Command Guide Skill

Comprehensive command guide for Claude DMS3 workflow system covering 69 commands across 4 categories (workflow, cli, memory, task).

🧠 Core Principle: Intelligent Integration

⚠️ IMPORTANT: This SKILL provides reference materials for intelligent integration, NOT templates for direct copying.

Response Strategy:

1. Analyze user's specific context - Understand their exact need, workflow stage, and technical level
2. Extract relevant information - Select only the pertinent parts from reference guides
3. Synthesize and customize - Combine multiple sources, add context-specific examples
4. Deliver targeted response - Provide concise, actionable guidance tailored to the user's situation

Never:

• ❌ Copy-paste entire template sections verbatim
• ❌ Return raw reference documentation without processing
• ❌ Provide generic responses that ignore user context

Always:

• ✅ Understand the user's specific situation first
• ✅ Integrate information from multiple sources (indexes, guides, reference docs)
• ✅ Customize examples and explanations to match user's use case
• ✅ Provide progressive depth - brief answers with "more detail available" prompts

---

🎯 Operation Modes

Mode 1: Command Search 🔍

When: User searches by keyword, category, or use-case

Triggers: "搜索命令", "find command", "planning 相关", "search"

Process:

1. Identify search type (keyword/category/use-case)
2. Query appropriate index (all-commands/by-category/by-use-case)
3. Intelligently filter and rank results based on user's implied context
4. Synthesize concise response with command names, brief descriptions, and use-case fit
5. Suggest next steps - related commands or workflow patterns

Example: "搜索 planning 命令" → Analyze user's likely goal → Present top 3-5 most relevant planning commands with context-specific usage hints, NOT raw JSON dump

---

Mode 2: Smart Recommendations 🤖

When: User asks for next steps after a command

Triggers: "下一步", "what's next", "after /workflow:plan", "推荐"

Process:

1. Analyze workflow context - Understand where user is in their development cycle
2. Query index/command-relationships.json for possible next commands
3. Evaluate and prioritize recommendations based on:
   • User's stated goals
   • Common workflow patterns
   • Project complexity indicators
4. Craft contextual guidance - Explain WHY each recommendation fits, not just WHAT to run
5. Provide workflow examples - Show complete flow, not isolated commands

Example: "执行完 /workflow:plan 后做什么？" → Analyze plan output quality → Recommend /workflow:action-plan-verify (if complex) OR /workflow:execute (if straightforward) with reasoning for each choice

---

Mode 3: Full Documentation 📖

When: User requests command details

Triggers: "参数说明", "怎么用", "how to use", "详情"

Process:

1. Locate command in index/all-commands.json
2. Read original command file for full details
3. Extract user-relevant sections - Focus on what they asked about (parameters OR examples OR workflow)
4. Enhance with context - Add use-case specific examples if user's scenario is clear
5. Progressive disclosure - Provide core info first, offer "need more details?" prompts

Example: "/workflow:plan 的参数是什么？" → Identify user's experience level → Present parameters with context-appropriate explanations (beginner: verbose + examples; advanced: concise + edge cases), NOT raw documentation dump

---

Mode 4: Beginner Onboarding 🎓

When: New user needs guidance

Triggers: "新手", "getting started", "如何开始", "常用命令"

Process:

1. Assess user background - Ask clarifying questions if needed (coding experience? project type?)
2. Design personalized learning path based on their goals
3. Curate essential commands from index/essential-commands.json - Select 3-5 most relevant for their use case
4. Provide guided first example - Walk through ONE complete workflow with explanation
5. Set clear next steps - What to try next, where to get help

Example: "我是新手，如何开始？" → Detect if they have a specific task OR just exploring → For specific task: provide laser-focused 3-step guide; For exploring: progressive learning path starting with simplest workflow, NOT overwhelming 14-command list

---

Mode 5: Issue Reporting 📝

When: User wants to report issue or request feature

Triggers: "CCW-issue", "CCW-help", "ccw-issue", "ccw-help", "ccw", "报告 bug", "功能建议", "问题咨询", "交互式诊断"

Process:

1. Understand issue context - Use AskUserQuestion to confirm type AND gather initial context
2. Intelligently guide information collection:
   • Adapt questions based on previous answers
   • Skip irrelevant sections
   • Probe for missing critical details
3. Select and customize template:
   • issue-diagnosis.md, issue-bug.md, issue-feature.md, or issue-question.md
   • Adapt template sections to match user's specific scenario
4. Synthesize coherent issue report:
   • Integrate collected information with appropriate template sections
   • Highlight key details - Don't bury critical info in boilerplate
   • Add privacy-protected command history
5. Provide actionable next steps - Immediate troubleshooting OR submission guidance

Example: "CCW-issue" → Detect user frustration level → For urgent: fast-track to critical info collection; For exploratory: comprehensive diagnostic flow, NOT one-size-fits-all questionnaire

🆕 Enhanced Features:

• Complete command history with privacy protection
• Interactive diagnostic checklists
• Decision tree navigation (diagnosis template)
• Execution environment capture

---

Mode 6: Deep Command Analysis 🔬

When: User asks detailed questions about specific commands or agents

Triggers: "详细说明", "命令原理", "agent 如何工作", "实现细节", specific command/agent name mentioned

Data Sources:

• reference/agents/*.md - All agent documentation (11 agents)
• reference/commands/**/*.md - All command documentation (69 commands)

Process:

Simple Query (direct documentation lookup):

1. Identify target command/agent from user query
2. Locate corresponding markdown file in reference/
3. Extract contextually relevant sections - Not entire document
4. Synthesize focused explanation:
   • Address user's specific question
   • Add context-appropriate examples
   • Link related concepts
5. Offer progressive depth - "Want to know more about X?"

Complex Query (CLI-assisted analysis):

1. Detect complexity indicators (多个命令对比、工作流程分析、最佳实践)
2. Design targeted analysis prompt for gemini/qwen:
   • Frame user's question precisely
   • Specify required analysis depth
   • Request structured comparison/synthesis

   gemini -p "
   PURPOSE: Analyze command documentation to answer user query
   TASK: [extracted user question with context]
   MODE: analysis
   CONTEXT: @**/*
   EXPECTED: Comprehensive answer with examples and recommendations
   RULES: $(cat ~/.claude/workflows/cli-templates/prompts/analysis/02-analyze-code-patterns.txt) | Focus on practical usage | analysis=READ-ONLY
   " -m gemini-3-pro-preview-11-2025 --include-directories ~/.claude/skills/command-guide/reference
   

   Note: Use absolute path ~/.claude/skills/command-guide/reference for reference documentation access

3. Process and integrate CLI analysis:
   • Extract key insights from CLI output
   • Add context-specific examples
   • Synthesize actionable recommendations
4. Deliver tailored response - Not raw CLI output

Query Classification:

• Simple: Single command explanation, parameter list, basic usage
• Complex: Cross-command workflows, performance comparison, architectural analysis, best practices across multiple commands

Examples:

Simple Query:

User: "action-planning-agent 如何工作？"
→ Read reference/agents/action-planning-agent.md
→ **Identify user's knowledge gap** (mechanism? inputs/outputs? when to use?)
→ **Extract relevant sections** addressing their need
→ **Synthesize focused explanation** with examples
→ NOT: Dump entire agent documentation

Complex Query:

User: "对比 workflow:plan 和 workflow:tdd-plan 的使用场景和最佳实践"
→ Detect: 多命令对比 + 最佳实践
→ **Design comparison framework** (when to use, trade-offs, workflow integration)
→ Use gemini to analyze both commands with structured comparison prompt
→ **Synthesize insights** into decision matrix and usage guidelines
→ NOT: Raw command documentation side-by-side

---

📚 Index Files

All command metadata is stored in JSON indexes for fast querying:

• all-commands.json - Complete catalog (69 commands) with full metadata
• by-category.json - Hierarchical organization (workflow/cli/memory/task)
• by-use-case.json - Grouped by scenario (planning/implementation/testing/docs/session)
• essential-commands.json - Top 14 most-used commands
• command-relationships.json - Next-step recommendations and dependencies

📖 Detailed structure: Index Structure Reference

---

🗂️ Supporting Guides

• Getting Started - 5-minute quickstart for beginners
• Workflow Patterns - Common workflow examples (Plan→Execute, TDD, UI design)
• CLI Tools Guide - Gemini/Qwen/Codex usage
• Troubleshooting - Common issues and solutions
• Implementation Details - Detailed logic for each mode
• Usage Examples - Example dialogues and edge cases

📦 Reference Documentation

Complete backup of all command and agent documentation for deep analysis:

• reference/agents/ - 11 agent markdown files with implementation details
• reference/commands/ - 69 command markdown files organized by category
  • cli/ - CLI tool commands (9 files)
  • memory/ - Memory management commands (8 files)
  • task/ - Task management commands (4 files)
  • workflow/ - Workflow commands (46 files)

Installation Path: ~/.claude/skills/command-guide/ (skill designed for global installation)

Absolute Reference Path: ~/.claude/skills/command-guide/reference/

Usage: Mode 6 queries these files directly for detailed command/agent analysis, or uses CLI tools (gemini/qwen) with absolute paths for complex cross-command analysis.

---

🛠️ Issue Templates

Generate standardized GitHub issue templates with execution flow emphasis:

• Interactive Diagnosis - 🆕 Comprehensive diagnostic workflow with decision tree, checklists, and full command history
• Bug Report - Report command errors with complete execution flow and environment details
• Feature Request - Suggest improvements with current workflow analysis and pain points
• Question - Ask usage questions with detailed attempt history and context

All templates now include:

• ✅ Complete command history sections (with privacy protection)
• ✅ Execution environment details
• ✅ Interactive problem-locating checklists
• ✅ Structured troubleshooting guidance

Templates are auto-populated during Mode 5 (Issue Reporting) interaction.

---

📊 System Statistics

• Total Commands: 69
• Total Agents: 11
• Categories: 4 (workflow: 46, cli: 9, memory: 8, task: 4, general: 2)
• Use Cases: 5 (planning, implementation, testing, documentation, session-management)
• Difficulty Levels: 3 (Beginner, Intermediate, Advanced)
• Essential Commands: 14
• Reference Docs: 80 markdown files (11 agents + 69 commands)

---

🔧 Maintenance

Updating Indexes

When commands are added/modified/removed:

bash scripts/update-index.sh

This script:

1. Scans all command files in ../../commands/
2. Extracts metadata from YAML frontmatter
3. Analyzes command relationships
4. Regenerates all 5 index files

Committing Updates

git add .claude/skills/command-guide/index/
git commit -m "docs: update command indexes"
git push

Team members get latest indexes via git pull.

---

📖 Related Documentation

• Workflow Architecture - System design overview
• Intelligent Tools Strategy - CLI tool selection
• Context Search Strategy - Search patterns
• Task Core - Task system fundamentals

---

Version: 1.3.1 (Path configuration for global installation) Last Updated: 2025-11-06 Maintainer: Claude DMS3 Team

Changelog v1.3.1:

• ✅ Updated all paths to use absolute paths (~/.claude/skills/command-guide/)
• ✅ CLI commands now use --include-directories with absolute reference path
• ✅ Ensures skill works correctly when installed in ~/.claude/skills/

Changelog v1.3.0:

• ✅ Added Mode 6: Deep Command Analysis with CLI-assisted queries
• ✅ Created reference documentation backup (80 files: 11 agents + 69 commands)
• ✅ Support simple queries (direct file lookup) and complex queries (CLI analysis)
• ✅ Integrated gemini/qwen for cross-command analysis and best practices

Changelog v1.2.0:

• ✅ Added Interactive Diagnosis template with decision tree
• ✅ Enhanced all templates with complete command history sections
• ✅ Added privacy protection guidelines for sensitive information
• ✅ Integrated execution flow emphasis across all issue templates