Sensei - Skill Frontmatter Compliance

Name: Sensei - Skill Frontmatter Compliance
Rating: 88 (1 reviews)
Author: spboyer

Trust Score 88/100

from spboyer

Iteratively improves SKILL.md frontmatter using the Ralph loop to meet compliance and testing standards.

triggers:run senseisensei helpimprove skillfix frontmatterscore skillfrontmatter audit

Sensei

A workflow skill that automates frontmatter improvement for SKILL.md files using the Ralph loop pattern.

What it does

Reads SKILL.md frontmatter and scores compliance
Scaffolds tests and improves descriptions to include routing triggers
Runs token checks and can run GEPA optimization for deep improvements

When to use

Ask Sensei to audit or improve a skill's frontmatter, fix triggers, or optimise for token budget and routing clarity.

Examples

"run sensei on my-skill"
"sensei help"

Output

Improved SKILL.md frontmatter with WHEN: trigger phrases
Test scaffolding and compliance report

Notes

Invokes token counting tools, test runners, and git commands. Designed as a utility for maintainers and CI workflows.

Audit Summary

Sensei is a workflow skill that iteratively improves SKILL.md frontmatter compliance using the Ralph loop pattern. It has no bundled scripts — instead it instructs the agent to run npm/pip commands for token counting and GEPA optimization. Well-documented with clear steps, scoring rubrics, and multiple invocation modes, but the actual execution depends entirely on external tooling (npm, gepa, gh auth) that must be pre-installed.

Watch Out

Requires npm and gepa pip package for full functionality
Uses gh auth token for LLM API calls in GEPA mode
No bundled scripts — all execution is agent-driven via referenced external tools

Notes

Clean skill with no security concerns. Thorough documentation and good structure following the skill spec. Niche usefulness as it targets skill authors maintaining multiple skills. The GEPA evolutionary optimization mode is an interesting advanced feature but adds complexity and dependency on external packages.

Information

Repository: spboyer
Installs: 0

Trust Score

Overall88

Security95

Code Quality82

Architecture78

Usefulness55

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

ds-fix — data-science mid-analysis fixer

Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

SHIP Score Interview

Run a structured SHIP interview to score and prioritise product features or bugs (Income + Strategy - Perspiration). Guides the agent to reach 90-95% confidence

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Back to Skills