Individual skill
atlas-commerce-ops-solver
Solve Atlas Commerce Operations benchmark tasks that provide a prompt, request payload JSON, answer_template.json, and authenticated task-environment API. Use for SQL-based operational analytics, cutoff/as-of metrics, strict answer.json generation, and approved canonical corrections with correction_audit verification.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_022/fewshot/codex/fewshot_attempt_01/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 121
- Repository last updated
- Oct 29, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- data Derived category
- operations Derived category
- data-databases Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 3,349 bytesSKILL.mdcore · 3,349 bytesSKILL.mdcore · 3,349 bytesSKILL.mdcore · 3,349 bytesSKILL.mdcore · 3,349 bytesagents/openai.yamlasset · 220 bytesreferences/api.mddoc · 2,220 bytesreferences/metric-patterns.mddoc · 6,868 bytesscripts/atlas_api.pyruns · 5,000 bytes
Read excerpt
# Atlas Commerce Ops Solver
## Core Workflow
1. Read the task prompt, every request payload under `input/payloads/`, and `answer_template.json` before querying data. Treat the request payload as the business contract and the template as the output contract.
2. Load the live schema and data dictionary from the task environment. Use [references/api.md](references/api.md) for the endpoint contract and `scripts/atlas_api.py` for repeatable calls.
3. Build the answer from SQL, not from denormalized intuition. Start with a cohort CTE, add one CTE per metric, then run independent count checks for every requested denominator, numerator, and sorted list.
4. Use [references/metric-patterns.md](references/metric-patterns.md) when the task involves effective source rows, cutoff state, refunds, fulfillment, carrier corrections, warehouse productivity, support health, or inventory movements.
5. Write exactly one JSON object to `answer.json`. Match required keys, nesting, array lengths, sorting, number precision, enum values, and `additionalProperties` restrictions from the template. Do not include commentary outside the JSON document.
## Query Discipline
- Preserve UTC text timestamps and compare them lexicographically only when they are all ISO-8601 UTC strings. Apply inclusive and exclusive boundaries exactly as stated.
- Distinguish current snapshot columns from append-only event/scans tables. When the request says `effective`, `as of cutoff`, or similar, derive state from the relevant source event stream at or before the cutoff.