Filters products strictly under the user's specified maximum price.
* Scores remaining products based on keyword matching in the title against the user's core requirements (e.g., "portable", "easy to carry", "double horn").
* Selects the product with the highest score. In case of a tie, it chooses the lowest-priced item.
3. **Execute Action:** The final action is always to click on the selected product's ID to navigate to its detail page for final verification and purchase. The action format is `click[product_id]`.
## Thought Process Template
Structure your reasoning before acting using this template:
**Thought:** [List the user's requirements, evaluate each candidate product against them, explain why the selected product is the best match.]View the complete source on GitHubwebshop-purchase-executor
When your agent uses it
Executes the purchase action for a confirmed suitable product on an e-commerce page. Use when a product has been verified against the user's requirements (price, attributes) and the decision is to buy. Performs a click[Buy Now] action on the purchase button to complete the transaction.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
501 tokensWhen the skill is activated
Reference documents
320 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Core Action
- Execution Logic
- Important Notes
- Example
Files
SKILL.mdcore2,333 bytesreferences/purchase_ui_patterns.mddoc1,421 bytes
Read SKILL.md
# Skill: webshop-purchase-executor
## Purpose
Execute the final purchase transaction for a verified product on an e-commerce platform. This skill is the terminal action in a shopping workflow, initiated only after a product has been confirmed to meet the user's criteria (e.g., price, description).
## When to Use
- **Trigger:** You are on a product detail page.
- **Prerequisite:** The product has been verified against the user's requirements (e.g., price < $40.00, "natural looking").
- **User Intent:** The user has made a decision to buy the product.
- **Available Action:** A purchase button (e.g., "Buy Now") is present in the list of clickable elements.
## Core Action
Perform a `click` action on the purchase button.
## Execution LogicView the complete source on GitHubwebshop-purchase-initiator
When your agent uses it
Initiates the purchase process by clicking the buy button once a product and its options have been selected and verified against requirements. Use when you are on a product detail page, all selection criteria (price, features, options) are satisfied, and the user is ready to proceed to checkout. Confirms the final price meets budget constraints before executing click[buy now].
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
583 tokensWhen the skill is activated
Reference documents
261 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Action
- Verification Logic (Before Clicking)
- Example
- Error Handling
Files
SKILL.mdcore2,649 bytesreferences/trajectory_example.mddoc979 bytes
Read SKILL.md
# Instructions
## When to Use
Activate this skill when:
1. A product has been selected from search results.
2. All required product options (e.g., size, color, quantity) have been chosen.
3. The final displayed price has been verified to be within the user's specified budget.
4. The user's instruction implicitly or explicitly indicates readiness to purchase (e.g., "I need to buy...", "I want this one").
## Core Action
Execute the `click[buy now]` action to proceed to checkout.
## Verification Logic (Before Clicking)
Before clicking "Buy Now", you **must** perform these checks:
1. **Budget Check**: Confirm the final displayed `Price:` is less than the maximum budget specified in the user's original instruction. If no budget is specified, skip this check.View the complete source on GitHubwebshop-query-interpreter
When your agent uses it
Interprets a user's shopping query to extract key product requirements such as item type, attributes, and constraints. Use when a new shopping instruction is received and you need to parse natural language into structured criteria (product category, desired features, price limits) before performing a search. The output is a clear set of search parameters for use in subsequent product lookup steps.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
557 tokensWhen the skill is activated
Reference documents
579 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Trigger
- Core Process
- Example
Files
SKILL.mdcore2,502 bytesreferences/execution_example.mddoc252 bytesreferences/query_patterns.mddoc2,002 bytes
Read SKILL.md
# Instructions
## Trigger
Activate this skill when a new shopping instruction is received from the user. The instruction will be a natural language request for a product.
## Core Process
1. **Parse the Instruction:** Analyze the user's query to identify the following key components:
* **Primary Product Type:** The main item being requested (e.g., "hair extension").
* **Key Attributes/Features:** Descriptive requirements (e.g., "long", "clip-in", "natural looking").
* **Constraints:** Hard limits, especially price (e.g., "price lower than 40.00 dollars").
2. **Structure the Output:** Format the extracted information into a clear, structured set of search parameters. Use the following template:
```View the complete source on GitHubwebshop-query-parser
When your agent uses it
This skill extracts key constraints and product requirements from a user's shopping query. It should be triggered when the agent receives a new shopping instruction, to identify product attributes (e.g., 'gluten free'), price limits (e.g., 'lower than 140.00 dollars'), and other specifications. The skill outputs a structured set of search criteria to guide subsequent product discovery.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
566 tokensWhen the skill is activated
Reference documents
615 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Task
- Procedure
- Output
- Notes
Files
SKILL.mdcore2,652 bytesreferences/query_components.mddoc2,217 bytes
Read SKILL.md
# Instructions
## When to Use
Activate this skill immediately when a new shopping instruction is received from the user, before any search or click actions are performed.
## Core Task
Parse the user's natural language instruction to extract structured search criteria. Your goal is to identify:
1. **Product Type/Name:** The primary item the user wants (e.g., "popcorn").
2. **Key Attributes:** Descriptive features like "gluten free", "organic", "vegan", etc.
3. **Price Constraints:** Any upper or lower price limits (e.g., "lower than 140.00 dollars").
4. **Other Specifications:** Brand, size, quantity, or other qualifying terms.
## Procedure
1. **Run the Parser:** Execute the bundled script `parse_query.py` on the user's instruction.
2. **Review & Refine:** Examine the script's output. If the instruction is complex or ambiguous, use your judgment to refine the criteria. For example, ensure price limits are correctly interpreted as numeric ranges.View the complete source on GitHubwebshop-result-analyzer
When your agent uses it
This skill evaluates a list of search results against the target product criteria. Trigger it when a search result page is observed, to identify promising product listings. It analyzes each result's title, price, and brief description to shortlist items that best match the required attributes (like size, color, and price), outputting a prioritized list of candidate product IDs or links for further inspection.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
430 tokensWhen the skill is activated
Reference documents
321 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Extract User Requirements
- 2. Analyze Search Results
- 3. Score and Prioritize
- 4. Output and Next Action
Files
SKILL.mdcore1,842 bytesreferences/attribute_patterns.mddoc1,020 bytesreferences/execution_example.mddoc64 bytes
Read SKILL.md
# Instructions
Trigger this skill when you observe a search result page (e.g., containing "Page 1 (Total results: 50)" and multiple product listings).
## 1. Extract User Requirements
First, parse the user's instruction from the observation. Identify the following key attributes:
- **Product Type:** (e.g., "woman's us size 5 high heel shoe")
- **Specific Attributes:** (e.g., "rubber sole", "color patent-beige")
- **Price Constraint:** (e.g., "price lower than 90.00 dollars")
## 2. Analyze Search Results
For each product listing in the observation (typically formatted as `[ASIN/Product ID] [SEP] [Title] [SEP] [Price Range]`):
1. Extract the **Product ID** (e.g., B09GXNYJCD).
2. Extract the **Product Title**.
3. Extract the **Price**. Convert any range (e.g., "$49.99 to $54.99") to its maximum value for comparison against the budget.View the complete source on GitHubwebshop-result-filter
When your agent uses it
Filters search results by evaluating product listings against specific user constraints like price, features, or ratings. Use when you are on a search results page and need to systematically identify which products meet all given criteria before selecting one for closer inspection. Takes a list of products with their details and outputs a filtered subset that meets the defined requirements.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
725 tokensWhen the skill is activated
Reference documents
537 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Instruction
- Example from Trajectory
- Next Action
Files
SKILL.mdcore3,074 bytesreferences/constraint_extraction_guide.mddoc2,007 bytes
Read SKILL.md
# Skill: webshop-result-filter
## When to Use
Activate this skill when you are on a search results page in a web shopping environment and need to systematically evaluate which products meet a user's specific, multi-faceted requirements (e.g., "price lower than 40.00 dollars" AND "natural looking").
## Core Instruction
1. **Parse the Instruction:** Extract the user's constraints from the instruction. Common constraints include:
* **Price:** A maximum or target price (e.g., `price lower than 40.00 dollars`).
* **Features:** Specific attributes or keywords (e.g., `natural looking`, `long`, `clip-in`).
* **Ratings:** A minimum rating threshold (if available in the observation).
2. **Validate Constraints:** Confirm you have at least one constraint extracted before proceeding. If the instruction contains no filterable criteria, skip filtering and select the first available product.
3. **Parse the Observation:** Extract the list of products from the search results page (Product ID, Title, Price, Rating if available).
View the complete source on GitHubwebshop-result-page-navigator
When your agent uses it
Navigates through paginated search results by moving to the next or previous page. Use this skill when the current page of product listings does not contain a suitable match and you need to review more options. It identifies and clicks the appropriate pagination controls (e.g., 'next >' or '< prev') to load additional result pages for evaluation.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
364 tokensWhen the skill is activated
Reference documents
249 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Logic
- Usage in Trajectory
- Key Principle
Files
SKILL.mdcore1,801 bytesreferences/pagination_controls.mddoc1,127 bytes
Read SKILL.md
# Skill: WebShop Result Page Navigator
## Purpose
This skill enables systematic navigation through paginated product search results in a WebShop environment. It is triggered when the current page of results does not contain an item matching the user's criteria, allowing the agent to access more options.
## Core Logic
1. **Trigger Condition:** The agent has reviewed the current page of product listings and determined that no item satisfies the user's requirements (e.g., price, features).
2. **Action Selection:** The skill identifies the correct pagination control to click:
* `click[next >]` to load the subsequent page of results.
* `click[< prev]` to return to the previous page of results.
3. **Post-Action:** After navigation, the agent should resume its primary task of evaluating the newly loaded product listings against the user's instruction.
## Usage in Trajectory
The skill was demonstrated when the agent, searching for a pendant light under $120 with a dimmer switch, found no suitable options on Page 1. It correctly executed `click[next >]` to access Page 2, and repeated the action to access Page 3, where a potential match was found.
View the complete source on GitHubwebshop-search-constructor
When your agent uses it
This skill formulates an effective search query from structured product criteria. It is used when initiating a product search on an e-commerce platform, converting attributes into a concise, relevant keyword string. The input is a set of parsed criteria (e.g., 'jewelry box', '10 slots', 'easy to clean', 'price < $60'), and the output is a formatted search action string (e.g., 'search[jewelry box, 10 slots, less than $60, easy to clean]') optimized for the platform's search engine.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
475 tokensWhen the skill is activated
Reference documents
337 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Process
- Workflow Example
- Important Notes
Files
SKILL.mdcore2,048 bytesSKILL.mdcore2,048 bytesreferences/query_optimization_guide.mddoc1,443 bytes
Read SKILL.md
# Instructions
When tasked with finding a product on an e-commerce platform, use this skill to construct the initial search query.
## Core Process
1. **Receive Criteria:** You will be given a set of structured product criteria (e.g., product type, attributes, price limit).
2. **Construct Query:** Use the `construct_search_query.py` script to transform the criteria into a single, optimized search string. The script handles formatting and keyword ordering.
3. **Execute Action:** Format the script's output into the required platform action: `search[<constructed_query>]`.
## Workflow Example
**Input Criteria:** `{'product': 'jewelry box', 'attributes': ['10 slots', 'easy to clean'], 'price_limit': 60.00}`
**Skill Execution:**
1. Run the script: `python scripts/construct_search_query.py --product "jewelry box" --attributes "10 slots" "easy to clean" --price-limit 60.00`
2. The script returns: `jewelry box, 10 slots, less than $60, easy to clean`
3. You output the final action: `search[jewelry box, 10 slots, less than $60, easy to clean]`
View the complete source on GitHubwebshop-search-executor
When your agent uses it
Executes a search on an e-commerce platform using parsed keywords. Use when you have extracted search terms from a user query and need to perform the actual search[] action on the WebShop interface. Takes structured search terms and performs a search action, returning a list of product results for evaluation.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
426 tokensWhen the skill is activated
Reference documents
404 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Trigger Condition
- Edge Cases
- 2. Action Protocol
- 3. Example
Files
SKILL.mdcore1,980 bytesreferences/action_grammar.mddoc1,591 bytes
Read SKILL.md
# Instructions
## 1. Trigger Condition
Activate when the user provides an instruction to find or buy a product with specific attributes. The instruction will be in the `Observation`.
## Edge Cases
* If the search returns 0 results, retry with a broader query (e.g., drop the least critical attribute).
* If all results exceed the user's price constraint, try adding price-related terms or narrowing the product category.
## 2. Action Protocol
You must respond using **only** the following two action formats. Your final response must be in the exact structure:
**Thought:** [Your reasoning about the search terms to use based on the user's requirements.]
**Action:** `search[<keywords>]`
View the complete source on GitHubwebshop-search-formulator
When your agent uses it
This skill generates effective search keywords based on parsed product criteria. It is triggered after query parsing, when the agent needs to perform an initial product search on an e-commerce platform. The skill takes structured attributes (e.g., 'women's size 5 patent-beige high heel') and produces a concise, platform-appropriate search string designed to return relevant results, balancing specificity with recall.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
576 tokensWhen the skill is activated
Reference documents
660 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Key Principles for Search Formulation
- Example from Trajectory
- Action Format
Files
SKILL.mdcore2,708 bytesreferences/search_strategy_guide.mddoc2,734 bytes
Read SKILL.md
# Skill: Webshop Search Formulator
## Purpose
You are an expert at formulating the initial search query for an e-commerce product search. Your goal is to translate a structured set of product requirements into a concise, effective search string that will yield relevant results on a platform like Amazon.
## Core Workflow
1. **Input:** You receive a parsed query containing key product attributes (e.g., category, type, size, color, material, price limit).
2. **Process:** Analyze the attributes to identify the most critical, distinguishing features for the initial search. Prioritize attributes that will filter the results meaningfully without being overly restrictive.
3. **Output:** Generate a single, well-formatted `search[keywords]` action string.
## Key Principles for Search Formulation
* **Balance Specificity & Recall:** Start with a moderately specific query. Including 2-3 core attributes (e.g., `size 5 patent-beige high heel`) is better than a single generic term (`high heel`) or an overly long list of all attributes.
* **Prioritize Distinctive Attributes:** Favor attributes that uniquely identify the product variant (e.g., "patent-beige", "size 5") over very common ones (e.g., "women's") in the initial search.
* **Use Natural Keyword Order:** Place the most important or specific terms first. Mimic how a user might type the query.
* **Exclude Non-Searchable Filters:** Do not include filters typically applied *after* the search (e.g., price ranges like `< $90`) in the initial keyword string. These are for later refinement.View the complete source on GitHubwebshop-variant-chooser
When your agent uses it
This skill selects a product variant (e.g., size, quantity) from available options on a product detail page. It is triggered when a product page displays multiple choices, assessing the options (like '1.1 pound (pack of 1)' or 'pack of 2') and selecting one that aligns with user needs, often defaulting to a standard single unit if unspecified.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
385 tokensWhen the skill is activated
Reference documents
56 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Core Decision Logic
- Action Format
Files
SKILL.mdcore1,785 bytesreferences/trajectory.mddoc267 bytes
Read SKILL.md
# Instructions
## When to Use
Use this skill when you are on a product detail page and the observation contains a list of variant options (e.g., under a "size" or "quantity" heading). The skill is triggered by the presence of multiple clickable options that represent different configurations of the same product.
## Core Decision Logic
1. **Parse the Observation:** Identify the list of available variant options from the observation text. These are typically presented as clickable values after a label like "size".
2. **Assess User Needs:** Review the original user instruction for any explicit or implicit preferences regarding variant (e.g., budget constraints, desired quantity). If no preference is stated, default logic applies.
3. **Select and Act:** Choose the most appropriate variant and execute a `click[value]` action.
* **If user instruction specifies a constraint (e.g., "price lower than 40.00 dollars"):** Ensure the selected variant's price (if displayed) complies.
* **If no user preference is stated:** Prefer the standard, single-unit option (e.g., "1.1 pound (pack of 1)" over "pack of 2") as a sensible default.
* **If the choice is ambiguous:** You may need to click on a variant to see its updated price/details before finalizing the selection, as shown in the trajectory.
## Action Format
Your response must strictly follow this format:View the complete source on GitHubskillnet
When your agent uses it
Search, download, create, evaluate, analyze and route reusable agent skills with SkillNet. Use when asked to find or reuse a skill, turn a repo/document/trace into a skill, assess skill quality, build a local skill graph, select skills for a task, or fill a clearly identified capability gap with a reusable skill. 中文:搜索、下载、创建、评估、分析与路由技能。不用于普通代码修改或仅阅读文档。
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
1,277 tokensWhen the skill is activated
Reference documents
5,076 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose the workflow
- Runtime and configuration
- Find and use a skill
- Create and evaluate
- Results and recovery
Scripts executed separately
scripts/_skillnet_cli.pyscripts/skillnet_create.pyscripts/skillnet_validate.py
Files
SKILL.mdcore6,108 bytesSKILL.mdcore6,108 bytesreferences/api-reference.mddoc7,523 bytesreferences/platforms.mddoc3,159 bytesreferences/routing.mddoc1,796 bytesreferences/security-privacy.mddoc2,331 bytesreferences/setup.mddoc4,602 bytesreferences/workflow-patterns.mddoc3,187 bytesscripts/_skillnet_cli.pyruns1,165 bytesscripts/skillnet_create.pyruns1,611 bytesscripts/skillnet_validate.pyruns696 bytes
Read SKILL.md
# SkillNet
Find a useful skill, bring its complete resources into the workspace, create and
evaluate reusable skills, or analyze and route a local library through the SkillNet SDK.
## Choose the workflow
- **Analyze and route:** build a local skill graph, then select skills for a task.
Read [routing.md](references/routing.md) for separate model and SDK configuration.
- **Find:** search and return relevant candidates with URLs and tradeoffs.
- **Reuse or install:** inspect relevant skills already available, then search →
select → download → inspect → apply when the user requested its use.
- **Create:** choose one source → create through SkillNet → check structure → evaluate.
- **Evaluate:** evaluate the requested local skill or GitHub skill URL and explainView the complete source on GitHubSkills included
- alfworld-appliance-navigator
- alfworld-appliance-preparer
- alfworld-clean-object
- alfworld-device-operator
- alfworld-environment-scanner
- alfworld-goal-interpreter
- alfworld-heat-object-with-appliance
- alfworld-inventory-management
- alfworld-locate-target-object
- alfworld-location-navigator
- alfworld-navigation-planner
- alfworld-object-cooler
- alfworld-object-disposer
- alfworld-object-heater
- alfworld-object-locator
- alfworld-object-picker
- alfworld-object-placer
- alfworld-object-retriever
- alfworld-object-state-inspector
- alfworld-object-state-modifier
- alfworld-object-storer
- alfworld-object-transporter
- alfworld-open-receptacle
- alfworld-receptacle-closer
- alfworld-receptacle-finder
- alfworld-receptacle-navigator
- alfworld-receptacle-opener
- alfworld-receptacle-operator
- alfworld-receptacle-preparer
- alfworld-receptacle-searcher
- alfworld-search-pattern-executor
- alfworld-search-verifier
- alfworld-storage-explorer
- alfworld-task-verifier
- alfworld-temperature-regulator
- alfworld-tool-locator
- alfworld-tool-user
- scienceworld-ambiguous-action-resolution
- scienceworld-animal-identifier
- scienceworld-circuit-builder
- scienceworld-circuit-connector
- scienceworld-conditional-box-placer
- scienceworld-conditional-focus-executor
- scienceworld-conditional-placer
- scienceworld-conductivity-tester
- scienceworld-container-inspector
- scienceworld-container-item-retriever
- scienceworld-container-relocator
- scienceworld-container-transfer
- controlled-waiting
- scienceworld-device-activator
- scienceworld-environment-isolation
- scienceworld-environment-scanner
- scienceworld-growth-focuser
- scienceworld-heating-apparatus-setup
- scienceworld-instruction-reader
- scienceworld-inventory-focus
- scienceworld-inventory-manager
- scienceworld-item-fetcher
- scienceworld-liquid-filler
- scienceworld-liquid-pourer
- scienceworld-liquid-source-finder
- scienceworld-living-entity-identifier
- scienceworld-material-classifier
- scienceworld-measurement-taker
- scienceworld-mixture-creator
- scienceworld-object-classifier
- scienceworld-object-focuser
- scienceworld-object-locator
- scienceworld-object-placer
- scienceworld-object-retriever
- scienceworld-object-selector
- scienceworld-planting-coordinator
- scienceworld-planting-operation
- scienceworld-pot-preparer
- scienceworld-process-monitor
- scienceworld-process-pauser
- scienceworld-recipe-retriever
- scienceworld-result-archiver
- scienceworld-room-explorer
- scienceworld-room-navigator
- scienceworld-room-scanner
- scienceworld-room-teleporter
- scienceworld-substance-cooler
- scienceworld-substance-fetcher
- scienceworld-substance-preparator
- scienceworld-target-identifier
- scienceworld-target-locator
- scienceworld-task-focuser
- scienceworld-task-interpreter
- scienceworld-task-parser
- scienceworld-temperature-measurer
- scienceworld-threshold-evaluator
- scienceworld-tool-fetcher
- scienceworld-tool-user
- scienceworld-tool-validator
- soil-extraction
- task-completion-focus
- webshop-action-executor
- webshop-attribute-selector
- webshop-attribute-verifier
- webshop-initial-search
- webshop-option-selector
- webshop-price-checker
- webshop-product-detail-check
- webshop-product-detail-inspector
- webshop-product-detail-navigator
- webshop-product-evaluator
- webshop-product-search
- webshop-product-selector
- webshop-purchase-executor
- webshop-purchase-initiator
- webshop-query-interpreter
- webshop-query-parser
- webshop-result-analyzer
- webshop-result-filter
- webshop-result-page-navigator
- webshop-search-constructor
- webshop-search-executor
- webshop-search-formulator
- webshop-variant-chooser
- skillnet
Repository facts
- License
- MIT
- Created
- Jan 10, 2026
- Last pushed
- Nov 2, 2026
- Forks
- 155
- Open issues
- 0
- Project activity
- Active
Rank over the last 12 weeks
Now #662 · best #505 · down 108 in 30 days
- #654 on Nov 1
- #655 on Nov 2
- #658 on Nov 3
- #659 on Nov 4
- #660 on Nov 5
- #662 since Nov 6
58 earlier periods
- #504 on Aug 2
- #509 on Aug 7
- #503 on Aug 9
- #522 on Aug 10
- #520 on Aug 11
- #518 on Aug 12
- #505 on Aug 15
- #507 on Aug 16
- #509 on Aug 17
- #527 on Aug 18
- #521 on Aug 19
- #524 on Aug 21
- #508 on Aug 22
- #519 on Aug 23
- #513 on Aug 24
- #522 on Aug 25
- #512 on Aug 26
- #524 on Aug 27
- #530 on Sep 1
- #527 on Sep 2
- #512 on Sep 5
- #530 on Sep 7
- #548 on Sep 8
- #535 on Sep 11
- #531 on Sep 13
- #552 on Sep 14
- #553 on Sep 16
- #539 on Sep 19
- #552 on Sep 20
- #559 on Sep 21
- #567 on Sep 22
- #563 on Sep 23
- #547 on Sep 24
- #532 on Sep 25
- #535 on Sep 26
- #544 on Sep 27
- #545 on Sep 28
- #562 on Sep 29
- #548 on Sep 30
- #539 on Oct 1
- #527 on Oct 3
- #528 on Oct 4
- #538 on Oct 5
- #549 on Oct 6
- #554 on Oct 7
- #574 on Oct 8
- #570 on Oct 9
- #555 from Oct 10 to Oct 11
- #576 on Oct 14
- #573 on Oct 15
- #576 on Oct 16
- #567 on Oct 17
- #585 on Oct 19
- #592 on Oct 20
- #639 on Oct 25
- #646 on Oct 28
- #648 on Oct 29
- #651 from Oct 30 to Oct 31
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 25 notes
experiments/src/skills/alfworld/alfworld-object-picker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-picker/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-object-transporter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/alfworld/alfworld-receptacle-preparer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-container-transfer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-filler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-filler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-filler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-filler/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-pourer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-pourer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-pourer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-pourer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-source-find/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-source-find/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexperiments/src/skills/scienceworld/scienceworld-liquid-source-find/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 11 network referencesin 3 files: skillnet/references/platforms.md:44 skillnet/references/setup.md:50 skillnet/references/workflow-patterns.md:24
- No hidden or obfuscated text
- No instruction overrides
- 3 executable scriptsin 3 files: skillnet/scripts/_skillnet_cli.py:1 skillnet/scripts/skillnet_create.py:1 skillnet/scripts/skillnet_validate.py:1
- 12 references to secretsin 9 files: skillnet/references/routing.md:7 skillnet/references/setup.md:42 alfworld-goal-interpreter/references/search_patterns.md:15 and 6 more
- No requests to vote in Hot
Show all 26 signals by file
experiments/src/skills/alfworld/alfworld-goal-interpreter/references/search_patterns.md
- Access to secretsline 15
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-inventory-management/SKILL.md
- Access to secretsline 69
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-navigation-planner/references/action_primer.md
- Access to secretsline 27
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-search-pattern-executor/SKILL.md
- Access to secretsline 39
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-search-pattern-executor/references/common_sense_locations.md
- Access to secretsline 21
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-search-verifier/SKILL.md
- Access to secretsline 36
[Credential-related source omitted]
experiments/src/skills/alfworld/alfworld-tool-locator/SKILL.md
- Access to secretsline 37
[Credential-related source omitted]
skills/skillnet/references/platforms.md
- Network accessline 44
Sources: - Codex: https://learn.chatgpt.com/docs/build-skills - Network accessline 45
- Codex: https://learn.chatgpt.com/docs/build-skills - Network accessline 46
- Claude Code: https://code.claude.com/docs/en/skills - Network accessline 47
- dsh: https://github.com/deepseek-ai/deepseek-harness/blob/ddefc45fbc7f8e46dd73185e68295696d1297887/docs/subsystems/skills.zh.md - Network accessline 48
- WorkBuddy: https://www.codebuddy.cn/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Skills-Market
skills/skillnet/references/routing.md
skills/skillnet/references/setup.md
- Access to secretsline 42
[Credential-related source omitted] - Network accessline 50
Precedence is explicit SDK/CLI arguments → nonempty environment variables → user config → defaults. Defaults remain `gpt-4o`, `https://api.openai.com/v1`, and - Network accessline 51
config → defaults. Defaults remain `gpt-4o`, `https://api.openai.com/v1`, and - Network accessline 52
`http://api-skillnet.openkg.cn` for search. Choose the correct model when using a - Network accessline 67
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Network accessline 83
skillnet configure --base-url "https://your-provider.example/v1" --model "your-model"
skills/skillnet/references/workflow-patterns.md
- Network accessline 24
skillnet create --github "https://github.com/owner/repository" --max-files 20 --output-dir "./generated_skills" --evaluate --json
skills/skillnet/scripts/_skillnet_cli.py
- Executable scriptline 1
Executable file
skills/skillnet/scripts/skillnet_create.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/skillnet/scripts/skillnet_validate.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md experiments/src/skills/alfworld/alfworld-appliance-navigator/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/zjunlp-skillnet/)