Skill Writer

---
name: skill-writer
description: 'Create or improve Agent Skills, SKILL.md frontmatter, structure, instructions, and resources.'
---

# Skill Writer

This Skill helps you create well-structured Agent Skills for Claude Code that follow best practices and validation requirements.

## When to use this Skill

Use this Skill when:
- Creating a new Agent Skill
- Writing or updating SKILL.md files
- Designing skill structure and frontmatter
- Troubleshooting skill discovery issues
- Converting existing prompts or workflows into Skills

## Instructions

### Step 1: Determine Skill scope

First, understand what the Skill should do:

1. **Ask clarifying questions**:
   - What specific capability should this Skill provide?
   - When should Claude use this Skill?
   - What tools or resources does it need?
   - Is this for personal use or team sharing?

2. **Keep it focused**: One Skill = one capability
   - Good: "PDF form filling", "Excel data analysis"
   - Too broad: "Document processing", "Data tools"

### Step 2: Choose Skill location

Determine where to create the Skill:

**Personal Skills** (`~/.claude/skills/`):
- Individual workflows and preferences
- Experimental Skills
- Personal productivity tools

**Project Skills** (`.claude/skills/`):
- Team workflows and conventions
- Project-specific expertise
- Shared utilities (committed to git)

### Step 3: Create Skill structure

Create the directory and files:

```bash
# Personal
mkdir -p ~/.claude/skills/skill-name

# Project
mkdir -p .claude/skills/skill-name
```

For multi-file Skills:
```
skill-name/
├── SKILL.md (required)
├── reference.md (optional)
├── examples.md (optional)
├── scripts/
│   └── helper.py (optional)
└── templates/
    └── template.txt (optional)
```

### Step 4: Write SKILL.md frontmatter

Create YAML frontmatter with required fields:

```yaml
---
name: skill-name
description: Brief description of what this does and when to use it
---
```

**Field requirements**:

- **name**:
  - Lowercase letters, numbers, hyphens only
  - Max 64 characters
  - Must match directory name
  - Good: `pdf-processor`, `git-commit-helper`
  - Bad: `PDF_Processor`, `Git Commits!`

- **description**:
  - Max 1024 characters
  - Include BOTH what it does AND when to use it
  - Use specific trigger words users would say
  - Mention file types, operations, and context

**Optional frontmatter fields**:

- **allowed-tools**: Restrict tool access (comma-separated list)
  ```yaml
  allowed-tools: Read, Grep, Glob
  ```
  Use for:
  - Read-only Skills
  - Security-sensitive workflows
  - Limited-scope operations

### Step 5: Write effective descriptions

The description is critical for Claude to discover your Skill.

**Formula**: `[What it does] + [When to use it] + [Key triggers]`

**Examples**:

✅ **Good**:
```yaml
description: Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
```

✅ **Good**:
```yaml
description: Analyze Excel spreadsheets, create pivot tables, and generate charts. Use when working with Excel files, spreadsheets, or analyzing tabular data in .xlsx format.
```

❌ **Too vague**:
```yaml
description: Helps with documents
description: For data analysis
```

**Tips**:
- Include specific file extensions (.pdf, .xlsx, .json)
- Mention common user phrases ("analyze", "extract", "generate")
- List concrete operations (not generic verbs)
- Add context clues ("Use when...", "For...")

### Step 6: Structure the Skill content

Use clear Markdown sections:

```markdown
# Skill Name

Brief overview of what this Skill does.

## Quick start

Provide a simple example to get started immediately.

## Instructions

Step-by-step guidance for Claude:
1. First step with clear action
2. Second step with expected outcome
3. Handle edge cases

## Examples

Show concrete usage examples with code or commands.

## Best practices

- Key conventions to follow
- Common pitfalls to avoid
- When to use vs. not use

## Requirements

List any dependencies or prerequisites:
```bash
pip install package-name
```

## Advanced usage

For complex scenarios, see [reference.md](reference.md).
```

### Step 7: Add supporting files (optional) + token budget

Create additional files for progressive disclosure:

**reference.md**: Detailed API docs, advanced options
**examples.md**: Extended examples and use cases
**scripts/**: Helper scripts and utilities
**templates/**: File templates or boilerplate

Reference them from SKILL.md:
```markdown
For advanced usage, see [reference.md](reference.md).

Run the helper script:
\`\`\`bash
python scripts/helper.py input.txt
\`\`\`
```

#### Token-efficiency budget (required for new/edited skills)

Skills are loaded into the agent context. Bloat here multiplies every session.

| Artifact | Soft cap | Hard expectation |
|---|---|---|
| `SKILL.md` | **~8 KB (~2k tokens)** | Triggers, steps, script entrypoints, top pitfalls only |
| `reference.md` | unlimited | Flags, edge cases — **Read only on demand** |
| `scripts/*` | prefer scripts | Anything mechanical or multi-round-trip CLI |

**Rules:**

1. If an agent would run the same 3+ CLI calls every time → write a script that writes artifacts to disk and prints a JSON summary.
2. If you wrote the same `.tmp/*.ts` helper in two real sessions → promote it into `scripts/` and delete the ad-hoc pattern from instructions.
3. Happy-path workflows (commit/ship, gather PR/MR context, list+close jobs) must **not** require loading an encyclopedia skill.
4. Put exact argv for the top 5 operations in a short cheat sheet at the top of `SKILL.md` so agents stop running `--help`.
5. Encode pitfalls in scripts when possible (pagination, wrong flags) instead of hoping the model rereads prose.

Validate size before finishing:

```bash
wc -c path/to/SKILL.md   # prefer < 8000; investigate if > 16000
```

### Step 8: Validate the Skill

Check these requirements:

✅ **File structure**:
- [ ] SKILL.md exists in correct location
- [ ] Directory name matches frontmatter `name`

✅ **YAML frontmatter**:
- [ ] Opening `---` on line 1
- [ ] Closing `---` before content
- [ ] Valid YAML (no tabs, correct indentation)
- [ ] `name` follows naming rules
- [ ] `description` is specific and < 1024 chars

✅ **Content quality**:
- [ ] Clear instructions for Claude
- [ ] Concrete examples provided
- [ ] Edge cases handled
- [ ] Dependencies listed (if any)
- [ ] `SKILL.md` within token budget (~8KB soft cap) or justified
- [ ] Multi-step CLI work has a `scripts/` helper when it saves round trips

✅ **Testing**:
- [ ] Description matches user questions
- [ ] Skill activates on relevant queries
- [ ] Instructions are clear and actionable

### Step 9: Test the Skill

1. **Restart Claude Code** (if running) to load the Skill

2. **Ask relevant questions** that match the description:
   ```
   Can you help me extract text from this PDF?
   ```

3. **Verify activation**: Claude should use the Skill automatically

4. **Check behavior**: Confirm Claude follows the instructions correctly

### Step 10: Debug if needed

If Claude doesn't use the Skill:

1. **Make description more specific**:
   - Add trigger words
   - Include file types
   - Mention common user phrases

2. **Check file location**:
   ```bash
   ls ~/.claude/skills/skill-name/SKILL.md
   ls .claude/skills/skill-name/SKILL.md
   ```

3. **Validate YAML**:
   ```bash
   cat SKILL.md | head -n 10
   ```

4. **Run debug mode**:
   ```bash
   claude --debug
   ```

## Common patterns

### Read-only Skill

```yaml
---
name: code-reader
description: Read and analyze code without making changes. Use for code review, understanding codebases, or documentation.
allowed-tools: Read, Grep, Glob
---
```

### Script-based Skill

```yaml
---
name: data-processor
description: Process CSV and JSON data files with Python scripts. Use when analyzing data files or transforming datasets.
---

# Data Processor

## Instructions

1. Use the processing script:
\`\`\`bash
python scripts/process.py input.csv --output results.json
\`\`\`

2. Validate output with:
\`\`\`bash
python scripts/validate.py results.json
\`\`\`
```

### Multi-file Skill with progressive disclosure

```yaml
---
name: api-designer
description: Design REST APIs following best practices. Use when creating API endpoints, designing routes, or planning API architecture.
---

# API Designer

Quick start: See [examples.md](examples.md)

Detailed reference: See [reference.md](reference.md)

## Instructions

1. Gather requirements
2. Design endpoints (see examples.md)
3. Document with OpenAPI spec
4. Review against best practices (see reference.md)
```

## Best practices for Skill authors

1. **One Skill, one purpose**: Don't create mega-Skills
2. **Specific descriptions**: Include trigger words users will say
3. **Clear instructions**: Write for Claude, not humans
4. **Concrete examples**: Show real code, not pseudocode
5. **List dependencies**: Mention required packages in description
6. **Test with teammates**: Verify activation and clarity
7. **Version your Skills**: Document changes in content
8. **Use progressive disclosure**: Put advanced details in separate files

## Validation checklist

Before finalizing a Skill, verify:

- [ ] Name is lowercase, hyphens only, max 64 chars
- [ ] Description is specific and < 1024 chars
- [ ] Description includes "what" and "when"
- [ ] YAML frontmatter is valid
- [ ] Instructions are step-by-step
- [ ] Examples are concrete and realistic
- [ ] Dependencies are documented
- [ ] File paths use forward slashes
- [ ] Skill activates on relevant queries
- [ ] Claude follows instructions correctly

## Troubleshooting

**Skill doesn't activate**:
- Make description more specific with trigger words
- Include file types and operations in description
- Add "Use when..." clause with user phrases

**Multiple Skills conflict**:
- Make descriptions more distinct
- Use different trigger words
- Narrow the scope of each Skill

**Skill has errors**:
- Check YAML syntax (no tabs, proper indentation)
- Verify file paths (use forward slashes)
- Ensure scripts have execute permissions
- List all dependencies

## Examples

See the documentation for complete examples:
- Simple single-file Skill (commit-helper)
- Skill with tool permissions (code-reviewer)
- Multi-file Skill (pdf-processing)

## Output format

When creating a Skill, I will:

1. Ask clarifying questions about scope and requirements
2. Suggest a Skill name and location
3. Create the SKILL.md file with proper frontmatter
4. Include clear instructions and examples
5. Add supporting files if needed
6. Provide testing instructions
7. Validate against all requirements

The result will be a complete, working Skill that follows all best practices and validation rules.