How do I install the Skill Compass skill?

Run npx skillmds@latest add bertbertov/skill-compass in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skill Compass safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill Compass?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill Compass free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Skill Compass?

bertbertov (@bertbertov) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill Compass by bertbertov — Agent Skill

Name: Skill Compass
Author: bertbertov

Skill Compass

Audits all installed Claude Code skills for quality, redundancy, and dead weight. Use when the user asks to audit skills, find dead skills, evaluate skill coverage, compare skills, or identify the weakest skill in their library. Runs against ~/.claude/skills/ and surfaces which skills are stale, overlapping, or under-performing.

bertbertov 3c6cc28 2.2 KB Updated Sep 17, 2026

File contents

skill-compass — audit your installed skills

A wrapper around the SkillCompass Node tool installed at ~/.claude/skill-compass/. Use this skill when the user wants to:

Find which skills they don't actually use
Spot redundant/overlapping skills they should consolidate
Evaluate skill quality with concrete metrics
Compare two skills against the same task
Trace why a skill is misfiring

Commands

The tool exposes its slash-commands at ~/.claude/skill-compass/commands/:

/eval-audit     # full audit of installed skills, scores each
/eval-compare   # head-to-head compare two skills on the same input
/eval-evolve    # iteratively improve a skill based on its own audit
/eval-improve   # one-shot improve a skill
/eval-merge     # merge two overlapping skills into one

Invocation

From a Claude Code session:

node ~/.claude/skill-compass/oc/run.js audit ~/.claude/skills/<skill-name>
node ~/.claude/skill-compass/oc/run.js audit-all ~/.claude/skills/

Or read the SkillCompass AGENTS.md and commands/eval-audit.md for the full agent-driven flow:

cat ~/.claude/skill-compass/AGENTS.md
cat ~/.claude/skill-compass/commands/eval-audit.md

When to invoke

"audit my skills" / "which of my skills are dead weight"
"are my skills overlapping"
"score this skill"
"improve this skill" / "fix this skill"
After installing 5+ new skills (catch regressions early)

Why it matters

the user has 200+ skills installed. Without this tool, identifying dead weight is manual eyeballing. SkillCompass produces ranked output with pass/fail signals per skill so the audit produces a punch list, not a wall of text.

Source

Repo: https://github.com/Evol-ai/SkillCompass
Local install: ~/.claude/skill-compass/
License: MIT

---name: skill-compassdescription: Audits all installed Claude Code skills for quality, redundancy, and dead weight. Use when the user asks to audit skills, find dead skills, evaluate skill coverage, compare skills, or identify the weakest skill in their library. Runs against ~/.claude/skills/ and surfaces which skills are stale, overlapping, or under-performing.license: MIT---# skill-compass — audit your installed skillsA wrapper around the [SkillCompass](https://github.com/Evol-ai/SkillCompass) Node tool installed at `~/.claude/skill-compass/`. Use this skill when the user wants to:- Find which skills they don't actually use- Spot redundant/overlapping skills they should consolidate- Evaluate skill quality with concrete metrics- Compare two skills against the same task- Trace why a skill is misfiring## CommandsThe tool exposes its slash-commands at `~/.claude/skill-compass/commands/`:```/eval-audit # full audit of installed skills, scores each/eval-compare # head-to-head compare two skills on the same input/eval-evolve # iteratively improve a skill based on its own audit/eval-improve # one-shot improve a skill/eval-merge # merge two overlapping skills into one```## InvocationFrom a Claude Code session:```bashnode ~/.claude/skill-compass/oc/run.js audit ~/.claude/skills/<skill-name>node ~/.claude/skill-compass/oc/run.js audit-all ~/.claude/skills/```Or read the SkillCompass `AGENTS.md` and `commands/eval-audit.md` for the full agent-driven flow:```bashcat ~/.claude/skill-compass/AGENTS.mdcat ~/.claude/skill-compass/commands/eval-audit.md```## When to invoke- "audit my skills" / "which of my skills are dead weight"- "are my skills overlapping"- "score this skill"- "improve this skill" / "fix this skill"- After installing 5+ new skills (catch regressions early)## Why it mattersthe user has 200+ skills installed. Without this tool, identifying dead weight is manual eyeballing. SkillCompass produces ranked output with pass/fail signals per skill so the audit produces a punch list, not a wall of text.## Source- Repo: https://github.com/Evol-ai/SkillCompass- Local install: `~/.claude/skill-compass/`- License: MIT

Frequently asked questions