Refines and scores skill metadata files using the Ralph loop pattern to ensure they meet repository compliance standards.

Install

mkdir -p .claude/skills/sensei && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10440" && unzip -o skill.zip -d .claude/skills/sensei && rm skill.zip

Installs to .claude/skills/sensei

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.
372 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Audit skill frontmatter compliance
  • Fix malformed frontmatter
  • Improve skill documentation
  • Run compliance tests
  • Optimize token usage

How it works

It iteratively improves skill frontmatter using a Ralph loop pattern until compliance scores and tests pass.

Inputs & outputs

You give it
Skill name or batch
You get back
Compliant skill frontmatter

When to use sensei

  • Auditing repository skill compliance
  • Fixing malformed skill frontmatter
  • Improving skill documentation scores

About sensei

Sensei iteratively improves skill frontmatter until it passes compliance tests. It checks for correct metadata, token usage, and adherence to documentation standards.

**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git co

When not to use it

  • Single operations (use token CLI)

Limitations

  • Max 5 iterations per skill
  • Requires manual final commit

How it compares

This automates the compliance and quality improvement process compared to manual auditing.

Compared to similar skills

sensei side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
sensei (this skill)01moReviewAdvanced
cursor-local-dev-loop325dReviewBeginner
codex-worker16moReviewAdvanced
agent-challenges16moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry