skill-generator
Skill1 starsChanged 11 months agoMITView on GitHub
Meta-skill for creating, refining, and managing Agent Skills. Use when needing to create new skills, improve existing skills, analyze skill performance, or teach the agent new capabilities. Enables self-improvement and knowledge capture.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- k1lgor/virtual-companytheir own version, first seen Nov 1, 2026
- osren/interview-flashcardtheir own version, first seen Oct 24, 2026
- axetroy/skillstheir own version, first seen Oct 13, 2026
- catlog22/Maestro-Flowtheir own version, first seen Oct 9, 2026
- cigery-useio/useio-skillstheir own version, first seen Sep 23, 2026
- catlog22/maestro-flowtheir own version, first seen Sep 4, 2026
Used with
Projects with it also use skill-iter-tune, skill-simplify and 9 more.
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.
zhao-wuyanSkillskill-iter-tune
Iterative skill tuning via execute-evaluate-improve feedback loop. Uses ccw cli Claude to execute skill, Gemini to evaluate quality, and Agent to apply improvements. Iterates until quality threshold or max iterations. Triggers on "skill iter tune", "iterative skill tuning", "tune skill".
Also in 3 projects that use this
zhao-wuyanSkillskill-simplify
SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost. Triggers on "simplify skill", "optimize skill", "skill-simplify".
Also in 3 projects that use this
- +9 more from zhao-wuyan
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- catlog22/maestro-flow★ 571same name
- catlog22/Maestro-Flow★ 571same name
- cigery-useio/useio-skills★ 103same name
- zhao-wuyan/ccw-command-explorer★ 45same name
- gqy20/Skills_demo★ 4same name
- k1lgor/virtual-company★ 4same name
- u9401066/template-is-all-you-need★ 3same name
- osren/interview-flashcard★ 2same name
- axetroy/skills★ 1same name
- fabianmagrini/skills★ 1same name
1 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.
In this repository4 other files it gives its agents.
- AGENTS.MDAGENTS.md
- advanced-debuggingSkill
- oneplanSkill
- tech-debt-reducerSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Create a skill when you observe:
- Distinctive: line 103
When a debug session reveals new patterns, create a skill:
- Distinctive: line 120
When a skill proves insufficient:
- Distinctive: line 123
Add to appropriate section (or new reference file)
- Distinctive: line 124
Update version in metadata
- Distinctive: line 128
When a skill becomes obsolete:
- Very specific: line 129
Add deprecation notice at top of SKILL.md
- Distinctive: line 131
Remove after migration period
- Very specific: line 135
After discovering a recurring Next.js hydration issue pattern:
- Distinctive: line 182
Use specific keywords users might mention
“Common” is measured: kept by at least 6 in 10 of the 7 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
🧬 Skill Generator - Self-Evolving Capabilities
This skill enables the agent to create, refine, and manage new skills autonomously, capturing learned patterns and domain expertise into reusable capabilities.
When to Create a New Skill
Create a skill when you observe:
- Repeated context provided across multiple conversations
- Domain-specific knowledge that Claude doesn't have by default
- Multi-step workflows that benefit from consistent execution
- Project-specific conventions that should be encoded
- Debugging patterns discovered during problem resolution
Skill Creation Workflow
Step 1: Identify the Need
Ask yourself:
- Is this knowledge reusable across sessions?
- Would encoding this save significant tokens in future conversations?
- Does this represent procedural knowledge Claude lacks?
Step 2: Design the Skill Structure
skill-name/
├── SKILL.md # Required: Main instructions (<500 lines)
├── scripts/ # Optional: Executable code
│ └── helper.ts
├── references/ # Optional: Detailed documentation
│ └── REFERENCE.md
└── assets/ # Optional: Templates, data
└── template.mdStep 3: Write the SKILL.md
Template:
---
name: [lowercase-hyphen-name]
description: [What it does AND when to use it. Max 1024 chars. Be specific with keywords.]
metadata:
author: [author]
version: "1.0"
---
# [Skill Title]
## Quick Reference
[Table or list of most common operations]
## Core Functionality
[Main instructions, organized by task]
## Examples
[Concrete input/output examples]
## Guidelines
[Rules and constraints]Step 4: Validate the Skill
Checklist before saving:
- Name is lowercase with hyphens only
- Description includes WHAT and WHEN
- SKILL.md body < 500 lines
- No time-sensitive information
- Consistent terminology
- Clear examples provided
- File references are one level deep
Skill Categories for This Project
Debug Skills (.github/skills/debug-*)
For capturing debugging patterns:
debug-nextjs- Next.js specific debuggingdebug-prisma- Database debuggingdebug-react-query- State management debugging
Feature Skills (.github/skills/feature-*)
For feature development patterns:
feature-api-routes- API route conventionsfeature-components- Component patterns
Process Skills (.github/skills/process-*)
For workflow automation:
process-deploy- Deployment proceduresprocess-migration- Database migrations
Auto-Generation from Debug Sessions
When a debug session reveals new patterns, create a skill:
## Pattern Discovered: [Name]
**Problem Type**: [category]
**Root Cause**: [description]
**Solution Pattern**: [reusable fix]
**Prevention Strategy**: [how to avoid]
→ Suggest: Create skill `debug-[category]` capturing this patternSkill Evolution
Improving Existing Skills
When a skill proves insufficient:
- Identify the gap
- Propose enhancement
- Add to appropriate section (or new reference file)
- Update version in metadata
Deprecating Skills
When a skill becomes obsolete:
- Add deprecation notice at top of SKILL.md
- Point to replacement skill
- Remove after migration period
Example: Creating a Debug Skill
After discovering a recurring Next.js hydration issue pattern:
---
name: debug-hydration
description: Diagnose and fix React hydration mismatches in Next.js. Use when seeing hydration errors, content flickering, or server/client mismatches.
metadata:
author: coachone
version: "1.0"
---
# Hydration Debugging
## Quick Diagnosis
1. Check browser console for specific hydration error
2. Identify the component mentioned in error
3. Compare server-rendered HTML with client-rendered output
## Common Causes
| Symptom | Cause | Fix |
|---------|-------|-----|
| Date/time mismatch | Server/client timezone | Use `suppressHydrationWarning` or standardize timezone |
| Random IDs | useId() not used | Replace Math.random() with React.useId() |
| Browser APIs | window/document access | Check typeof window !== 'undefined' |
| Extension interference | Browser extensions | Test in incognito mode |
## Fix Patterns
### Pattern 1: Deferred Client Rendering
\`\`\`tsx
const [mounted, setMounted] = useState(false);
useEffect(() => setMounted(true), []);
if (!mounted) return <Skeleton />;
return <DynamicContent />;
\`\`\`
### Pattern 2: Suppress Warning (use sparingly)
\`\`\`tsx
<time suppressHydrationWarning>{new Date().toLocaleString()}</time>
\`\`\`Skill Discovery Tips
Skills are activated when their description matches user intent. Write descriptions that:
- Use specific keywords users might mention
- Cover synonyms and alternative phrasings
- Describe both the capability AND the trigger context
Good: "Debug and fix React hydration errors, content mismatches between server and client rendering, SSR issues" Bad: "Helps with React problems"
File Locations
Skills for this project should be created in:
.github/skills/[skill-name]/
├── SKILL.md
└── [optional resources]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.

