validate-skill
Skill10 starsChanged 3 months agoMITView on GitHub
Validate that a skill conforms to the ai-agent-skills repository standards
3 other projects use a version of this.
Adopted by
Most recently taken up by
- unional/skillstheir own version, first seen Nov 6, 2026
- DunoDoge/OHOS-Skillstheir own version, first seen Sep 6, 2026
- MSiccDev/ai-context-kittheir own version, first seen Jul 7, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- MSiccDev/ai-context-kit★ 12same name
- DunoDoge/OHOS-Skills★ 1same name
- unional/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- document-skillSkill
- improve-code-coverageSkill
- migrate-datapkg-to-zenodoSkill
- security-audit-r-packageSkill
- update-package-instructionsSkill
- update-r-newsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 36
Run Generic Validation (Optional): If available, run markdownlint on the file, and validate the YAML frontmatter syntax (e.g., by …
- Very specific: line 37
Validate Repository Standards: Check the file against the requirements in AGENTS.md and SKILL_STANDARD.md.
- Very specific: line 38
Ensure the YAML frontmatter contains required fields and no prohibited fields (platforms, triggers).
- Distinctive: line 39
Check that the structure matches the standard format.
- Distinctive: line 40
Verify agent neutrality (no tool references or platform commands in instructions).
- Distinctive: line 42
Ensure it does not duplicate content from SSOT documents.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
validate-skill
Validate that a skill conforms to bioconductor standards. Uses generic validators (markdownlint, yamllint) for basic checks, then adds bioconductor-specific validation for platform-agnostic compliance and repository conventions.
Usage
Invoke this skill to validate a skill file:
- "Validate this skill"
- "Check if skills/[skill-name]/SKILL.md meets standards"
Prerequisites
- Target skill file exists at
skills/{skill-name}/SKILL.md - Optional:
markdownlintandyamllintinstalled
Note — CI/CD integration: The deterministic subset of these checks (frontmatter completeness, directory-name matching, name uniqueness, SKILLS.md sync, broken links, version bump) runs automatically via GitHub Actions on every PR that modifies a
SKILL.mdfile. Use this skill for interactive local validation before opening a PR and for the full subjective review (agent neutrality, verbosity, SSOT compliance) that the static script cannot evaluate.
Process
- Locate Target Skill: Determine the skill to validate from the user's prompt or current directory.
- Run Generic Validation (Optional): If available, run
markdownlinton the file, and validate the YAML frontmatter syntax (e.g., by extracting the frontmatter and runningyamllint -d relaxedon it). - Validate Repository Standards: Check the file against the requirements in AGENTS.md and SKILL_STANDARD.md.
- Ensure the YAML frontmatter contains required fields and no prohibited fields (
platforms,triggers). - Check that the structure matches the standard format.
- Verify agent neutrality (no tool references or platform commands in instructions).
- Confirm it describes a workflow, not just code snippets.
- Ensure it does not duplicate content from SSOT documents.
- Ensure the YAML frontmatter contains required fields and no prohibited fields (
- Generate Validation Report: Produce a summary of passed and failed checks, categorized by CRITICAL, WARNING, and INFO.
- Suggest Next Steps: Offer to help fix any identified issues.
Output Format
Generate a validation report in markdown format:
# Skill Validation Report: [skill-name]
**Status**: ✅ PASS | ❌ FAIL ([N] issues)
## Generic Validation
**markdownlint**: ✅ PASS | ⚠️ [N] warnings
**YAML frontmatter**: ✅ PASS | ❌ FAIL
## Bioconductor-Specific Validation
### CRITICAL Issues (Must Fix)
❌ **[Issue title]** ([location])
- Issue: [What violates standards]
- Fix: [How to fix it]
- Reference: [AGENTS.md or SKILL_STANDARD.md section]
### WARNING Issues (Should Fix)
⚠️ **[Issue title]** ([location])
### INFO Issues (Optional Improvements)
ℹ️ **[Issue title]** ([location])Examples
Example: Validating a Skill
User: "Check if the analyze-r-package skill meets standards" Agent:
- Locates
skills/analyze-r-package/SKILL.md - Runs generic and repository-specific validations
- Reports results, identifying any CRITICAL or WARNING issues.
See also: SKILL_STANDARD.md, AGENTS.md
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.

