本文へ移動
cccskills
無料GitHub で公開

agent-documenting-references

Standardized reference documentation section structure for agents - project guidance, conventions, related agents, and Skills. Use when implementing or updating agent documentation.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md9.4 KB
  • metadata.json122 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Documenting Agent References

Standard structure for "Reference Documentation" sections in agent files to ensure consistent navigation and discoverability.

When This Skill Loads

This Skill auto-loads when implementing agents or updating agent documentation sections.

Reference Documentation Section

All agents SHOULD include a "Reference Documentation" section near the end (before any appendices) with standardized subsections.

Section Template

## Reference Documentation

**Project Guidance**:

- [CLAUDE.md](../../CLAUDE.md) - Primary guidance for Claude Code
- [Agent-specific convention](path/to/convention.md) - Domain-specific standards

**Related Agents**:

- `maker-agent` - Creates content for this domain
- `checker-agent` - Validates content (upstream dependency)
- `fixer-agent` - Fixes issues found by checker
- `related-domain-agent` - Related functionality

**Related Conventions**:

- [Primary Convention](path/to/convention.md) - Main standards this agent implements
- [Secondary Convention](path/to/convention.md) - Additional relevant standards

**Skills**:

- `primary-skill` - Main Skill for domain knowledge
- `wow-assessing-criticality-confidence` - Criticality assessment (if applicable)
- `wow-generating-validation-reports` - Report generation (if applicable)

Subsection Details

Project Guidance

Purpose: Link to primary project instructions and domain-specific conventions.

Always Include:

  • CLAUDE.md (primary guidance for all agents)

Conditionally Include:

  • Domain-specific conventions (e.g., README Quality Convention for readme-agents)
  • Framework-specific guidance (e.g., Hextra guide for ayokoding-web-agents)
  • Special standards relevant to agent's scope

Pattern:

**Project Guidance**:

- [CLAUDE.md](../../CLAUDE.md) - Primary guidance
- [Specific Convention](path/to/convention.md) - Domain standards

Related Agents

Purpose: Help users understand agent ecosystem and workflow relationships.

Include:

  • Upstream agents: Agents this agent depends on (e.g., checker for fixer)
  • Downstream agents: Agents that depend on this one (e.g., fixer for checker)
  • Parallel agents: Agents in same family/domain (e.g., other checkers)
  • Complementary agents: Agents with related functionality

Organize by Relationship:

**Related Agents**:

- `upstream-agent` - Description of relationship
- `downstream-agent` - Description of relationship
- `parallel-agent` - Description of functionality

Examples by Agent Type:

Maker Agents:

- `checker-agent` - Validates content created by this maker
- `related-maker` - Creates content in related domain

Checker Agents:

- `maker-agent` - Creates content this checker validates
- `fixer-agent` - Fixes issues found by this checker
- `related-checker` - Validates related aspects

Fixer Agents:

- `checker-agent` - Generates audit reports this fixer processes
- `maker-agent` - Updates content after fixes applied

Related Conventions

Purpose: Link to conventions and development practices the agent implements.

Include:

  • Primary convention agent implements
  • Secondary conventions relevant to agent's scope
  • Development practices agent follows (e.g., AI Agents Convention)
  • Standards agent enforces (for checkers)

Pattern:

**Related Conventions**:

- [Primary Convention](path/to/convention.md) - Main standards
- [Secondary Convention](path/to/convention.md) - Additional standards
- [Development Practice](path/to/practice.md) - Implementation guidance

Checkers Should List:

  • Conventions they validate against
  • Quality standards they enforce

Makers Should List:

  • Conventions they follow when creating content
  • Formatting standards they apply

Skills

Purpose: Reference Skills the agent uses for domain knowledge and patterns.

Include:

  • All Skills listed in agent's skills: frontmatter field
  • Skills should be listed without path (just skill name)
  • Brief description of what each Skill provides

Pattern:

**Skills**:

- `domain-skill` - Domain-specific knowledge
- `wow-skill` - Cross-cutting pattern or workflow
- `agent-skill` - Agent development guidance

Note: Skills section duplicates frontmatter skills: field for documentation visibility.

Placement in Agent Files

Recommended Location: Near end of agent file, before any appendices or examples.

Typical Structure:

# Agent Name

[Agent description]

## Core Responsibility

[What agent does]

## Main Content Sections

[Detailed agent instructions]

## Reference Documentation

[Reference sections using template above]

## Appendices (Optional)

[Additional examples, edge cases, etc.]

Examples by Agent Family

docs-family Agents

## Reference Documentation

**Project Guidance**:

- [CLAUDE.md](../../CLAUDE.md) - Primary guidance
- [Content Quality Principles](../../docs/explanation/rules/conventions/content/ex-ru-co-co__quality.md)
- [Diátaxis Framework](../../docs/explanation/rules/conventions/meta/ex-ru-co-me__diataxis-framework.md)

**Related Agents**:

- `docs-maker` - Creates documentation
- `docs-checker` - Validates documentation
- `docs-fixer` - Fixes documentation issues
- `docs-tutorial-checker` - Specialized tutorial validation

**Related Conventions**:

- [Content Quality Principles](../../docs/explanation/rules/conventions/content/ex-ru-co-co__quality.md)
- [Factual Validation Convention](../../docs/explanation/rules/conventions/content/ex-ru-co-co__factual-validation.md)
- [Linking Convention](../../docs/explanation/rules/conventions/formatting/ex-ru-co-fo__linking.md)

**Skills**:

- `docs-applying-content-quality` - Content quality standards
- `docs-validating-factual-accuracy` - Fact-checking methodology
- `wow-assessing-criticality-confidence` - Criticality assessment
- `wow-generating-validation-reports` - Report generation

readme-family Agents

## Reference Documentation

**Project Guidance**:

- [CLAUDE.md](../../CLAUDE.md) - Primary guidance
- [README Quality Convention](../../docs/explanation/rules/conventions/content/ex-ru-co-co__readme-quality.md)

**Related Agents**:

- `readme-maker` - Creates README content
- `readme-checker` - Validates README quality
- `readme-fixer` - Fixes README issues
- `docs-checker` - Validates other documentation

**Related Conventions**:

- [README Quality Convention](../../docs/explanation/rules/conventions/content/ex-ru-co-co__readme-quality.md)
- [Content Quality Principles](../../docs/explanation/rules/conventions/content/ex-ru-co-co__quality.md)

**Skills**:

- `readme-writing-readme-files` - README-specific standards
- `wow-assessing-criticality-confidence` - Criticality assessment
- `wow-generating-validation-reports` - Report generation

plan-family Agents

## Reference Documentation

**Project Guidance**:

- [CLAUDE.md](../../CLAUDE.md) - Primary guidance
- [Plans Organization Convention](../../docs/explanation/rules/conventions/project/ex-ru-co-pr__plans-organization.md)

**Related Agents**:

- `plan-maker` - Creates project plans
- `plan-checker` - Validates plan quality
- `plan-executor` - Executes plans
- `plan-execution-checker` - Validates completed work
- `plan-fixer` - Fixes plan issues

**Related Conventions**:

- [Plans Organization Convention](../../docs/explanation/rules/conventions/project/ex-ru-co-pr__plans-organization.md)
- [Gherkin Acceptance Criteria](../../docs/explanation/rules/development/infra/ex-ru-de-in__acceptance-criteria.md)

**Skills**:

- `plan-creating-project-plans` - Plan structure and organization
- `plan-writing-gherkin-criteria` - Acceptance criteria patterns
- `wow-assessing-criticality-confidence` - Criticality assessment

Benefits of Standardization

✅ Improved Discoverability: Users can quickly find related agents and conventions
✅ Consistent Navigation: Same structure across all agents
✅ Clear Relationships: Understand agent dependencies and workflows
✅ Better Maintainability: Easy to update references across agents
✅ Enhanced Documentation: Skills and conventions properly referenced

Best Practices

  1. Keep Links Current: Update when conventions move or rename
  2. Be Selective: Only include truly relevant references
  3. Describe Relationships: Explain how related agents connect
  4. Match Frontmatter: Ensure Skills section matches skills: field
  5. Use Relative Paths: Make links work from agent file location
  6. Group Logically: Keep subsections organized and scannable

Key Takeaways

  • Standard structure: Use consistent subsections across all agents
  • Four subsections: Project Guidance, Related Agents, Related Conventions, Skills
  • Clear relationships: Help users understand agent ecosystem
  • Proper placement: Near end of agent file before appendices
  • Keep current: Update references when files move or change
  • Match frontmatter: Skills section mirrors skills: field

This standardization improves agent documentation consistency and helps users navigate the agent ecosystem effectively.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic expungement research". NOT for interpreting laws (use national-expungement-expert), building UI, or legal advice.

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

Generated by Gremlin Forge Meta-Agent 🍆👾⚡

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

Work autonomously without waiting for hand-holding — complete tasks end-to-end without asking for permission at every step.

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

abmahnung

無料

Entwurf einer BAG-konformen Abmahnung im Arbeitsrecht – konkrete Schilderung der Pflichtverletzung, klare Verhaltenserwartung, ausdrückliche Sanktionsandrohung. Use when AG eine verhaltensbedingte Sanktion vor einer Kündigung dokumentieren muss oder AN die Wirksamkeit einer empfangenen Abmahnung prüft.

日本語の概要は準備中です。原文の説明を表示しています。

majiayu000/claude-skill-registry-data262026年10月11日 更新

majiayu000 のスキルをすべて見る

このスキルの問題を報告する