Improve create-agentsmd with evidence-based validation 🤖🤖🤖

[sunxiayi]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution updates an existing skill in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested this skill with GitHub Copilot.
• I have run npm start and verified that generated documentation is up to date.
• I am targeting the main branch for this pull request.

---

Description

This rewrites the existing create-agentsmd skill from a generic template into an evidence-first workflow for creating, revising, and auditing repository AGENTS.md files.

The update:

• preserves accurate maintainer-authored instructions instead of replacing them wholesale;
• derives commands and conventions from repository manifests, CI, docs, and representative source files;
• explains root and nested AGENTS.md scope for monorepos;
• separates safe local validation from destructive, deployment, or production operations;
• requires a maintainer-style diff review and honest reporting of untested claims;
• replaces placeholder-heavy guidance with shorter, directly actionable instructions.

The generated skill catalog entry is updated to match the new description.

---

Type of Contribution

• Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.

---

Validation

• npm run skill:validate — all 415 skills passed
• npm start — generated documentation and marketplace data are up to date
• git diff --check — passed
• the standalone skill validator — passed

Affiliation disclosure

The optional browser-local second-opinion link is Repo Agent Kit, which I maintain. It is free, requires no signup, processes pasted content in the browser, and is explicitly presented as optional rather than a substitute for repository evidence or local validation.

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

🔒 PR Risk Scan Results

Scanned 1 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🟡 Contributor Reputation Check: MEDIUM risk

Check	Risk
Profile	MEDIUM
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	✅ create-agentsmd (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️	✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️	1 skill(s) linted, 1 passed

Full linter output

### Linting skills/create-agentsmd
✅ create-agentsmd (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed