Evol-ai/SkillCompass

Evaluate agent skill quality. Find the weakest link. Fix it. Prove it worked.

216Stars on the repository
20Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

eval-audit

01

Evol-ai/SkillCompass

Command

Use the Glob tool to find all /SKILL.md files recursively under the specified directory. Also check /.claude/skills/ if scanning project-level.

216 4mo ago A 0 tokens original MIT

eval-compare

02

Evol-ai/SkillCompass

Command

Command "eval-compare" from Evol-ai/SkillCompass, covering /eval-compare — version comparison, arguments, steps, step 1: resolve versions and step 2: check cached results.

216 4mo ago A 0 tokens original MIT

eval-evolve

03

Evol-ai/SkillCompass

Command

Command "eval-evolve" from Evol-ai/SkillCompass, covering arguments, prerequisites, what this command does, step 1: validate and step 2: read current state.

216 4mo ago A 0 tokens original MIT

eval-improve

04

Evol-ai/SkillCompass

Command

If --internal is passed, skip all interactive prompts — return results silently. This flag is set when eval-improve is called by other commands (e.g., from setup or skill-inbox action queue).

216 4mo ago A 0 tokens original MIT

eval-merge

05

Evol-ai/SkillCompass

Command

Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.

216 4mo ago A 0 tokens original MIT

eval-rollback

06

Evol-ai/SkillCompass

Command

Use the Read tool to load .skill-compass/{skill-name}/manifest.json.

216 4mo ago A 0 tokens original MIT

eval-security

07

Evol-ai/SkillCompass

Command

Parse arguments. Use the Read tool to load the target SKILL.md file.

216 4mo ago A 0 tokens original MIT

eval-skill

08

Evol-ai/SkillCompass

Command

🚀 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.

216 4mo ago A 0 tokens original MIT

Evol-ai/SkillCompass

Command

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.

216 4mo ago B 0 tokens original MIT

setup

10

Evol-ai/SkillCompass

Command

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

216 4mo ago B 0 tokens original MIT

skill-compass

11

Evol-ai/SkillCompass

Command

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

216 4mo ago A 0 tokens original MIT

skill-inbox

12

Evol-ai/SkillCompass

Command

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

216 4mo ago A 0 tokens original MIT

skill-report

13

Evol-ai/SkillCompass

Command

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

216 4mo ago A 0 tokens original MIT

skill-update

14

Evol-ai/SkillCompass

Command

Check installed skills for remote updates and guide the user through updating and evaluating them.

216 4mo ago A 0 tokens original MIT