Add Mutagent CLI skill: eval-driven prompt optimization

[bene-mutagent]

Adds the Mutagent CLI skill — open-source (MIT) Agent Skills bundle backed by the @mutagent/cli.

What it does: Gives AI engineers an eval-driven loop for prompt and agent optimization — explore codebase → upload prompt → curate dataset → score against rubrics → optimize against measurable targets. Native framework tracing adapters for Mastra, LangChain, LangGraph, Vercel AI SDK.

Why we're adding here: Fits the skills template as a CLI-backed eval/optimization workflow — sits naturally next to llm-evaluation, langfuse, observability-langsmith, and prompt-engineer under cli-tool/components/skills/ai-research/.

Conforms to: Anthropic Agent Skills spec (SKILL.md format with YAML frontmatter — name, description, source, date_added — matching the convention used by langfuse, llm-evaluation, and other community skills in the same directory).

Credibility: 9.6k npm downloads / 30d on @mutagent/cli. v0.1.185. Runtime-agnostic (Claude Code, Cursor, Aider, Continue).

Files added:

• cli-tool/components/skills/ai-research/mutagent-cli/SKILL.md

The SKILL.md follows the community-skill template style (frontmatter + Role/Capabilities/Requirements/Patterns/Anti-Patterns/Sharp Edges/Related Skills sections). The full canonical SKILL.md (with subfile router, all workflows, all concept docs) lives upstream and is linked from the Resources section.

Source: https://github.com/mutagent-io/skills
npm: https://www.npmjs.com/package/@mutagent/cli
Docs: https://docs.mutagent.io

Happy to adjust naming, placement (different category folder?), or trim further to match conventions.

---

Summary by cubic

Adds the Mutagent CLI skill for eval-driven prompt and agent optimization using @mutagent/cli. Enables explore → dataset → rubric → optimize workflows with adapters for Mastra, LangChain, LangGraph, and Vercel AI SDK.

• Area: components (cli-tool/components/)
• New component added: skills/ai-research/mutagent-cli/SKILL.md (Agent Skills spec with YAML frontmatter)
• Catalog: Regenerate docs/components.json to include this skill
• No changes to CLI/API/website/workers and no new env vars or secrets required

^{Written for commit 3ea938c. Summary will update on new commits.}

[vercel]

@bene-mutagent is attempting to deploy a commit to the Daniel Avila's projects Team on Vercel.

A member of the Team first needs to authorize it.

[github-actions]

👋 Thanks for contributing, @bene-mutagent!

This PR touches cli-tool/components/** and has been marked review-pending.

What happens next

1. 🤖 Automated security audit runs and posts results on this PR.
2. 👀 Maintainer review — a human reviewer validates the component with the component-reviewer agent (format, naming, security, clarity).
3. ✅ Merge — once approved, your PR is merged to main.
4. 📦 Catalog regeneration — the component catalog is rebuilt automatically.
5. 🚀 Live on aitmpl.com — your component appears on the website after deploy.

While you wait

• Check the Security Audit comment below for any issues to fix.
• Make sure your component follows the contribution guide.

This is an automated message. No action is required from you right now — a maintainer will review soon.

[cubic-dev-ai]

No issues found across 1 file