メニュー
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/opsMachine/OM-Agency --skill skill-writerコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
SKILL.md を表示中
| name | skill-writer |
| description | Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure. |
This Skill helps you create well-structured Agent Skills for Claude Code that follow best practices and validation requirements.
Use this Skill when:
First, understand what the Skill should do:
Ask clarifying questions:
Keep it focused: One Skill = one capability
Determine where to create the Skill:
Personal Skills (~/.claude/skills/):
Project Skills (.claude/skills/):
Create the directory and files:
# 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)
Create YAML frontmatter with required fields:
---
name: skill-name
description: Brief description of what this does and when to use it
---
Field requirements:
name:
pdf-processor, git-commit-helperPDF_Processor, Git Commits!description:
Optional frontmatter fields:
allowed-tools: Restrict tool access (comma-separated list)
allowed-tools: Read, Grep, Glob
Use for:
contract: Structured metadata for workflow chaining. Required for any skill that participates in the workflow system (see Writing Contracts below).
contract:
tags: [tag1, tag2]
state_source: spec | security_plan
inputs:
params:
- name: spec_path
required: true
gates:
- field: "Test Plan.status"
value: "Planned"
outputs:
mutates:
- field: "Test Plan.status"
sets_to: "Tests Written"
side_effects: ["Comments GitHub issue"]
next: [implement-to-pass]
human_gate: false
The description is critical for Claude to discover your Skill.
Formula: [What it does] + [When to use it] + [Key triggers]
Examples:
✅ Good:
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:
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:
description: Helps with documents
description: For data analysis
Tips:
Use clear Markdown sections:
# 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
For complex scenarios, see reference.md.
### Step 7: Add supporting files (optional)
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
\`\`\`
Check these requirements:
✅ File structure:
name✅ YAML frontmatter:
--- on line 1--- before contentname follows naming rulesdescription is specific and < 1024 chars✅ Content quality:
✅ Testing:
Restart Claude Code (if running) to load the Skill
Ask relevant questions that match the description:
Can you help me extract text from this PDF?
Verify activation: Claude should use the Skill automatically
Check behavior: Confirm Claude follows the instructions correctly
If Claude doesn't use the Skill:
Make description more specific:
Check file location:
ls ~/.claude/skills/skill-name/SKILL.md
ls .claude/skills/skill-name/SKILL.md
Validate YAML:
cat SKILL.md | head -n 10
Run debug mode:
claude --debug
---
name: code-reader
description: Read and analyze code without making changes. Use for code review, understanding codebases, or documentation.
allowed-tools: Read, Grep, Glob
---
---
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
\`\`\`
---
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)
If your skill participates in the workflow system (feature path, bug path, security path), add a contract: block to frontmatter. The contract is what makes chaining programmatic — the workflow-router reads contracts to build decision trees and a manager agent uses them to auto-chain skills.
contract:
tags: [tag1, tag2] # Capability tags. Used for discovery (see Tag Lookup in workflow-router).
# Common: intake, tdd, implementation, testing, security, github, closure
state_source: spec # Which artifact holds this skill's state. Values: spec | security_plan
inputs:
params: # Explicit arguments the skill requires
- name: spec_path
required: true
gates: # State conditions that must be true BEFORE this skill runs.
- field: "status" # Field path inside the state artifact
value: "Approved" # Must equal this value. Router checks this before allowing invocation.
outputs:
mutates: # State fields this skill WRITES. Router uses this to know what gates will be satisfied next.
- field: "Test Plan.status"
sets_to: "Tests Written"
side_effects: [] # Transparency: list non-state side effects (e.g. "Comments GitHub issue")
next: [skill-name] # Skills that are valid to run AFTER this one. Router presents these as options.
human_gate: false # If true: workflow pauses for human approval AFTER this skill completes.
# The skill AFTER the gate is not invoked until the human says go.
Read DESIGN.md first to understand the shared/ vs primitives/ architecture.
If your skill needs general methodology that applies to ANY project, reference existing shared docs or propose creating a new one:
Existing shared docs:
> See shared/github-ops.md for posting comments and updating project status.
> See shared/spec-io.md for reading acceptance criteria and updating Test Plan status.
> See shared/e2e-patterns.md for E2E testing patterns (Playwright, reconnaissance-then-action).
> See shared/test-planning.md for test granularity framework (when to combine vs split tests).
When to create a NEW shared doc:
When to reference primitives instead:
primitives/testing-conventions.mdprimitives/stack.mdDESIGN.md → "Why Shared vs Primitives" for the decision ruleKeep your step headers (e.g. "Step 7: Update GitHub Issue") so the skill's flow is readable. Replace only the implementation details under those steps with the reference.
---
name: plan-tests
description: "Create a test plan for an approved spec..."
contract:
tags: [tdd, test-planning]
state_source: spec
inputs:
params:
- name: spec_path
required: true
gates:
- field: "status"
value: "Approved"
outputs:
mutates:
- field: "Test Plan.status"
sets_to: "Planned"
side_effects: []
next: [write-failing-test]
human_gate: false
---
shared/github-ops.md and shared/spec-io.md.Before finalizing a Skill, verify:
Skill doesn't activate:
Multiple Skills conflict:
Skill has errors:
See the documentation for complete examples:
When creating a Skill, I will:
The result will be a complete, working Skill that follows all best practices and validation rules.