Documentation production methodology with DRY principles. Covers 8 document types (GUIDE, INCIDENT, SESSION, AUDIT, RECHERCHE, etc.), naming conventions, and YAML metadata.
Produces standardized technical documentation with DRY principles and YAML metadata.
/plugin marketplace add theflysurfer/claude-skills-marketplace/plugin install theflysurfer-claude-skills-marketplace@theflysurfer/claude-skills-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Version: 2.0.0-DRY
project/
├── docs/
│ ├── guides/ # Evolving docs
│ └── rapports/ # Event-based docs
└── README.md # Index
Types: GUIDE, METHODOLOGIE, AUDIT, TROUBLESHOOTING
Name: [TYPE]_[subject].md (no date)
Timestamp: In content, per section
Required YAML header:
---
title: "Guide X"
version: X.Y.Z
created: YYYY-MM-DD
updated: YYYY-MM-DD
authors: [...]
audience: ["Humans"|"LLM"|"All"]
level: "Beginner (1-3)" | "Intermediate (4-6)" | "Expert (7-10)"
status: "Active" | "Archived" | "Draft"
tags: [...]
related: [related files]
---
Types: INCIDENT, SESSION, RECHERCHE, RECOMMANDATIONS, MIGRATION, PERFORMANCE, SECURITE
Name: YYYY.MM.DD_HH.mm_[commit-short]_[TYPE]_[subject].md
Timestamp format: 2025.10.14_12.33 (dots + underscores)
Required metadata:
## Metadata
- **Date**: YYYY-MM-DD HH:MM
- **Commit**: abc1234 (7 chars)
- **Duration**: X hours (if applicable)
When: Blocking problem resolved
# Incident: [Title]
## Metadata
- Date, Duration, Severity, Commit
## Summary
[2-3 sentences]
## Symptoms → Timeline → Cause → Solution → Prevention
## References
When: Significant session (feature, refactor)
# Session: [Title]
## Metadata
- Date, Duration, Commits
## Objective → Achievements → Decisions → Problems → Modified files → Tests → Next
## References
When: Reusable procedure
---
[Complete YAML header]
---
# Guide: [Title]
## Overview → Concepts → Step-by-step → Troubleshooting → Examples → References
When: Pre-intervention analysis
# Audit: [Title]
## Metadata
## Executive Summary
- Score, Risks, Recommendations
## Findings (Critical, Major, Minor)
## Prioritized recommendations → Action plan → References
When: Investigation, exploration, benchmark
# Research: [Title]
## Metadata
- Date, Objective, Duration
## Question → Methodology → Discoveries → Options → Comparison → Recommendation → References
When: Important technical decision
# Recommendations: [Title]
## Metadata
## Context → Evaluated options (Pros/Cons/Evaluation) → Decision matrix → Recommendation → Risks → Next
When: Tech/version/infra migration
# Migration: [Title]
## Metadata
## Objective → Before/After → Procedure → Verifications → Problems → Rollback plan → Lessons → Follow-up
When: Measurable optimization
# Performance: [Title]
## Metadata
## Summary → Metrics before → Optimizations → Metrics after → Charts → Recommendations → References
When: Security audit, vulnerabilities
# Security Audit: [Title]
## Metadata
## Summary → Vulnerabilities (Critical/Major/Minor) → Best practices → Remediation plan → Verifications → References
Create report when:
Production:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.