Individual skill
skill-writer
Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Use when asked to "create a skill", "write a skill", "synthesize sources into a skill", "improve a skill from positive/negative examples", "update a skill", or "maintain skill docs and registration". Handles source capture, precision passes, authoring, registration, and validation.
skills/skill-writer/SKILL.md
Source commit 0c464f411bdfb8d4c12314b36264d06cb2f60270
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 4, 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)
- 1,135
- Repository last updated
- Nov 5, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- tag-production Repository topic
- docs 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
EVAL.mddoc · 6,545 bytesSKILL.mdcore · 10,017 bytesSKILL.mdcore · 10,017 bytesSKILL.mdcore · 10,017 bytesSKILL.mdcore · 10,017 bytesSOURCES.mddoc · 19,540 bytesSPEC.mddoc · 9,960 bytesevals/axis.config.jsonasset · 318 bytesevals/scenarios/iteration-from-bad-output.jsonasset · 2,911 bytesevals/scenarios/reference-backed-integration.jsonasset · 1,981 bytesevals/scenarios/small-inline-workflow.jsonasset · 1,956 bytesreferences/authoring-path.mddoc · 4,772 bytesreferences/claude-argument-substitutions.mddoc · 624 bytesreferences/claude-dynamic-context.mddoc · 579 bytesreferences/claude-frontmatter-invocation.mddoc · 1,962 bytesreferences/claude-hook-backed.mddoc · 913 bytesreferences/claude-subagent-fork.mddoc · 718 bytesreferences/description-optimization.mddoc · 1,034 bytesreferences/design-principles.mddoc · 3,736 bytesreferences/example-documentation-skill.mddoc · 2,819 bytesreferences/example-hook-backed-skill.mddoc · 989 bytesreferences/example-router-skill.mddoc · 1,039 bytesreferences/example-subagent-fork-skill.mddoc · 1,079 bytesreferences/example-workflow-process-skill.mddoc · 2,503 bytesreferences/execution-shapes.mddoc · 4,695 bytesreferences/iteration-evidence.mddoc · 2,676 bytesreferences/iteration-path.mddoc · 1,505 bytesreferences/layout-argument-driven-skill.mddoc · 1,056 bytesreferences/layout-asset-template-skill.mddoc · 809 bytesreferences/layout-inline-skill.mddoc · 731 bytesreferences/layout-reference-backed-skill.mddoc · 1,256 bytesreferences/layout-script-backed-workflow.mddoc · 846 bytesreferences/mode-selection.mddoc · 3,310 bytesreferences/output-contracts.mddoc · 1,097 bytesreferences/reference-architecture.mddoc · 2,537 bytesreferences/registration-validation.mddoc · 3,600 bytesreferences/skill-evals.mddoc · 5,771 bytesreferences/source-adaptation.mddoc · 2,194 bytesreferences/source-discovery.mddoc · 2,631 bytesreferences/spec-template.mddoc · 2,213 bytesreferences/structure-troubleshooting.mddoc · 4,073 bytesreferences/synthesis-path.mddoc · 3,822 bytesreferences/workflow-orchestrator-workers.mddoc · 652 bytesreferences/workflow-parallel.mddoc · 540 bytesreferences/workflow-plan-validate-execute.mddoc · 678 bytesreferences/workflow-prompt-chaining.mddoc · 548 bytesreferences/workflow-routing.mddoc · 828 bytesreferences/workflow-validation-loops.mddoc · 658 bytesscripts/quick_validate.pyruns · 4,759 bytes
Read excerpt
# Skill Writer
Use this as the single canonical workflow for skill creation and improvement.
Primary success condition: maximize high-value input coverage before authoring while minimizing wasted runtime tokens.
Follow the workflow steps in order. Load only the reference files required for the step you are on.
`SKILL.md` is the primary router: every bundled reference file should be flat under `references/` and listed here with a direct "open when..." reason.
## Core Workflow References
| Open when you need to... | Read |
|--------------------------|------|
| choose the minimum workflow path for create, update, iterate, or research-first work | `references/mode-selection.md` |
| choose the simplest adequate execution shape before deciding files | `references/execution-shapes.md` |