Is the Skill Scorer skill free?

Yes. The skill itself is free from AndrewNgGirl/SkillLens. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Skill Scorer SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.

How do I install Skill Scorer?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Skill Scorer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Skill Scorer

Rubric-based 100-point quality scorer for Claude/Cursor/OpenClaw SKILL.md files, with anti-fabrication rules.

by AndrewNgGirl · AndrewNgGirl/SkillLens

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 28ea270

The backing rubric.yaml is a real, deep 100-point spec (5 pillars weighted 25/15/15/20/25, each with named sub-dimensions), and the skill's own contract bans claiming 'Deep Review 完成' or any score not printed verbatim by the official CLI — meta-honesty baked into the tool that reviews other skills.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 5/5

What Skill Scorer does

Runs a SKILL.md, skill folder, or zip through an official 5-pillar, 100-point rubric (skill value, market competitiveness, runtime cost, reliability, writeup, plus a bonus pillar) via a local Python CLI, returning pillar/dimension scores, cited evidence, and concrete fixes in Chinese and English. Triggers on requests to review, rate, audit, grade, lint, or improve an Agent Skill file or folder, and its own contract explicitly forbids claiming a score (e.g. '100/100') that didn't come from the official CLI output.

How to install Skill Scorer

git clone https://github.com/AndrewNgGirl/SkillLens
cd SkillLens
mkdir -p ~/.claude/skills
cp -r skills/skill-scorer ~/.claude/skills/skill-scorer

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Skill Scorer

/skill-scorer Rubric-based 100-point quality scorer for Claude/Cursor/OpenClaw SKILL.md files, with anti-fabrication rules.

It also activates on plain-language prompts like these:

Can you score this SKILL.md file against a quality rubric?
Audit my agent skill folder and tell me what needs fixing.
Give this Claude skill a rated review with concrete feedback.

Frequently asked questions

Is the Skill Scorer skill free?: Yes. The skill itself is free from AndrewNgGirl/SkillLens. SkillProof publishes the install command and an independent test verdict at no cost.
Does Skill Scorer work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. The backing rubric.yaml is a real, deep 100-point spec (5 pillars weighted 25/15/15/20/25, each with named sub-dimensions), and the skill's own contract bans claiming 'Deep Review 完成' or any score not printed verbatim by the official CLI — meta-honesty baked into the tool that reviews other skills.
What is the Skill Scorer SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Skill Scorer?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Skill Scorer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.