Add lean-comments skill 🤖🤖🤖

[JonathanXDR]

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 adds a new instruction, prompt, agent, skill, workflow, or canvas extension file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, workflow, or canvas extension with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the main branch for this pull request.

---

Description

Adds lean-comments, a skill that decides whether a source-code comment should exist before deciding how it should read.

The default is no comment. A comment survives only when it preserves meaningful, non-obvious information a competent maintainer could not recover from the code, names, types, signatures, tests, configuration, or nearby repository context. Everything else gets removed rather than reworded.

It covers line comments, doc comments, docstrings, file headers, and stale TODO / FIXME / HACK markers, and it protects lint, compiler, and license directives. It refuses to invent a security, performance, or compatibility rationale to justify keeping a comment, which is the common failure mode when an agent is asked to "improve the comments".

Source repository: https://github.com/JonathanXDR/lean-comments (MIT).

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• New canvas extension.
• Update to existing instruction, prompt, agent, plugin, skill, workflow, or canvas extension.
• Other (please specify):

---

Additional Notes

On the one unchecked box: this skill has been used in day-to-day agent work and validated against this repository's own gates (npm run skill:validate passes for all 419 skills, and npx @microsoft/vally-cli lint skills/lean-comments reports 2/2 checks passed), but I have not run it specifically inside GitHub Copilot, so I have left that box unticked rather than tick it on assumption.

On overlap: the two existing comment-related skills, add-educational-comments and comment-code-generate-a-tutorial, both add explanatory commentary for teaching. This one is the inverse. It removes commentary that carries no information, so it does not duplicate either.

docs/README.skills.md was regenerated with npm start and contains exactly the one new row.

[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: HIGH risk

Check	Risk
Profile	HIGH
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	✅ lean-comments (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/lean-comments
✅ lean-comments (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