Plugin

skill-compass

Name: skill-compass
Author: evol-ai

Locally evaluate Claude Code/OpenClaw skills for quality across six dimensions and security risks using JS validators and LLM, score/compare versions, auto-evolve improvements via Ralph loops, merge git updates/rollbacks, scan portfolios, and generate reports—all stored under .skill-compass.

npx claudepluginhub evol-ai/skillcompass

Component Overview

Commands

Hooks

Component Details

Commands (14)

/eval-audit — Batch Skill Evaluation

/eval-audit

> **Locale**: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.

/eval-compare — Version Comparison

/eval-compare

/eval-evolve — Optional Plugin-Assisted Multi-Round Evolution via Ralph Loop

/eval-evolve

/eval-improve — Evaluate + Directed Improvement

/eval-improve

- **Recommended model: Claude Opus 4.6** (`claude-opus-4-6`). Directed improvement requires understanding complex rubric feedback and generating precise, targeted edits. Weaker models may produce unfocused rewrites that fail to address the weakest dimension or introduce regressions in other dimensions.

/eval-merge — Three-Way Version Merge

/eval-merge

/eval-rollback — Version Rollback

/eval-rollback

/eval-security — Standalone Security Scan

/eval-security

/eval-skill — Six-Dimension Evaluation

/eval-skill

**🚀 Enhanced with Local Validators**: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. Complex reasoning tasks (D4, D5, D6) continue to use LLM evaluation with local pre-analysis.

Post-Install Onboarding

/post-install-onboarding

Triggered by the SessionStart hook (`hooks/scripts/session-tracker.js`), which compares the current SkillCompass version against the last recorded version. On first install, reinstall, or version change the hook injects a context message instructing Claude to load this file and follow it on the user's first interaction.

/setup - Skill Inventory & Health Check

/setup

This command gives users a quick local inventory of installed skills and surfaces only high-signal issues. It supports two modes:

/skillcompass — Natural Language Dispatcher

/skill-compass

This command accepts free-form natural language and routes to the appropriate SkillCompass command. Also accessible as `/skill-compass`.

/skill-inbox — Skill Suggestion Inbox

/skill-inbox

Unified entry point for managing skill suggestions and browsing all installed skills. Provides two views: suggestions (default) and all skills.

/skill-report — Skill Portfolio Report

/skill-report

Generate a comprehensive report of all installed skills: quick health scan, context budget, portfolio overview, and quality summary.

/skill-update — Check and Update Skills

/skill-update

Hooks (1)

Review workflow modifications before installing

Event Hooks

File writes

5 hooks across 3 events

README

SkillCompass

Evaluate quality. Find the weakest link. Fix it. Prove it worked. Repeat.

GitHub · SKILL.md · Schemas · Changelog


What it is	A local-first skill quality evaluator and management tool for Claude Code / OpenClaw. Six-dimension scoring, usage-driven suggestions, guided improvement, version tracking.
Pain it solves	Turns "tweak and hope" into diagnose → targeted fix → verified improvement. Turns "install and forget" into ongoing visibility over what's working, what's stale, and what's risky.
Use in 30 seconds	`/skillcompass` — see your skill health at a glance. `/eval-skill {path}` — instant quality report showing exactly what's weakest and what to improve next.

Evaluate → find weakest link → fix it → prove it worked → next weakness → repeat. Meanwhile, Skill Inbox watches your usage and tells you what needs attention.

Who This Is For

For

Anyone maintaining agent skills and wanting measurable quality
Developers who want directed improvement — not guesswork, but knowing exactly which dimension to fix next
Teams needing a quality gate — any tool that edits a skill gets auto-evaluated
Users who install many skills and need visibility over what's actually used, what's stale, and what's risky

Not For

General code review or runtime debugging
Creating new skills from scratch (use skill-creator)
Evaluating non-skill files

Quick Start

Prerequisites: Claude Opus 4.6 / 4.7 (complex reasoning + consistent scoring) · Node.js v18+ (local validators)

One-Command Install (recommended)

npx skills add Evol-ai/SkillCompass

Supports 45+ agents including Claude Code, Codex, Cursor, Cline, Gemini CLI, GitHub Copilot, and more. The CLI auto-detects installed agents and sets up the skill in the right location.

Claude Code (manual)

git clone https://github.com/Evol-ai/SkillCompass.git
cd SkillCompass && npm install

# User-level (all projects)
rsync -a --exclude='.git'  . ~/.claude/skills/skill-compass/

# Or project-level (current project only)
rsync -a --exclude='.git'  . .claude/skills/skill-compass/

First run: SkillCompass auto-triggers a brief onboarding — scans your installed skills (~5 seconds), offers statusLine setup, then hands control back. Claude Code will request permission for node commands; select "Allow always" to avoid repeated prompts.

OpenClaw

git clone https://github.com/Evol-ai/SkillCompass.git
cd SkillCompass && npm install
# Follow OpenClaw skill installation docs for your setup
rsync -a --exclude='.git'  . <your-openclaw-skills-path>/skill-compass/

If your OpenClaw skills live outside the default scan roots, add them to skills.load.extraDirs in ~/.openclaw/openclaw.json:

{
  "skills": {
    "load": {
      "extraDirs": ["<your-openclaw-skills-path>"]
    }
  }
}

Usage

/skillcompass is the single entry point. Use it with a slash command or just talk naturally — both work:

/skillcompass                              → see what needs attention
/skillcompass evaluate my-skill            → six-dimension quality report
"improve the nano-banana skill"            → fix weakest dimension, verify, next
"what skills haven't I used recently?"     → usage-based insights
"security scan this skill"                 → D3 security deep-dive

What It Does

SkillCompass — Skill Quality Report

The score isn't the point — the direction is. You instantly see which dimension is the bottleneck and what to do about it.

Each /eval-improve round follows a closed loop: fix the weakest → re-evaluate → verify improvement → next weakest. No fix is saved unless the re-evaluation confirms it actually helped.

Six-Dimension Evaluation Model

View full README on GitHub

Similar Plugins

singularity-claude

Self-evolving skill engine for Claude Code. Creates, scores, repairs, and hardens skills autonomously through recursive improvement cycles.

Stats

Version1.0.0

Stars136

Forks8

MaintenanceExcellent

LicenseMIT

AddedApr 2, 2026

Actions

View on GitHub View README Plugin Marketplace JSON Homepage

Safety Signals

Caution

Modifies files

Hook triggers on file write and edit operations

Runs pre-commands

Contains inline bash commands via ! syntax

Help us improve

Share bugs, ideas, or general feedback.

Back to Plugins

SkillCompass

Evaluate quality. Find the weakest link. Fix it. Prove it worked. Repeat.

GitHub · SKILL.md · Schemas · Changelog


What it is	A local-first skill quality evaluator and management tool for Claude Code / OpenClaw. Six-dimension scoring, usage-driven suggestions, guided improvement, version tracking.
Pain it solves	Turns "tweak and hope" into diagnose → targeted fix → verified improvement. Turns "install and forget" into ongoing visibility over what's working, what's stale, and what's risky.
Use in 30 seconds	`/skillcompass` — see your skill health at a glance. `/eval-skill {path}` — instant quality report showing exactly what's weakest and what to improve next.

Evaluate → find weakest link → fix it → prove it worked → next weakness → repeat. Meanwhile, Skill Inbox watches your usage and tells you what needs attention.

Who This Is For

For

Anyone maintaining agent skills and wanting measurable quality
Developers who want directed improvement — not guesswork, but knowing exactly which dimension to fix next
Teams needing a quality gate — any tool that edits a skill gets auto-evaluated
Users who install many skills and need visibility over what's actually used, what's stale, and what's risky

Not For

General code review or runtime debugging
Creating new skills from scratch (use skill-creator)
Evaluating non-skill files

Quick Start

Prerequisites: Claude Opus 4.6 / 4.7 (complex reasoning + consistent scoring) · Node.js v18+ (local validators)

One-Command Install (recommended)

npx skills add Evol-ai/SkillCompass

Supports 45+ agents including Claude Code, Codex, Cursor, Cline, Gemini CLI, GitHub Copilot, and more. The CLI auto-detects installed agents and sets up the skill in the right location.

Claude Code (manual)

git clone https://github.com/Evol-ai/SkillCompass.git
cd SkillCompass && npm install

# User-level (all projects)
rsync -a --exclude='.git'  . ~/.claude/skills/skill-compass/

# Or project-level (current project only)
rsync -a --exclude='.git'  . .claude/skills/skill-compass/

First run: SkillCompass auto-triggers a brief onboarding — scans your installed skills (~5 seconds), offers statusLine setup, then hands control back. Claude Code will request permission for node commands; select "Allow always" to avoid repeated prompts.

OpenClaw

git clone https://github.com/Evol-ai/SkillCompass.git
cd SkillCompass && npm install
# Follow OpenClaw skill installation docs for your setup
rsync -a --exclude='.git'  . <your-openclaw-skills-path>/skill-compass/

If your OpenClaw skills live outside the default scan roots, add them to skills.load.extraDirs in ~/.openclaw/openclaw.json:

{
  "skills": {
    "load": {
      "extraDirs": ["<your-openclaw-skills-path>"]
    }
  }
}

Usage

/skillcompass is the single entry point. Use it with a slash command or just talk naturally — both work:

/skillcompass                              → see what needs attention
/skillcompass evaluate my-skill            → six-dimension quality report
"improve the nano-banana skill"            → fix weakest dimension, verify, next
"what skills haven't I used recently?"     → usage-based insights
"security scan this skill"                 → D3 security deep-dive

What It Does

SkillCompass — Skill Quality Report

The score isn't the point — the direction is. You instantly see which dimension is the bottleneck and what to do about it.

Each /eval-improve round follows a closed loop: fix the weakest → re-evaluate → verify improvement → next weakest. No fix is saved unless the re-evaluation confirms it actually helped.

skill-compass

Component Overview

Component Details

Commands (14)

Hooks (1)

README

SkillCompass

Who This Is For

Quick Start

One-Command Install (recommended)

Claude Code (manual)

OpenClaw

Usage

What It Does

Six-Dimension Evaluation Model

Similar Plugins

singularity-claude

Help us improve

Help us improve

skill-compass

Component Overview

Component Details

Commands (14)

Hooks (1)

README

SkillCompass

Who This Is For

Quick Start

One-Command Install (recommended)

Claude Code (manual)

OpenClaw

Usage

What It Does

Six-Dimension Evaluation Model

Similar Plugins

singularity-claude

Help us improve

skill-forge

skill-judge

skill-optimizer

skill-development

skill-creator

Help us improve