skill-builder
Skill8 starsChanged 3 months agoMITView on GitHub
Create production-ready Claude Code skills with guided workflow, templates, and best practices. Generate SKILL.md files with optimized YAML frontmatter, proper structure, and discovery-optimized descriptions. Use when creating new skills, scaffolding skill directories, building skills from scratch, or need expert guidance on skill design. Triggers on "create skill", "new skill", "build skill", "scaffold skill", "make a skill".
74 other projects use a version of this.
Adopted by
Most recently taken up by
- BloodSweatxED/Claude-skillstheir own version, first seen Nov 16, 2026
- arctan303/creator.skilltheir own version, first seen Nov 12, 2026
- Kikobazz123/lordgen-skill-buildertheir own version, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- shetengteng/skillix-hubtheir own version, first seen Nov 8, 2026
- davidgfolch/AI-job-searchtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use contract-test, literature-research and 10 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.
squall-chuaSkillcontract-test
Test a running API against its own contract — OpenAPI, GraphQL, protobuf, or AsyncAPI — from the outside, and report every drift between what the contract promises and what the API does.
Also in 3 projects that use this
nickjwellsSkillliterature-research
Search academic literature and perform deep research reviews. Use when user asks to search PubMed, find academic papers, or do literature reviews.
Also in 3 projects that use this
nopandererSkillcommit-and-push
Automatically analyze git changes, generate Conventional Commits compliant commit messages, commit changes, and push to remote in a single automated workflow. Use when the user invokes /commit-and-push or explicitly requests to automatically commit and push changes following Conventional Commits format (feat:, fix:, docs:, etc.). This skill provides a fully automated git workflow without manual intervention.
Also in 3 projects that use this
MicrosoftSkillskill-reviewer
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions. WHEN: \"review skill\", \"review skill PR\", \"review skill changes\", \"check skill quality\", \"skill PR feedback\".
Also in 3 projects that use this
SkillPilotCHSkilllevel-up
Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.
Also in 3 projects that use this
MicrosoftSkillexcalidraw-diagram
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
Also in 4 projects that use this
Other versions74 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 74
- yusufkaraaslan/Skill_Seekers★ 15ksame name
- block/berd★ 1.1ksame name
- boshu2/agentops★ 454same name
- metaskills/skill-builder★ 112same name
- AsiaOstrich/universal-dev-standards★ 84same name
- nateherkai/a-bunch-of-skills★ 41same name
- clasen/Skills★ 40same name
- sanqi-cd/Sanqi-Skills★ 28same name
- arctan303/creator.skill★ 19same name
- aiagentwithdhruv/skills★ 16same name
64 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- cotSkill
- dependency-healthSkill
- hibernateSkill
- repo-docsSkill
- skill-validatorSkill
- task-cleanupSkill
- template-upgradeSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 65 edited versions we read keep these.
10
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 53
When invoked, ask these questions:
- Distinctive: line 72
Add to description for discovery
- Distinctive: line 149
If this throws an error, your frontmatter is broken and the skill won't load.
- Distinctive: line 381
Write specific, actionable descriptions
- Distinctive: line 383
Use clear, imperative instructions
- Distinctive: line 386
Test that Claude discovers your skill
- Distinctive: line 389
Write vague descriptions like "helps with files"
- Distinctive: line 391
Put everything in one massive skill
- Distinctive: line 399
After gathering requirements, provide:
- Distinctive: line 439
User: Create a skill to analyze Python code quality
“Common” is measured: kept by at least 6 in 10 of the 65 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 Builder
Expert-guided skill creation system combining template generation with best practices for building discoverable, effective Claude Code skills.
Quick Start
# Interactive skill creation
/skill-builder
# Create specific skill
/skill-builder api-client-generator
# Create with type hint
/skill-builder --type analysis security-scannerCore Principles
1. Discovery is Everything
Skills are model-invoked - Claude autonomously decides when to use them based on:
- Your request context
- The skill's
descriptionfield - Keyword matching and semantic understanding
The description MUST include BOTH:
- What the skill does (capabilities)
- When to use it (triggers, file types, keywords)
2. Description Formula
[Action verbs] + [Specific capabilities] + [File types/formats] + [Use case triggers]Example:
description: Analyze code complexity, detect anti-patterns, suggest refactoring opportunities. Works with .js, .ts, .py, .java files. Use when reviewing code quality, performing technical debt analysis, or need complexity metrics.Interactive Workflow
When invoked, ask these questions:
Question 1: Purpose
"What should this skill do?" (1-2 sentences)
- Listen for domain clues (analyze, generate, transform, validate, orchestrate)
Question 2: Domain Type
"What type of skill is this?"
| Type | Description | Example |
| Analysis | Examine code/data/systems | Code quality, security audit |
| Generation | Create files/code/content | API client, test suite |
| Transformation | Convert between formats | JSON→YAML, JS→TS |
| Validation | Check correctness/compliance | Schema validator |
| Orchestration | Coordinate multiple operations | Deploy pipeline |
Question 3: File Types
"What file types or formats will it work with?"
- Add to description for discovery
- Include extensions: .js, .ts, .py, .md, .json, .yaml
Question 4: Use Cases
"When would someone use this skill? What problems does it solve?"
- Extract trigger keywords
- Include problem scenarios
Question 5: Supporting Files
"Do you need supporting files?"
- Templates, examples, scripts, reference docs
Skill Templates
Minimal Skill Structure
skill-name/
└── SKILL.mdFull Skill Structure
skill-name/
├── SKILL.md # Required: Main skill definition
├── reference.md # Optional: Detailed documentation
├── examples/ # Optional: Example outputs
│ ├── example-1.md
│ └── example-2.md
├── templates/ # Optional: Code/file templates
│ └── template.txt
└── scripts/ # Optional: Helper scripts
└── helper.pyYAML Frontmatter Reference
Required Fields
---
name: Skill Display Name
description: "What it does + when to use it (critical for discovery!)"
---YAML Safety Rules (CRITICAL)
ALWAYS quote the description field. Unquoted descriptions with colons, arrows, or special characters will silently break YAML parsing, making the skill invisible.
# BROKEN - colon after "approach" breaks YAML parsing
description: 4-layer approach: Trust → Structure → Calibration → Psychology
# FIXED - quoted string handles all special characters
description: "4-layer approach (Trust, Structure, Calibration, Psychology)"Characters that require quoting:
- Colons (
:) — YAML interprets as key-value separator - Arrows (
→,←) — Unicode can cause issues - Hash (
#) — YAML interprets as comment - Curly braces (
{}) — YAML interprets as flow mapping - Square brackets (
[]) — YAML interprets as flow sequence - Em-dashes (
—) — sometimes problematic
Validation command:
python3 -c "import yaml; yaml.safe_load(open('SKILL.md').read().split('---')[1])"If this throws an error, your frontmatter is broken and the skill won't load.
Optional Fields
---
name: Skill Display Name
description: "Complete description with capabilities and trigger phrases — put invocation keywords HERE (a separate triggers: field is not part of the documented frontmatter and is ignored)"
allowed-tools: Read, Grep, Glob, Bash # Restrict Claude's tool access
---Domain-Specific Templates
Analysis Skill Template
---
name: [Target] Analyzer
description: "Analyze [target] for [aspects]. Detect [issues], identify [patterns], measure [metrics]. Works with [file types]. Use when reviewing [context], investigating [problems], or need [specific insights]."
---
# [Target] Analyzer
Examines [target] to provide insights on [aspects].
## When to Use
- When you need to understand [target] quality
- When investigating [specific problems]
- When working with [file types or systems]
## Analysis Process
### 1. Data Collection
Gather [target] information using [tools/methods]
### 2. Analysis Execution
Apply [analysis techniques]:
- [Technique 1]
- [Technique 2]
- [Technique 3]
### 3. Results Interpretation
Interpret findings:
- [Metric 1]: [What it means]
- [Metric 2]: [What it means]
### 4. Recommendations
Provide actionable insights based on analysis
## Examples
[Concrete examples with real data]
## Best Practices
- [Best practice 1]
- [Best practice 2]
## Common Pitfalls
- [Common mistake] → [Correct approach]Generation Skill Template
---
name: [Output] Generator
description: "Generate [output type] from [input]. Create [artifacts], scaffold [structures], build [components]. Works with [formats]. Use when creating [specific things], need [output format], or building [project type]."
---
# [Output] Generator
Creates [output type] following [standards/patterns].
## When to Use
- Creating new [artifact type]
- Scaffolding [structure type]
- Need [specific output format]
## Generation Process
### 1. Input Requirements
Gather required information:
- [Input 1]
- [Input 2]
- [Input 3]
### 2. Template Selection
Choose appropriate template based on [criteria]
### 3. Generation Steps
1. [Step 1]
2. [Step 2]
3. [Step 3]
### 4. Output Validation
Verify generated content meets requirements
## Templates
Available templates:
- [Template 1]: For [use case]
- [Template 2]: For [use case]
## Examples
[Real-world generation examples]Transformation Skill Template
---
name: [Source] to [Target] Transformer
description: "Transform [source format] to [target format]. Convert [file types], migrate [systems], adapt [structures]. Works with [formats]. Use when converting between [formats], migrating from [old] to [new], or need [target format]."
---
# [Source] to [Target] Transformer
Converts [source] into [target] while preserving [important aspects].
## When to Use
- Converting [source format] files to [target format]
- Migrating from [old system] to [new system]
- Need [target format] output
## Transformation Process
### 1. Source Validation
Verify input [source] is valid and complete
### 2. Mapping
Map [source] elements to [target]:
- [Source element 1] → [Target element 1]
- [Source element 2] → [Target element 2]
### 3. Conversion
Apply transformation rules
### 4. Target Validation
Ensure output [target] is correct
## Examples
[Before/after transformation examples]Validation Skill Template
---
name: [Target] Validator
description: "Validate [target] against [criteria/standards]. Check [aspects], verify [requirements], ensure [compliance]. Works with [formats]. Use when validating [target type], ensuring [standards], or checking [requirements]."
---
# [Target] Validator
Validates [target] against [criteria] to ensure correctness.
## When to Use
- Validating [target type] meets standards
- Ensuring compliance with [requirements]
- Checking [aspects] are correct
## Validation Process
### 1. Load Validation Rules
Apply [standards/criteria]
### 2. Execute Checks
Run validation:
- [Check 1]
- [Check 2]
- [Check 3]
### 3. Report Results
Provide validation report:
- Pass/fail status
- Specific violations
- Suggested fixes
### 4. Suggest Fixes
For failed checks, recommend corrections
## Examples
[Validation examples with results]Orchestration Skill Template
---
name: [Workflow] Orchestrator
description: "Orchestrate [workflow] by coordinating [actions]. Automate [process], manage [steps], handle [dependencies]. Use when automating [workflow], coordinating [tasks], or managing [pipeline]."
---
# [Workflow] Orchestrator
Automates [workflow] by orchestrating multiple steps.
## When to Use
- Automating [multi-step process]
- Coordinating [related tasks]
- Managing [complex workflow]
## Orchestration Process
### 1. Workflow Definition
Define steps:
1. [Step 1]
2. [Step 2]
3. [Step 3]
### 2. Dependency Management
Handle dependencies:
- [Step X] requires [Step Y]
- [Parallel steps]
- [Sequential steps]
### 3. Execution
Run workflow with error handling
### 4. Monitoring
Track progress and handle failures
## Examples
[Complete workflow examples]Best Practices
DO
- Write specific, actionable descriptions
- Include file extensions and formats in description
- Use clear, imperative instructions
- Provide concrete examples
- Organize complex skills with supporting files
- Test that Claude discovers your skill
DON'T
- Write vague descriptions like "helps with files"
- Assume Claude knows when to use your skill
- Put everything in one massive skill
- Forget to include trigger keywords in description
- Skip examples (they're critical for understanding)
Output Format
After gathering requirements, provide:
## Generated Skill
Save this to: `~/.claude/skills/[skill-name]/SKILL.md`
\`\`\`markdown
---
name: [Generated Name]
description: [Optimized description]
---
[Full skill content based on template]
\`\`\`
## Verification Checklist
- [ ] YAML frontmatter parses without errors (run validation command)
- [ ] Description field is QUOTED (wrapped in double quotes)
- [ ] Description includes action verbs
- [ ] Description mentions file types/formats
- [ ] Description includes use cases and triggers
- [ ] Name is clear and specific
- [ ] Instructions are step-by-step
- [ ] Examples are concrete
- [ ] Best practices included
## Test Discovery
Try these phrases to verify Claude finds your skill:
1. "[Direct trigger phrase]"
2. "[Problem-based phrase]"
3. "[File type phrase]"Example: Creating a Python Code Analyzer
User: Create a skill to analyze Python code quality
Generated:
---
name: Python Code Quality Analyzer
description: Analyze Python code for complexity, PEP 8 compliance, code smells, and test coverage. Detect anti-patterns, measure cyclomatic complexity, suggest refactoring. Works with .py files. Use when reviewing Python code quality, performing code reviews, or investigating technical debt.
---
# Python Code Quality Analyzer
Comprehensive Python code quality analysis tool.
## When to Use This Skill
- Reviewing Python code quality
- Performing code reviews on .py files
- Investigating technical debt in Python projects
- Need metrics on code complexity
- Checking PEP 8 compliance
## Instructions
### Step 1: Code Collection
Identify Python files to analyze using Glob tool:
- Single file: `.py` file path
- Project: `**/*.py` pattern
### Step 2: Quality Analysis
Execute analysis:
- **Complexity**: Calculate cyclomatic complexity
- **Code Smells**: Detect anti-patterns
- **Style**: Check PEP 8 compliance
- **Coverage**: Assess test coverage (if tests exist)
### Step 3: Report Generation
Generate comprehensive report:
- Complexity scores per function
- Identified code smells with locations
- Style violations with fix suggestions
- Overall quality grade
### Step 4: Recommendations
Provide prioritized improvement suggestions
## Examples
### Example 1: Simple Function Analysis
**Input:** `utils.py` with helper functions
**Process:** Analyze complexity and style
**Output:** Report showing complexity scores, style violations, refactoring suggestions
### Example 2: Project-Wide Analysis
**Input:** Entire Python project (`**/*.py`)
**Process:** Analyze all files, aggregate metrics
**Output:** Project quality dashboard with trends
## Best Practices
- Run on changed files during code review
- Set complexity thresholds appropriate for project
- Fix high-priority issues first
- Track quality metrics over time
## Common Pitfalls
- Analyzing generated code (migrations, etc.) → Use .gitignore patterns to exclude
- Ignoring context (some complexity is necessary) → Review suggestions, don't blindly applyVersion: 1.0.0 Created: 2026-01-23 Replaces: skill-template-generator, claude-code-skills-expert
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.

