document-skill
Skill10 starsChanged 3 months agoMITView on GitHub
Automate documentation updates to SKILLS.md after creating or modifying a skill
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- instructions/claude.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adr-authorSkill
- analyze-r-packageSkill
- bioc-howtoSkill
- bioc-pkg-devSkill
- bioc-pkg-finderSkill
- bioc-pkg-reviewSkill
- build-check-bioccheckSkill
- check-bioconductor-skillsSkill
- create-package-instructionsSkill
- create-skillSkill
- improve-code-coverageSkill
- migrate-datapkg-to-zenodoSkill
- security-audit-r-packageSkill
- update-package-instructionsSkill
- update-r-newsSkill
- validate-skillSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Generate SKILLS.md Entry: Create a new entry following the format specified in SKILLS.md.
- Distinctive: line 30
Check if the skill already exists in SKILLS.md.
- Distinctive: line 32
Update the "By Category" and "By Tag" tables.
- Distinctive: line 33
Ask the user if the skill should be added to the "Finding Skills by Use Case" section in USAGE.md.
- Distinctive: line 54
validate-skill: Should be run before document-skill to ensure standards compliance.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
document-skill
Automate updating SKILLS.md after creating or modifying a skill. Reads the skill file, generates entries, and updates all relevant sections with user confirmation.
Usage
Invoke this skill after creating or modifying a skill file:
- "Document the new skill I just created"
- "Update SKILLS.md for the validate-r-docs skill"
Prerequisites
- Skill file exists at
skills/{skill-name}/SKILL.md - SKILLS.md exists in the repository root
Process
- Input and Validation: Parse the
skills/{skill-name}/SKILL.mdfile to extract YAML frontmatter and main sections. - Generate SKILLS.md Entry: Create a new entry following the format specified in SKILLS.md. Auto-generate 2-3 natural language invocation examples. Present the generated entry to the user for confirmation and editing.
- Update SKILLS.md Sections:
- Check if the skill already exists in SKILLS.md. If so, prompt to replace.
- Insert the entry alphabetically into the appropriate domain section.
- Update the "By Category" and "By Tag" tables.
- Ask the user if the skill should be added to the "Finding Skills by Use Case" section in USAGE.md.
- Confirm and Apply: Show a summary of changes to SKILLS.md and apply them upon user confirmation.
Output Format
This skill produces an updated SKILLS.md file. No new files are created.
Examples
Example: Documenting a New Skill
User: "Document the validate-r-docs skill I just created" Agent:
- Reads
skills/validate-r-docs/SKILL.md. - Generates entry with invocation examples and shows a preview.
- Adds to the "R/Bioconductor Domain" section and updates Category/Tag tables.
- User confirms, SKILLS.md is updated.
- Reports: "✅ Documentation updated successfully!"
Integration with Other Skills
- create-skill: Automatically invoked at the end of the skill creation workflow.
- validate-skill: Should be run before document-skill to ensure standards compliance.
Related: See SKILLS.md for the skill catalog format.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

