chore(validation): Added first approach of SKILL_CHECKLIST file and validation script

[r2dedios]

Summary

Introduces a SKILL validation script and a checklist with AgentSKills.io Specification requirements + our Claude Design patterns

Pack(s) affected

• rh-sre
• rh-developer
• ocp-admin
• rh-support-engineer
• rh-virt
• 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)

[dmartinol]

1- we need to find a single definition for the Skill specification document.
Let's compare SKILL_CHECKLIST.md from this PR and SKILL_DESIGN_PRINCIPLES.md from the main branch
2- I think python better fits the need to implement the compliance check, but we can add to it the missing checks that you added here.
WDYT?

[r2dedios]

@dmartinol I modified the workflow for using ONLY the Skill Specification Linter script following the agentskills.io specs.

It also should detect the changes on the PR to do not evaluate every SKILL everytime. If you want to try it by your own, checkout this PR and run ./scripts/run-skill-linter.sh

[dmartinol]

a few minor comments. haven't tested locally yet, but I will
Thank you!

[r2dedios]

@dmartinol SKILL design files were merged and workflow scripts updated

[dmartinol]

thank you!