chore(review): replace adversarial CodeRabbit with skill-validator refs

Remove the cynical adversarial reviewer persona from .coderabbit.yaml
and replace with per-path instructions that reference
tools/skill-validator.md as the single source of truth — matching the
approach already used in .augment/code_review_guidelines.yaml.

Add skill-validator pointer to AGENTS.md so all AI tools can discover it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.coderabbit.yaml

@@ -60,23 +60,33 @@ reviews:
     - "!**/validation-report-*.md"
     - "!CHANGELOG.md"
   path_instructions:
-    - path: "**/*"
+    - path: "src/**/skills/**"
       instructions: |
-        You are a cynical, jaded reviewer with zero patience for sloppy work.
+        Skill file. Apply the full rule catalog defined in tools/skill-validator.md.
-        This PR was submitted by a clueless weasel and you expect to find problems.
+        That document is the single source of truth for all skill validation rules
-        Be skeptical of everything.
+        covering SKILL.md metadata, workflow.md constraints, step file structure,
-        Look for what's missing, not just what's wrong.
+        path references, variable resolution, sequential execution, and skill
-        Use a precise, professional tone — no profanity or personal attacks.
+        invocation syntax.
-
+    - path: "src/**/workflows/**"
-        Review with extreme skepticism — assume problems exist.
+      instructions: |
-        Find at least 10 issues to fix or improve.
+        Legacy workflow file (pre-skill conversion). Apply the full rule catalog
-
+        defined in tools/skill-validator.md — the same rules apply to workflows
-        Do NOT:
+        that are being converted to skills.
-        - Comment on formatting, linting, or style
+    - path: "src/**/tasks/**"
-        - Give "looks good" passes
+      instructions: |
-        - Anchor on any specific ruleset — reason freely
+        Task file. Apply the full rule catalog defined in tools/skill-validator.md.
-
+    - path: "src/**/*.agent.yaml"
-        If you find zero issues, re-analyze — this is suspicious.
+      instructions: |
+        Agent definition file. Check:
+        - Has metadata section with id, name, title, icon, and module
+        - Defines persona with role, identity, communication_style, and principles
+        - Menu triggers reference valid skill names that exist
+    - path: "docs/**/*.md"
+      instructions: |
+        Documentation file. Check internal markdown links point to existing files.
+    - path: "tools/**"
+      instructions: |
+        Build script/tooling. Check error handling and proper exit codes.
 chat:
   auto_reply: true # Response to mentions in comments, a la @coderabbit review
 issue_enrichment:

AGENTS.md

@@ -7,3 +7,5 @@ Open source framework for structured, agent-assisted software delivery.
 - Use Conventional Commits for every commit.
 - Before pushing, run `npm ci && npm run quality` on `HEAD` in the exact checkout you are about to push.
   `quality` mirrors the checks in `.github/workflows/quality.yaml`.
+
+- Skill validation rules are in `tools/skill-validator.md`.