skill-generator
Generates Claude Code skills from user descriptions. Use when creating new skills, converting documentation to skills, or scaffolding skill structure.
What this skill does
# Skill Generator
## Purpose
Generate production-ready Claude Code skills from natural language descriptions, existing documentation, or code examples.
## When to Use
- User asks to "create a skill" or "generate a skill"
- Converting documentation into skill format
- Scaffolding new skill structure
- Creating skills from examples or patterns
## Process
1. **Understand Requirements**
- Ask clarifying questions if needed:
- What should the skill do?
- What tools/APIs does it need?
- Who is the target audience?
- Are there existing docs or examples?
2. **Determine Skill Type**
- Generator skill (creates content)
- Integrator skill (connects to services)
- Converter skill (transforms formats)
- Or combination
3. **Generate SKILL.md**
Follow this structure:
```markdown
---
name: [skill-name]
description: [What it does + when to use it - max 1024 chars]
allowed-tools: [optional - list tools]
---
# [Skill Name]
## Purpose
[2-3 sentences]
## Process
1. [Step 1]
2. [Step 2]
3. [Step 3]
## Examples
[Concrete examples]
## Best Practices
[Key guidelines]
```
4. **Create Directory Structure**
```
.claude/skills/[skill-name]/
├── SKILL.md # Main file (3-5KB max)
├── reference/ # Optional: Detailed docs
│ └── [topic].md
└── scripts/ # Optional: Utility scripts
└── [script].py
```
5. **Apply Best Practices**
- Use gerund form for name: `processing-pdfs`
- Write description in third person
- Keep SKILL.md under 500 lines
- Use progressive disclosure for large content
- Include concrete examples
6. **Review and Refine**
- Check YAML frontmatter is valid
- Verify description is specific
- Ensure clear instructions
- Test mental walkthrough
## Output Format
Always create:
1. **SKILL.md** - Main skill file
2. **Directory structure** - Planned reference/ scripts if needed
3. **Usage examples** - How to invoke the skill
4. **Next steps** - What user should do next
## Example Generation
If user says: "Create a skill for processing Excel files"
Generate:
```
.claude/skills/
├── excel-processor/
│ ├── SKILL.md
│ ├── reference/
│ │ ├── pandas-api.md
│ │ └── openpyxl-api.md
│ └── scripts/
│ ├── analyze.py
│ └── convert.py
```
SKILL.md includes:
- Name: `excel-processor`
- Description: "Processes Excel files including data extraction, format conversion, and analysis. Use when working with .xlsx files, spreadsheets, or tabular data."
- Process for reading, analyzing, converting Excel files
- Examples with pandas and openpyxl
- Links to reference docs for detailed API usage
## Quality Checklist
Before presenting to user, verify:
- [ ] YAML frontmatter is valid (starts with `---`)
- [ ] Name uses lowercase, numbers, hyphens only
- [ ] Description is specific and includes trigger terms
- [ ] Description is under 1024 characters
- [ ] Instructions are clear and numbered
- [ ] Examples are concrete and practical
- [ ] File paths use forward slashes
- [ ] Progressive disclosure used if content is large
- [ ] No reserved words (anthropic, claude) in name
## Common Patterns
### For Generator Skills
```
## Purpose
Generate [output type] from [input type]
## Process
1. Analyze [input]
2. Generate [output] using [best practices]
3. Validate output
4. Present to user
```
### For Integrator Skills
```
## Purpose
Integrate with [service name]
## Process
1. Understand user's goal
2. Prepare data for [service]
3. Call [service] API/tool
4. Handle response
5. Report results
```
### For Converter Skills
```
## Purpose
Convert [format A] to [format B]
## Process
1. Read [format A] file
2. Parse structure
3. Transform to [format B]
4. Write output
5. Verify conversion
```
## Progressive Disclosure Guidance
If skill will have >10KB of documentation:
**In SKILL.md:**
```markdown
## Quick Reference
[Brief overview and common tasks]
## Detailed Documentation
- **API Reference**: See [reference/api.md](reference/api.md)
- **Examples**: See [reference/examples.md](reference/examples.md)
- **Troubleshooting**: See [reference/troubleshooting.md](reference/troubleshooting.md)
```
Then create the reference files with detailed content.
## Troubleshooting
**If requirements are unclear:**
- Ask: "What specific task should this skill automate?"
- Ask: "What tools or APIs does it need to work with?"
- Ask: "Who will be using this skill?"
**If skill seems too complex:**
- Consider splitting into multiple focused skills
- Use progressive disclosure for documentation
- Create subtasks as separate skills
**If documentation is large:**
- Use progressive disclosure pattern
- Create reference/ directory
- Link to detailed docs from SKILL.md
## See Also
- [SKILL_REVIEWER.md](.claude/skills/skill-reviewer/SKILL.md) - Review skills for quality
- [SKILL_OPTIMIZER.md](.claude/skills/skill-optimizer/SKILL.md) - Optimize existing skills
- [SKILL_ARCHITECT.md](.claude/skills/skill-architect/SKILL.md) - Complete skill workflow
## Sources
Based on:
- [CLAUDE_SKILLS_ARCHITECTURE.md](../../../docs/CLAUDE_SKILLS_ARCHITECTURE.md)
- Official Anthropic skill documentation
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.