modes
Skill4 starsChanged 7 months agoMITView on GitHub
Review a SKILL.md design instead of code. Meta-review. Be constructive — skill authors are building something new. Roast the gaps, but respect the ambition. Make the skill better, not the builder worse. Note: Skill Roast does NOT offer Auto-Fix — skill design changes are judgment calls, not mechanical edits.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- lombarddaniel14-coder/claude-skillstheir own version, first seen Aug 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- lombarddaniel14-coder/claude-skills★ 0same name
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.
In this repositoryOne other file it gives its agents.
- blunt-cakeSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 11
Deliver the verdict: Follow the Skill Output Format below.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill Roast Mode
Review a SKILL.md design instead of code. Meta-review. Be constructive — skill authors are building something new. Roast the gaps, but respect the ambition. Make the skill better, not the builder worse.
Skill Review Steps
- Read the entire skill definition. Understand what it's trying to do and who it's for.
- Evaluate each category. Score each of the 8 categories below.
- Write the roast. Same energy as code roasts, but constructive. The goal is to make the skill better.
- Score it. Rate on the Skill Roast Scale.
- Deliver the verdict. Follow the Skill Output Format below.
Skill Review Categories
- 🎯 TRIGGER — Is the trigger clear? Will it fire correctly? Will it false-positive on unrelated prompts? Is there priority logic if multiple triggers could match?
- 📋 INSTRUCTIONS — Are the instructions specific enough to produce consistent output? Too vague? Too rigid? Would two different models produce the same structure?
- 🧪 EDGE CASES — What happens with empty input? Huge input? Ambiguous requests? Multilingual code? Does the skill handle gracefully or crash and burn?
- 📐 OUTPUT FORMAT — Is the output format well-defined with a template? Will it produce parseable, consistent results? Could you regex the score out of the output?
- 🔄 PROCESS — Is the workflow logical? Missing steps? Redundant steps? Steps in wrong order? Does it tell the model WHEN to do each thing?
- ⚖️ RULES — Are the rules internally consistent? Contradictory? Missing obvious guardrails? Prioritized or just a flat list?
- ✨ CREATIVITY — Is this skill actually useful? Does it do something a bare prompt can't? What's the unique value? Would you install this?
- 📊 EVAL-READINESS — Could you write meaningful pass/fail assertions for this skill's output? If not, the spec is too vague to test.
Skill Roast Scale
| Score | Rating |
| 10 | 🏆 Production-grade — ship it, I'd install this |
| 7-9 | 📦 Almost there — real value, needs polish |
| 4-6 | 📝 Draft — the idea is good, the spec needs work |
| 1-3 | 🗒️ Napkin sketch — you wrote a wish, not a skill |
Skill Output Format
# 🔥 ROAST MY SKILL — [skill name]
## The Verdict
[One-paragraph summary roast of the skill design. Be funny but constructive.]
**Score: [X]/10 — [Rating Emoji] [Rating Name]**
---
## Findings
### [Category Emoji] [CATEGORY] — [Short title]
> [The roast line — one sentence, punchy, funny]
**What's wrong:** [Actual explanation of the design gap]
**Severity:** [CRITICAL/HIGH/MEDIUM/LOW/NITPICK]
**Suggestion:** [How to fix the skill definition — specific wording or structural change]
[Repeat for each finding]
---
## The Scoreboard
| Category | Issues | Worst Severity |
|----------|:------:|---------------|
| 🎯 Trigger | X | ... |
| 📋 Instructions | X | ... |
| 🧪 Edge Cases | X | ... |
| 📐 Output Format | X | ... |
| 🔄 Process | X | ... |
| ⚖️ Rules | X | ... |
| ✨ Creativity | X | ... |
| 📊 Eval-Readiness | X | ... |
## Final Words
[Closing roast. Acknowledge the ambition, then push them to make it better.]Note: Skill Roast does NOT offer Auto-Fix — skill design changes are judgment calls, not mechanical edits.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.