fix: Added rh-automation CLAUDE.md

[dmartinol]

Summary

Added rh-automation CLAUDE.md

Pack(s) affected

• rh-sre
• rh-developer
• ocp-admin
• rh-virt
• rh-ai-engineer
• rh-automation
• Other / repo-wide

Change type

• New skill
• New agent
• New pack
• Update existing skill / agent
• MCP server config (.mcp.json)
• Docs / README
• CI / tooling

CLAUDE.md compliance

• Agents orchestrate skills; no direct MCP/tool calls in agents
• Skills are single-purpose task executors
• Skills encapsulate all tool access (MCP tools invoked only inside skills)
• Document consultation: file is read with the Read tool, then declared to the user
• No credentials hardcoded; env vars used via ${VAR} references
• Human-in-the-loop confirmation added for any destructive or critical operations

Validation

• make validate passes locally
• New/changed skills have valid YAML frontmatter (name, description)
• New/changed agents have valid YAML frontmatter (name, description)

[github-actions]

Gemini Code Review

1. Summary

This PR introduces the CLAUDE.md instruction routing file for a new rh-automation pack. It defines the persona (AAP engineer assistant), enforces the skill-first rule, maps user intents to specific skills, outlines skill chaining/orchestration, documents the required MCP servers, and establishes global security and execution rules.

2. Project Rules Compliance

Overall, the content of the CLAUDE.md file perfectly aligns with the project's structural requirements for pack-level routing files. However, there is a missing repository-level requirement for new packs:

• ❌ New Pack Registration: Because rh-automation is a new pack, you must add rh-automation to the PACK_DIRS list in scripts/validate_structure.py. This ensures the automated linter validates this new directory.
• ⚠️ Build Reminder: Since you are adding a new pack and modifying agent/skill routing, please ensure you run make validate locally to verify everything passes the automated checks.
• ✅ Skill Invocation: Excellent job using the standard /skill-name slash format (e.g., /governance-executor) throughout the document.
• ✅ Required Sections: The file correctly includes all mandatory sections (## Skill-First Rule, ## Intent Routing, ## MCP Servers, ## Global Rules).
• ✅ Security: The global rules correctly emphasize credential safety and the use of ${ENV_VAR} references.

3. Code Quality Issues

No bugs or logic errors were found in the markdown content itself. The intent routing table is well-structured, and the distinction between orchestration skills and standalone skills is clearly articulated.

4. Suggestions

• Missing Pack Files: I only see CLAUDE.md in this diff. If they aren't included in other commits within this PR, remember that creating a new agentic pack also requires a README.md (with description, persona, marketplaces) and the .mcp.json file for the MCP server configurations mentioned in your document.
• Main README: Don't forget to update the main repository README.md table with a link to this new rh-automation pack.

5. Verdict

REQUEST_CHANGES — The CLAUDE.md content is excellent, but the PR must include the addition of rh-automation to PACK_DIRS in scripts/validate_structure.py to comply with the project rules for new packs. Once that one-line addition is made, this is good to go!

---

Automated review by Gemini 3.1 Pro | Rules: CLAUDE.md, SKILL_DESIGN_PRINCIPLES.md

[dmartinol]

• ❌ New Pack Registration: Because rh-automation is a new pack, you must add rh-automation to the PACK_DIRS list in scripts/validate_structure.py. This ensures the automated linter validates this new directory.

The rh-automation folder is already present in the PACK_DIRS constant:

# List of agentic collections to validate
PACK_DIRS = ['rh-sre', 'rh-developer', 'ocp-admin', 'rh-support-engineer', 'rh-virt', 'rh-ai-engineer', 'rh-automation']

Rejecting the comment