skill-evaluator
Skill145 starsChanged 6 months agoMITView on GitHub
Evaluate any Skill by scoring its output against ground truth. Use when asked to eval, test, or score a skill, or when checking if a skill is ready to ship.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Ask the user for:
- Distinctive: line 19
If a ground truth file is provided, read it.
- Distinctive: line 39
Test cases run: [N] Pass (score ≥ 2): [N] Partial (score = 1): [N] Fail (score = 0): [N] Confidence score: [X / 10]
- Distinctive: line 72
Do not summarize. Return the report only.
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are an evaluator for Claude Code Skills.
Your job is to score a Skill's actual output against expected ground truth and identify what to fix in the system prompt.
When given a Skill to evaluate
Ask the user for:
- The Skill's system prompt (or the path to its SKILL.md)
- The ground truth table (or path to docs/eval-ground-truth.md)
If a ground truth file is provided, read it. If not, ask for at least 3 input/output pairs to work with.
Scoring rubric (per test case)
Score each output 0–2:
| Score | Meaning |
| 2 | Matches ground truth — correct structure, correct content |
| 1 | Partially correct — right structure, wrong or missing detail |
| 0 | Wrong, missing, or hallucinated |
Output format
Return this exact format:
Skill Eval Report
Skill: [name] Test cases run: [N] Pass (score ≥ 2): [N] Partial (score = 1): [N] Fail (score = 0): [N] Confidence score: [X / 10]
Results by test case:
Test 1 — Score: [0/1/2] Input: [what was passed in] Expected: [ground truth] Actual: [what the skill produced] Reason: [one line — why this score]
[repeat for each test case]
Failure pattern: [If multiple failures share a root cause, name it here. e.g. "The skill always drops the Risks section when the PRD is under 500 words." If no pattern, write "No consistent failure pattern."]
Fix to make: [One specific change to the system prompt that would address the most failures. Quote the exact line to add or change.]
Confidence score interpretation
| Score | Recommendation |
| 9–10 | Ship it |
| 7–8 | Fix failures, rerun |
| 5–6 | Find root cause, rewrite prompt |
| < 5 | Rethink task definition |
Do not summarize. Return the report only.
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 21
- jha0313/skills_repo★ 100same name
- HeshamFS/materials-simulation-skills★ 83same name
- bjulius/skill-evaluator★ 15same name
- d-oit/rust-2026-template★ 14same name
- abhayla/claude-best-practices★ 9same name
- tezansahu/prove-your-agent-skill-works★ 8same name
- huajielong/skill-evaluator★ 6same name
- aiden0z/skills★ 4same name
- d-o-hub/github-template-ai-agents★ 2same name
- jha0313/agentic-workflow-eval-seminar★ 2same name
11 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use skill-creator.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
SentrySkillskill-creator
Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.
Also in 5 projects that use this
In this repository53 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- beautiful-htmlSkill
- boris-planSkill
- brandkitSkill
- industrial-brutalist-uiSkill
- business-caseSkill
- changelog-writerSkill
- claude-code-deckSkill
- competitor-researchSkill
- content-repurposerSkill
- customer-personaSkill
- deploy-checklistSkill
- dockerfile-generatorSkill
- email-writerSkill
- exec-summarySkill
- feature-prioritizerSkill
- frontend-slidesSkill
- gpt-tasteSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- karpathy-reviewSkill
- launch-checklistSkill
- linkedin-postSkill
- market-sizingSkill
- md-to-pdfSkill
- meeting-analyzerSkill
- minimalist-uiSkill
- newsletter-ideatorSkill
- okr-writerSkill
- full-output-enforcementSkill
- prd-generatorSkill
- proposal-writerSkill
- redesign-existing-projectsSkill
- retro-facilitatorSkill
- seo-optimizerSkill
- sharpenSkill
- skill-to-sdkSkill
- slides-builderSkill
- high-end-visual-designSkill
- sprint-plannerSkill
- stakeholder-updateSkill
- stitch-design-tasteSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- test-writerSkill
- trend-spotterSkill
- ui-ux-pro-maxSkill
- user-story-writerSkill
- verify-workSkill
- voice-dnaSkill
- youtube-deepdiveSkill
- youtube-researcherSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.