Agent skill
documentation
Install this agent skill to your Project
npx add-skill https://github.com/duc01226/EasyPlatform/tree/main/.claude/skills/documentation
SKILL.md
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.
Quick Summary
Goal: Enhance code documentation, API docs, README files, and technical writing with verified accuracy.
Workflow:
- Analysis — Build knowledge model: discover APIs, components, structure, documentation gaps
- Plan — Generate detailed documentation plan with priorities and outline
- Approval Gate — Present plan for explicit user approval before writing
- Execute — Write documentation following anti-hallucination protocols
Key Rules:
- Never proceed without explicit user approval of the documentation plan
- Verify every documented feature against actual code (no assumptions)
- For business feature docs, use
feature-docsskill instead - Include practical examples and copy-pasteable code snippets
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Skill Variant: Use this skill for interactive documentation tasks including code docs AND README files.
Disambiguation
- For business feature docs → use
feature-docs - This skill covers code documentation and README files
Documentation Enhancement
You are to operate as an expert technical writer and software documentation specialist to enhance documentation.
IMPORTANT: Always thinks hard, plan step by step to-do list first before execute. Always remember to-do list, never compact or summary it when memory context limit reach. Always preserve and carry your to-do list through every operation.
Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs
file:lineproof. Confidence: >95% recommend freely, 80-94% with caveats, <80% DO NOT recommend — gather more evidence. Cross-service validation required for architectural changes. MUST READ.claude/skills/shared/evidence-based-reasoning-protocol.mdfor full protocol and checklists.
README Structure Template
Use this structure when creating or improving README files:
# Project Name
Brief description of the project.
## Table of Contents
- [Features](#features)
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Configuration](#configuration)
- [Usage](#usage)
- [Development](#development)
- [Testing](#testing)
- [Deployment](#deployment)
- [Troubleshooting](#troubleshooting)
- [Contributing](#contributing)
- [License](#license)
## Features
- Feature 1
- Feature 2
## Prerequisites
- Node.js >= 18
- .NET 9 SDK
## Installation
```bash
# Clone the repository
git clone [url]
# Install dependencies
npm install
dotnet restore
```
## Configuration
[Configuration details]
## Usage
[Usage examples]
## Development
[Development setup]
## Testing
[Testing instructions]
## Troubleshooting
[Common issues and solutions]
PHASE 1: EXTERNAL MEMORY-DRIVEN DOCUMENTATION ANALYSIS
Build a structured knowledge model in .ai/workspace/analysis/[task-name].analysis.md.
PHASE 1A: INITIALIZATION AND DISCOVERY
- Initialize the analysis file with standard headings
- Discovery searches for all related files
DOCUMENTATION-SPECIFIC DISCOVERY
DOCUMENTATION_COMPLETENESS_DISCOVERY: Focus on documentation-relevant patterns:
-
API Documentation Analysis: Find API endpoints and identify missing documentation. Document under
## API Documentation. -
Component Documentation Analysis: Find public classes/methods and identify complex logic needing explanation. Document under
## Component Documentation. -
Basic Structure Analysis: Find key configuration files and main application flows. Document under
## Structure Documentation.
PROJECT_OVERVIEW_DISCOVERY (README-specific): Focus on README-relevant patterns:
- Project Structure Analysis: Find entry points, map key directories, identify technologies
- Feature Discovery: Find user-facing features and map API endpoints
- Setup Requirements Analysis: Find package files, map dependencies, identify configuration needs
PHASE 1B: SYSTEMATIC FILE ANALYSIS FOR DOCUMENTATION
IMPORTANT: Must do with todo list.
For each file, document in ## Knowledge Graph:
- Standard fields plus documentation-specific:
documentationGaps: Missing or incomplete documentationcomplexityLevel: How difficult to understand (1-10)userFacingFeatures: Features needing user documentationdeveloperNotes: Technical details needing developer docsexampleRequirements: Code examples or usage scenarios neededapiDocumentationNeeds: API endpoints requiring documentationconfigurationOptions: Configuration parameters needing explanationtroubleshootingAreas: Common issues requiring troubleshooting docs
README-specific fields (when analyzing for README documentation):
| Field | Description |
|---|---|
readmeRelevance |
How component should be represented (1-10) |
userImpact |
How component affects end users |
setupRequirements |
Prerequisites for this component |
configurationNeeds |
Configuration required |
featureDescription |
User-facing features provided |
exampleUsage |
Usage examples for README |
projectContext |
How it fits into overall project |
PHASE 1C: OVERALL ANALYSIS
Write comprehensive summary showing:
- Complete end-to-end workflows discovered
- Documentation gaps identified
- Priority areas for documentation
- Key features and capabilities (README)
- Setup and configuration requirements (README)
PHASE 2: DOCUMENTATION PLAN GENERATION
Generate detailed documentation plan under ## Documentation Plan:
- Focus on completeness
- Ensure clarity
- Include examples
- Maintain consistency
For README plans, generate a detailed outline covering: Project Overview, Installation, Usage, Configuration, Development guidelines.
PHASE 3: APPROVAL GATE
CRITICAL: Present documentation plan for explicit approval. DO NOT proceed without it.
PHASE 4: DOCUMENTATION EXECUTION
Once approved, execute the plan using all DOCUMENTATION_SAFEGUARDS.
SUCCESS VALIDATION
Verify documentation is:
- Accurate (matches actual code)
- Complete (covers all public APIs)
- Helpful (includes examples)
README-specific checks:
- Accurate: All instructions work
- Comprehensive: Covers all setup needs
- Helpful: New users can get started
- Tested: Commands verified to work
Document under ## Documentation Validation.
Documentation Guidelines
- Accuracy-first approach: Verify every documented feature with actual code
- User-focused content: Organize documentation based on user needs
- Example-driven documentation: Include practical examples and usage scenarios
- Consistency maintenance: Follow established documentation patterns
- No assumptions: Always verify behavior before documenting
README Guidelines
- User-first approach: Organize content for new users; start with what the project does and why; provide clear getting-started path
- Verified instructions: Test all setup and installation instructions; include exact commands that work; document version requirements
- Practical examples: Include working examples users can follow; show common use cases; provide copy-pasteable code snippets
- No assumptions: Don't assume user knowledge; explain acronyms and domain terms; link to prerequisite documentation
⚠️ MUST READ: CLAUDE.md for code pattern examples (backend/frontend) when writing code documentation. See .claude/docs/ for existing documentation structure.
Anti-Hallucination Protocols
ASSUMPTION_VALIDATION_CHECKPOINT
Before every major operation:
- "What assumptions am I making about [X]?"
- "Have I verified this with actual code evidence?"
EVIDENCE_CHAIN_VALIDATION
Before claiming any relationship:
- "I believe X calls Y because..." → show actual code
- "This follows pattern Z because..." → cite specific examples
TOOL_EFFICIENCY_PROTOCOL
- Batch multiple Grep searches into single calls with OR patterns
- Use parallel Read operations for related files
CONTEXT_ANCHOR_SYSTEM
Every 10 operations:
- Re-read the original task description
- Verify the current operation aligns with original goals
Related
feature-docschangelogrelease-notes
Task Planning Notes (MUST FOLLOW)
- Always plan and break work into many small todo tasks
- Always add a final review todo task to verify work quality and identify fixes/enhancements
Closing Reminders
- MUST break work into small todo tasks using
TaskCreateBEFORE starting - MUST search codebase for 3+ similar patterns before creating new code
- MUST cite
file:lineevidence for every claim (confidence >80% to act) - MUST add a final review todo task to verify work quality MANDATORY IMPORTANT MUST READ the following files before starting:
- MUST READ
.claude/skills/shared/evidence-based-reasoning-protocol.mdbefore starting
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
fix-parallel
[Implementation] Analyze & fix issues with parallel fullstack-developer agents
ask
[Utilities] Answer technical and architectural questions.
claude-code
[Utilities] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.
workflow-deployment
[Workflow] Trigger Deployment & Infrastructure workflow — CI/CD pipelines, Docker, Kubernetes setup and deployment.
workflow-idea-to-pbi
[Workflow] Trigger Idea to PBI workflow — po/ba workflow: capture idea, refine to pbi, create stories, prioritize.
easy-claude-help
[Utilities] Configuration guide for the easy-claude framework — explain settings, guide users through configuring .ck.json.
Didn't find tool you were looking for?