Fix stale AGENTS.md Validation step 3 (`.skills=="skills/"` contradicts auto-discovery convention)

[devantler]

🤖 Generated by the Daily AI Engineer

Problem. AGENTS.md → Validation step 3 asserts each plugin.json has .skills == "skills/", but the repo convention now omits the bare-string skills/agents fields (they are auto-discovered). Running the documented step 3 locally reports BAD fields for all 8 plugins — the doc snippet drifted from the real CI gate (CI validates via the real tool, not this check). Found while running the documented validation for #63.

Proposed direction. Update the step-3 snippet to match the actual convention (drop the .skills=="skills/" assertion; validate the non-empty name/description/version + the presence of a skills/ dir with at least one SKILL.md, consistent with CI). Trivial doc fix.

Size. XS.

[coderabbitai]

🔗 Related PRs

#32 - ci: guard README plugin table ↔ filesystem parity [merged]
#34 - docs: describe the live multi-upstream skill-sourcing model [merged]
#36 - feat: bundle in-house agent-skills into category plugins [merged]
#41 - ci: guard that every bundled SKILL.md carries upstream provenance [merged]
#53 - fix: omit skills/agents path fields so plugins install in Claude Code [merged]

---

📝 Issue Planner

_{Check the box below or use the @coderabbitai plan command to generate an implementation plan and prompts that you can use with your favorite coding assistant.}

• Create Plan

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord!