refactor: reorganize memory commands and update brainstorm workflows

Changes:
- Move memory commands to .claude/commands/memory/ directory
- Relocate update-memory-full.md and update-memory-related.md
- Add new docs.md command for documentation workflows
- Update brainstorm commands (api-designer, data-architect, system-architect, ui-designer, ux-expert)
- Remove deprecated workflow/tools/docs.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-16 10:41:38 +08:00
parent 7ac5412c97
commit 4aec163441
8 changed files with 120 additions and 20 deletions

View File

@@ -0,0 +1,828 @@
---
name: docs
description: Documentation planning and orchestration - creates structured documentation tasks for execution
argument-hint: "[path] [--tool <gemini|qwen|codex>] [--mode <full|partial>] [--cli-generate]"
---
# Documentation Workflow (/memory:docs)
## Overview
Lightweight planner that analyzes project structure, decomposes documentation work into tasks, and generates execution plans. Does NOT generate documentation content itself - delegates to doc-generator agent.
**Documentation Output**: All generated documentation is placed in `.workflow/docs/` directory with **mirrored project structure**. For example:
- Source: `src/modules/auth/index.ts` → Docs: `.workflow/docs/src/modules/auth/API.md`
- Source: `lib/core/utils.js` → Docs: `.workflow/docs/lib/core/README.md`
**Two Execution Modes**:
- **Default**: CLI analyzes in `pre_analysis` (MODE=analysis), agent writes docs in `implementation_approach`
- **--cli-generate**: CLI generates docs in `implementation_approach` (MODE=write)
## Path Mirroring Strategy
**Principle**: Documentation structure **mirrors** source code structure.
| Source Path | Documentation Path |
|------------|-------------------|
| `src/modules/auth/index.ts` | `.workflow/docs/src/modules/auth/API.md` |
| `src/modules/auth/middleware/` | `.workflow/docs/src/modules/auth/middleware/README.md` |
| `lib/core/utils.js` | `.workflow/docs/lib/core/API.md` |
| `lib/core/helpers/` | `.workflow/docs/lib/core/helpers/README.md` |
**Benefits**:
- Easy to locate documentation for any source file
- Maintains logical organization
- Clear 1:1 mapping between code and docs
- Supports any project structure (src/, lib/, packages/, etc.)
## Parameters
```bash
/memory:docs [path] [--tool <gemini|qwen|codex>] [--mode <full|partial>] [--cli-generate]
```
- **path**: Target directory (default: current directory)
- Specifies the directory to generate documentation for
- **--mode**: Documentation generation mode (default: full)
- `full`: Complete documentation (modules + project README + ARCHITECTURE + EXAMPLES)
- Level 1: Module tree documentation
- Level 2: Project README.md
- Level 3: ARCHITECTURE.md + EXAMPLES.md + HTTP API (optional)
- `partial`: Module documentation only
- Level 1: Module tree documentation (API.md + README.md)
- Skips project-level documentation
- **--tool**: CLI tool selection (default: gemini)
- `gemini`: Comprehensive documentation, pattern recognition
- `qwen`: Architecture analysis, system design focus
- `codex`: Implementation validation, code quality
- **--cli-generate**: Enable CLI-based documentation generation (optional)
- When enabled: CLI generates docs with MODE=write in implementation_approach
- When disabled (default): CLI analyzes with MODE=analysis in pre_analysis
## Planning Workflow
### Phase 1: Initialize Session
#### Step 1: Create Session and Generate Config
```bash
# Create session structure and initialize config in one step
bash(
# Parse arguments
path="${1:-.}"
tool="gemini"
mode="full"
cli_generate=false
shift
while [[ $# -gt 0 ]]; do
case "$1" in
--tool) tool="$2"; shift 2 ;;
--mode) mode="$2"; shift 2 ;;
--cli-generate) cli_generate=true; shift ;;
*) shift ;;
esac
done
# Detect paths
project_root=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
if [[ "$path" == /* ]] || [[ "$path" == [A-Z]:* ]]; then
target_path="$path"
else
target_path=$(cd "$path" 2>/dev/null && pwd || echo "$PWD/$path")
fi
# Create session
timestamp=$(date +%Y%m%d-%H%M%S)
session="WFS-docs-${timestamp}"
mkdir -p ".workflow/${session}"/{.task,.process,.summaries}
touch ".workflow/.active-${session}"
# Generate single config file with all info
cat > ".workflow/${session}/.process/config.json" <<EOF
{
"session_id": "${session}",
"timestamp": "$(date -Iseconds)",
"path": "${path}",
"target_path": "${target_path}",
"project_root": "${project_root}",
"mode": "${mode}",
"tool": "${tool}",
"cli_generate": ${cli_generate}
}
EOF
echo "✓ Session initialized: ${session}"
echo "✓ Target: ${target_path}"
echo "✓ Mode: ${mode}"
echo "✓ Tool: ${tool}, CLI generate: ${cli_generate}"
)
```
**Output**:
```
✓ Session initialized: WFS-docs-20240120-143022
✓ Target: /d/Claude_dms3
✓ Mode: full
✓ Tool: gemini, CLI generate: false
```
### Phase 2: Analyze Structure
#### Step 1: Discover and Classify Folders
```bash
# Run analysis pipeline (module discovery + folder classification)
bash(~/.claude/scripts/get_modules_by_depth.sh | ~/.claude/scripts/classify-folders.sh > .workflow/WFS-docs-20240120/.process/folder-analysis.txt)
```
**Output Sample** (folder-analysis.txt):
```
./src/modules/auth|code|code:5|dirs:2
./src/modules/api|code|code:3|dirs:0
./src/utils|navigation|code:0|dirs:4
```
#### Step 2: Extract Top-Level Directories
```bash
# Group folders by top-level directory
bash(awk -F'|' '{
path = $1
gsub(/^\.\//, "", path)
split(path, parts, "/")
if (length(parts) >= 2) print parts[1] "/" parts[2]
else if (length(parts) == 1 && parts[1] != ".") print parts[1]
}' .workflow/WFS-docs-20240120/.process/folder-analysis.txt | sort -u > .workflow/WFS-docs-20240120/.process/top-level-dirs.txt)
```
**Output** (top-level-dirs.txt):
```
src/modules
src/utils
lib/core
```
#### Step 3: Generate Analysis Summary
```bash
# Calculate statistics
bash(
total=$(wc -l < .workflow/WFS-docs-20240120/.process/folder-analysis.txt)
code_count=$(grep '|code|' .workflow/WFS-docs-20240120/.process/folder-analysis.txt | wc -l)
nav_count=$(grep '|navigation|' .workflow/WFS-docs-20240120/.process/folder-analysis.txt | wc -l)
top_dirs=$(wc -l < .workflow/WFS-docs-20240120/.process/top-level-dirs.txt)
echo "📊 Folder Analysis Complete:"
echo " - Total folders: $total"
echo " - Code folders: $code_count"
echo " - Navigation folders: $nav_count"
echo " - Top-level dirs: $top_dirs"
)
# Update config with statistics
bash(jq '. + {analysis: {total: "15", code: "8", navigation: "7", top_level: "3"}}' .workflow/WFS-docs-20240120/.process/config.json > .workflow/WFS-docs-20240120/.process/config.json.tmp && mv .workflow/WFS-docs-20240120/.process/config.json.tmp .workflow/WFS-docs-20240120/.process/config.json)
```
### Phase 3: Detect Update Mode
#### Step 1: Count Existing Documentation in .workflow/docs/
```bash
# Check .workflow/docs/ directory and count existing files
bash(if [[ -d ".workflow/docs" ]]; then
find .workflow/docs -name "*.md" 2>/dev/null | wc -l
else
echo "0"
fi)
```
**Output**: `5` (existing docs in .workflow/docs/)
#### Step 2: List Existing Documentation
```bash
# List existing files in .workflow/docs/ (for task context)
bash(if [[ -d ".workflow/docs" ]]; then
find .workflow/docs -name "*.md" 2>/dev/null > .workflow/WFS-docs-20240120/.process/existing-docs.txt
else
touch .workflow/WFS-docs-20240120/.process/existing-docs.txt
fi)
```
**Output** (existing-docs.txt):
```
.workflow/docs/src/modules/auth/API.md
.workflow/docs/src/modules/auth/README.md
.workflow/docs/lib/core/README.md
.workflow/docs/README.md
```
#### Step 3: Update Config with Update Status
```bash
# Determine update status (create or update) and update config
bash(
existing_count=$(find .workflow/docs -name "*.md" 2>/dev/null | wc -l)
if [[ $existing_count -gt 0 ]]; then
jq ". + {update_mode: \"update\", existing_docs: $existing_count}" .workflow/WFS-docs-20240120/.process/config.json > .workflow/WFS-docs-20240120/.process/config.json.tmp && mv .workflow/WFS-docs-20240120/.process/config.json.tmp .workflow/WFS-docs-20240120/.process/config.json
else
jq '. + {update_mode: "create", existing_docs: 0}' .workflow/WFS-docs-20240120/.process/config.json > .workflow/WFS-docs-20240120/.process/config.json.tmp && mv .workflow/WFS-docs-20240120/.process/config.json.tmp .workflow/WFS-docs-20240120/.process/config.json
fi
)
# Display strategy summary
bash(
mode=$(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json)
update_mode=$(jq -r '.update_mode' .workflow/WFS-docs-20240120/.process/config.json)
existing=$(jq -r '.existing_docs' .workflow/WFS-docs-20240120/.process/config.json)
tool=$(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json)
cli_gen=$(jq -r '.cli_generate' .workflow/WFS-docs-20240120/.process/config.json)
echo "📋 Documentation Strategy:"
echo " - Path: $(jq -r '.target_path' .workflow/WFS-docs-20240120/.process/config.json)"
echo " - Mode: $mode ($([ "$mode" = "full" ] && echo "complete docs" || echo "modules only"))"
echo " - Update: $update_mode ($existing existing files)"
echo " - Tool: $tool, CLI generate: $cli_gen"
)
```
### Phase 4: Decompose Tasks
#### Task Hierarchy
```
Level 1: Module Trees (always, parallel execution)
├─ IMPL-001: Document 'src/modules/'
├─ IMPL-002: Document 'src/utils/'
└─ IMPL-003: Document 'lib/'
Level 2: Project README (mode=full only, depends on Level 1)
└─ IMPL-004: Generate Project README
Level 3: Architecture & Examples (mode=full only, depends on Level 2)
├─ IMPL-005: Generate ARCHITECTURE.md + EXAMPLES.md
└─ IMPL-006: Generate HTTP API (optional)
```
#### Step 1: Generate Level 1 Tasks (Module Trees)
```bash
# Read top-level directories and create tasks
bash(
task_count=0
while read -r top_dir; do
task_count=$((task_count + 1))
task_id=$(printf "IMPL-%03d" $task_count)
echo "Creating $task_id for '$top_dir'"
# Generate task JSON (see Task Templates section)
done < .workflow/WFS-docs-20240120/.process/top-level-dirs.txt
)
```
**Output**:
```
Creating IMPL-001 for 'src/modules'
Creating IMPL-002 for 'src/utils'
Creating IMPL-003 for 'lib'
```
#### Step 2: Generate Level 2-3 Tasks (Full Mode Only)
```bash
# Check documentation mode
bash(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json)
# If full mode, create project-level tasks
bash(
mode=$(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json)
if [[ "$mode" == "full" ]]; then
echo "Creating IMPL-004: Project README"
echo "Creating IMPL-005: ARCHITECTURE.md + EXAMPLES.md"
# Optional: Check for HTTP API endpoints
if grep -r "router\.|@Get\|@Post" src/ >/dev/null 2>&1; then
echo "Creating IMPL-006: HTTP API docs"
fi
else
echo "Partial mode: Skipping project-level tasks"
fi
)
```
### Phase 5: Generate Task JSONs
#### Step 1: Extract Configuration
```bash
# Read config values from JSON
bash(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json)
bash(jq -r '.cli_generate' .workflow/WFS-docs-20240120/.process/config.json)
```
**Output**: `tool=gemini`, `cli_generate=false`
#### Step 2: Determine CLI Command Strategy
```bash
# Determine MODE and placement based on cli_generate flag
bash(
cli_generate=$(jq -r '.cli_generate' .workflow/WFS-docs-20240120/.process/config.json)
if [[ "$cli_generate" == "true" ]]; then
echo "mode=write"
echo "placement=implementation_approach"
echo "approval_flag=--approval-mode yolo"
else
echo "mode=analysis"
echo "placement=pre_analysis"
echo "approval_flag="
fi
)
```
**Output**:
```
mode=analysis
placement=pre_analysis
approval_flag=
```
#### Step 3: Build Tool-Specific Commands
```bash
# Generate command templates based on tool selection
bash(
tool=$(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json)
if [[ "$tool" == "codex" ]]; then
echo "codex -C \${dir} --full-auto exec \"...\" --skip-git-repo-check -s danger-full-access"
else
echo "bash(cd \${dir} && ~/.claude/scripts/${tool}-wrapper ${approval_flag} -p \"...\")"
fi
)
```
## Task Templates
### Level 1: Module Tree Task
**Path Mapping**: Source `src/modules/` → Output `.workflow/docs/src/modules/`
**Default Mode (cli_generate=false)**:
```json
{
"id": "IMPL-001",
"title": "Document Module Tree: 'src/modules/'",
"status": "pending",
"meta": {
"type": "docs-tree",
"agent": "@doc-generator",
"tool": "gemini",
"cli_generate": false,
"source_path": "src/modules",
"output_path": ".workflow/docs/src/modules"
},
"context": {
"requirements": [
"Analyze source code in src/modules/",
"Generate docs to .workflow/docs/src/modules/ (mirrored structure)",
"For code folders: generate API.md + README.md",
"For navigation folders: generate README.md only"
],
"focus_paths": ["src/modules"],
"folder_analysis_file": "${session_dir}/.process/folder-analysis.txt"
},
"flow_control": {
"pre_analysis": [
{
"step": "load_existing_docs",
"command": "bash(find .workflow/docs/${top_dir} -name '*.md' 2>/dev/null | xargs cat || echo 'No existing docs')",
"output_to": "existing_module_docs"
},
{
"step": "load_folder_analysis",
"command": "bash(grep '^src/modules' ${session_dir}/.process/folder-analysis.txt)",
"output_to": "target_folders"
},
{
"step": "analyze_module_tree",
"command": "bash(cd src/modules && ~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze module structure\\nTASK: Generate documentation outline\\nMODE: analysis\\nCONTEXT: @{**/*} [target_folders]\\nEXPECTED: Structure outline\\nRULES: Analyze only\")",
"output_to": "tree_outline",
"note": "CLI for analysis only"
}
],
"implementation_approach": [
{
"step": 1,
"title": "Generate module tree documentation",
"description": "Analyze source folders and generate docs to .workflow/docs/ with mirrored structure",
"modification_points": [
"Parse folder types from [target_folders]",
"Parse structure from [tree_outline]",
"For src/modules/auth/ → write to .workflow/docs/src/modules/auth/",
"Generate API.md for code folders",
"Generate README.md for all folders"
],
"logic_flow": [
"Parse [target_folders] to get folder types",
"Parse [tree_outline] for structure",
"For each folder in source:",
" - Map source_path to .workflow/docs/{source_path}",
" - If type == 'code': Generate API.md + README.md",
" - Elif type == 'navigation': Generate README.md only"
],
"depends_on": [],
"output": "module_docs"
}
],
"target_files": [
".workflow/docs/${top_dir}/*/API.md",
".workflow/docs/${top_dir}/*/README.md"
]
}
}
```
**CLI Generate Mode (cli_generate=true)**:
```json
{
"id": "IMPL-001",
"title": "Document Module Tree: 'src/modules/'",
"status": "pending",
"meta": {
"type": "docs-tree",
"agent": "@doc-generator",
"tool": "gemini",
"cli_generate": true,
"source_path": "src/modules",
"output_path": ".workflow/docs/src/modules"
},
"context": {
"requirements": [
"Analyze source code in src/modules/",
"Generate docs to .workflow/docs/src/modules/ (mirrored structure)",
"CLI generates documentation files directly"
],
"focus_paths": ["src/modules"]
},
"flow_control": {
"pre_analysis": [
{
"step": "load_existing_docs",
"command": "bash(find .workflow/docs/${top_dir} -name '*.md' 2>/dev/null | xargs cat || echo 'No existing docs')",
"output_to": "existing_module_docs"
},
{
"step": "load_folder_analysis",
"command": "bash(grep '^src/modules' ${session_dir}/.process/folder-analysis.txt)",
"output_to": "target_folders"
}
],
"implementation_approach": [
{
"step": 1,
"title": "Parse folder analysis",
"description": "Parse [target_folders] to get folder types and structure",
"modification_points": ["Extract folder types", "Identify code vs navigation folders"],
"logic_flow": ["Parse [target_folders] to get folder types", "Prepare folder list for CLI generation"],
"depends_on": [],
"output": "folder_types"
},
{
"step": 2,
"title": "Generate documentation via CLI",
"description": "Call CLI to generate docs to .workflow/docs/ with mirrored structure using MODE=write",
"modification_points": [
"Execute CLI generation command",
"Generate files to .workflow/docs/src/modules/ (mirrored path)",
"Generate API.md and README.md files"
],
"logic_flow": [
"CLI analyzes source code in src/modules/",
"CLI writes documentation to .workflow/docs/src/modules/",
"Maintains directory structure mirroring"
],
"command": "bash(cd src/modules && ~/.claude/scripts/gemini-wrapper --approval-mode yolo -p \"PURPOSE: Generate module docs\\nTASK: Create documentation files in .workflow/docs/src/modules/\\nMODE: write\\nCONTEXT: @{**/*} [target_folders] [existing_module_docs]\\nEXPECTED: API.md and README.md in .workflow/docs/src/modules/\\nRULES: Mirror source structure, generate complete docs\")",
"depends_on": [1],
"output": "generated_docs"
}
],
"target_files": [
".workflow/docs/${top_dir}/*/API.md",
".workflow/docs/${top_dir}/*/README.md"
]
}
}
```
### Level 2: Project README Task
**Default Mode**:
```json
{
"id": "IMPL-004",
"title": "Generate Project README",
"status": "pending",
"depends_on": ["IMPL-001", "IMPL-002", "IMPL-003"],
"meta": {
"type": "docs",
"agent": "@doc-generator",
"tool": "gemini",
"cli_generate": false
},
"flow_control": {
"pre_analysis": [
{
"step": "load_existing_readme",
"command": "bash(cat .workflow/docs/README.md 2>/dev/null || echo 'No existing README')",
"output_to": "existing_readme"
},
{
"step": "load_module_docs",
"command": "bash(find .workflow/docs -type f -name '*.md' ! -path '.workflow/docs/README.md' ! -path '.workflow/docs/ARCHITECTURE.md' ! -path '.workflow/docs/EXAMPLES.md' ! -path '.workflow/docs/api/*' | xargs cat)",
"output_to": "all_module_docs",
"note": "Load all module docs from mirrored structure"
},
{
"step": "analyze_project",
"command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze project structure\\nTASK: Extract overview from modules\\nMODE: analysis\\nCONTEXT: [all_module_docs]\\nEXPECTED: Project outline\")",
"output_to": "project_outline"
}
],
"implementation_approach": [
{
"step": 1,
"title": "Generate project README",
"description": "Generate project README with navigation links while preserving existing user modifications",
"modification_points": ["Parse [project_outline] and [all_module_docs]", "Generate project README structure", "Add navigation links to modules", "Preserve [existing_readme] user modifications"],
"logic_flow": ["Parse [project_outline] and [all_module_docs]", "Generate project README with navigation links", "Preserve [existing_readme] user modifications"],
"depends_on": [],
"output": "project_readme"
}
],
"target_files": [".workflow/docs/README.md"]
}
}
```
### Level 3: Architecture & Examples Documentation Task
**Default Mode**:
```json
{
"id": "IMPL-005",
"title": "Generate Architecture & Examples Documentation",
"status": "pending",
"depends_on": ["IMPL-004"],
"meta": {
"type": "docs",
"agent": "@doc-generator",
"tool": "gemini",
"cli_generate": false
},
"flow_control": {
"pre_analysis": [
{
"step": "load_existing_docs",
"command": "bash(cat .workflow/docs/ARCHITECTURE.md 2>/dev/null || echo 'No existing ARCHITECTURE'; echo '---SEPARATOR---'; cat .workflow/docs/EXAMPLES.md 2>/dev/null || echo 'No existing EXAMPLES')",
"output_to": "existing_arch_examples"
},
{
"step": "load_all_docs",
"command": "bash(cat .workflow/docs/README.md && find .workflow/docs -type f -name '*.md' ! -path '.workflow/docs/README.md' ! -path '.workflow/docs/ARCHITECTURE.md' ! -path '.workflow/docs/EXAMPLES.md' ! -path '.workflow/docs/api/*' | xargs cat)",
"output_to": "all_docs",
"note": "Load README + all module docs from mirrored structure"
},
{
"step": "analyze_architecture_and_examples",
"command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Analyze system architecture and generate examples\\nTASK: Synthesize architectural overview and usage patterns\\nMODE: analysis\\nCONTEXT: [all_docs]\\nEXPECTED: Architecture outline + Examples outline\")",
"output_to": "arch_examples_outline"
}
],
"implementation_approach": [
{
"step": 1,
"title": "Generate architecture and examples documentation",
"description": "Generate ARCHITECTURE.md and EXAMPLES.md while preserving existing user modifications",
"modification_points": [
"Parse [arch_examples_outline] and [all_docs]",
"Generate ARCHITECTURE.md structure with system design and patterns",
"Generate EXAMPLES.md structure with code snippets and usage examples",
"Preserve [existing_arch_examples] user modifications"
],
"logic_flow": [
"Parse [arch_examples_outline] and [all_docs]",
"Generate ARCHITECTURE.md with system design",
"Generate EXAMPLES.md with code snippets",
"Preserve [existing_arch_examples] modifications"
],
"depends_on": [],
"output": "arch_examples_docs"
}
],
"target_files": [
".workflow/docs/ARCHITECTURE.md",
".workflow/docs/EXAMPLES.md"
]
}
}
```
### Level 3: HTTP API Documentation Task (Optional)
**Default Mode**:
```json
{
"id": "IMPL-006",
"title": "Generate HTTP API Documentation",
"status": "pending",
"depends_on": ["IMPL-004"],
"meta": {
"type": "docs",
"agent": "@doc-generator",
"tool": "gemini",
"cli_generate": false
},
"flow_control": {
"pre_analysis": [
{
"step": "discover_api_endpoints",
"command": "mcp__code-index__search_code_advanced(pattern='router\\.|@(Get|Post)', file_pattern='*.{ts,js}')",
"output_to": "endpoint_discovery"
},
{
"step": "load_existing_api_docs",
"command": "bash(cat .workflow/docs/api/README.md 2>/dev/null || echo 'No existing API docs')",
"output_to": "existing_api_docs"
},
{
"step": "analyze_api",
"command": "bash(~/.claude/scripts/gemini-wrapper -p \"PURPOSE: Document HTTP API\\nTASK: Analyze API endpoints\\nMODE: analysis\\nCONTEXT: @{src/api/**/*} [endpoint_discovery]\\nEXPECTED: API outline\")",
"output_to": "api_outline"
}
],
"implementation_approach": [
{
"step": 1,
"title": "Generate HTTP API documentation",
"description": "Generate HTTP API documentation while preserving existing user modifications",
"modification_points": ["Parse [api_outline] and [endpoint_discovery]", "Generate HTTP API documentation", "Document endpoints and request/response formats", "Preserve [existing_api_docs] modifications"],
"logic_flow": ["Parse [api_outline] and [endpoint_discovery]", "Generate HTTP API documentation", "Preserve [existing_api_docs] modifications"],
"depends_on": [],
"output": "api_docs"
}
],
"target_files": [".workflow/docs/api/README.md"]
}
}
```
## Session Structure
```
.workflow/
├── .active-WFS-docs-20240120-143022 # Active session marker
└── WFS-docs-20240120-143022/
├── IMPL_PLAN.md # Implementation plan
├── TODO_LIST.md # Progress tracker
├── .process/
│ ├── config.json # Single config (all settings + stats)
│ ├── folder-analysis.txt # Folder classification results
│ ├── top-level-dirs.txt # Top-level directory list
│ └── existing-docs.txt # Existing documentation paths
└── .task/
├── IMPL-001.json # Module tree task
├── IMPL-002.json # Module tree task
├── IMPL-003.json # Module tree task
├── IMPL-004.json # Project README (full mode)
├── IMPL-005.json # ARCHITECTURE.md + EXAMPLES.md (full mode)
└── IMPL-006.json # HTTP API docs (optional)
```
**Config File Structure** (config.json):
```json
{
"session_id": "WFS-docs-20240120-143022",
"timestamp": "2024-01-20T14:30:22+08:00",
"path": ".",
"target_path": "/d/Claude_dms3",
"project_root": "/d/Claude_dms3",
"mode": "full",
"tool": "gemini",
"cli_generate": false,
"update_mode": "update",
"existing_docs": 5,
"analysis": {
"total": "15",
"code": "8",
"navigation": "7",
"top_level": "3"
}
}
```
## Generated Documentation
**Structure mirrors project source directories**:
```
.workflow/docs/
├── src/ # Mirrors src/ directory
│ ├── modules/ # Level 1 output
│ │ ├── README.md # Navigation for src/modules/
│ │ ├── auth/
│ │ │ ├── API.md # Auth module API signatures
│ │ │ ├── README.md # Auth module documentation
│ │ │ └── middleware/
│ │ │ ├── API.md # Middleware API
│ │ │ └── README.md # Middleware docs
│ │ └── api/
│ │ ├── API.md # API module signatures
│ │ └── README.md # API module docs
│ └── utils/ # Level 1 output
│ └── README.md # Utils navigation
├── lib/ # Mirrors lib/ directory
│ └── core/
│ ├── API.md
│ └── README.md
├── README.md # Level 2 output (root only)
├── ARCHITECTURE.md # Level 3 output (root only)
├── EXAMPLES.md # Level 3 output (root only)
└── api/ # Level 3 output (optional)
└── README.md # HTTP API reference
```
## Execution Commands
### Full Mode (--mode full)
```bash
# Level 1 - Module documentation (parallel)
/workflow:execute IMPL-001
/workflow:execute IMPL-002
/workflow:execute IMPL-003
# Level 2 - Project README (after Level 1)
/workflow:execute IMPL-004
# Level 3 - Architecture & Examples (after Level 2)
/workflow:execute IMPL-005 # ARCHITECTURE.md + EXAMPLES.md
/workflow:execute IMPL-006 # HTTP API (if present)
```
### Partial Mode (--mode partial)
```bash
# Only Level 1 tasks generated (module documentation)
/workflow:execute IMPL-001
/workflow:execute IMPL-002
/workflow:execute IMPL-003
```
## Simple Bash Commands
### Session Management
```bash
# Create session and initialize config (all in one)
bash(
session="WFS-docs-$(date +%Y%m%d-%H%M%S)"
mkdir -p ".workflow/${session}"/{.task,.process,.summaries}
touch ".workflow/.active-${session}"
cat > ".workflow/${session}/.process/config.json" <<EOF
{"session_id":"${session}","timestamp":"$(date -Iseconds)","path":".","mode":"full","tool":"gemini","cli_generate":false}
EOF
echo "Session: ${session}"
)
# Read session config
bash(cat .workflow/WFS-docs-20240120/.process/config.json)
# Extract config values
bash(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json)
bash(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json)
# List session tasks
bash(ls .workflow/WFS-docs-20240120/.task/*.json)
```
### Analysis Commands
```bash
# Discover and classify folders (scans project source)
bash(~/.claude/scripts/get_modules_by_depth.sh | ~/.claude/scripts/classify-folders.sh)
# Count existing docs (in .workflow/docs/ directory)
bash(if [[ -d ".workflow/docs" ]]; then find .workflow/docs -name "*.md" 2>/dev/null | wc -l; else echo "0"; fi)
# List existing documentation (in .workflow/docs/ directory)
bash(if [[ -d ".workflow/docs" ]]; then find .workflow/docs -name "*.md" 2>/dev/null; fi)
```
## Template Reference
**Available Templates**:
- `api.txt`: Unified template for Code API (Part A) and HTTP API (Part B)
- `module-readme.txt`: Module purpose, usage, dependencies
- `folder-navigation.txt`: Navigation README for folders with subdirectories
- `project-readme.txt`: Project overview, getting started, module navigation
- `project-architecture.txt`: System structure, module map, design patterns
- `project-examples.txt`: End-to-end usage examples
**Template Location**: `~/.claude/workflows/cli-templates/prompts/documentation/`
## CLI Generate Mode Summary
| Mode | CLI Placement | CLI MODE | Agent Role |
|------|---------------|----------|------------|
| **Default** | pre_analysis | analysis | Generates documentation files |
| **--cli-generate** | implementation_approach | write | Validates and coordinates CLI output |
## Related Commands
- `/workflow:execute` - Execute documentation tasks
- `/workflow:status` - View task progress
- `/workflow:session:complete` - Mark session complete

View File

@@ -0,0 +1,330 @@
---
name: update-full
description: Complete project-wide CLAUDE.md documentation update
argument-hint: "[--tool gemini|qwen|codex] [--path <directory>]"
---
# Full Documentation Update (/memory:update-full)
## Coordinator Role
**This command orchestrates project-wide CLAUDE.md updates** using depth-parallel execution strategy with intelligent complexity detection.
**Execution Model**:
1. **Initial Analysis**: Cache git changes, discover module structure
2. **Complexity Detection**: Analyze module count, determine strategy
3. **Plan Presentation**: Show user exactly what will be updated
4. **Depth-Parallel Execution**: Update modules by depth (highest to lowest)
5. **Safety Verification**: Ensure only CLAUDE.md files modified
**Tool Selection**:
- `--tool gemini` (default): Documentation generation, pattern recognition
- `--tool qwen`: Architecture analysis, system design docs
- `--tool codex`: Implementation validation, code quality analysis
**Path Parameter**:
- `--path <directory>` (optional): Target specific directory for updates
- If not specified: Updates entire project from current directory
- If specified: Changes to target directory before discovery
## Core Rules
1. **Analyze First**: Run git cache and module discovery before any updates
2. **Scope Control**: Use --path to target specific directories, default is entire project
3. **Wait for Approval**: Present plan, no execution without user confirmation
4. **Depth-Parallel**: Same depth runs parallel (max 4 jobs), different depths sequential
5. **Safety Check**: Verify only CLAUDE.md files modified, revert if source files touched
6. **Independent Commands**: Each update is a separate bash() call
7. **No Background Bash Tool**: Never use `run_in_background` parameter in bash() calls; use shell `&` for parallelism
## Execution Workflow
### Phase 1: Discovery & Analysis
**Cache git changes:**
```bash
bash(git add -A 2>/dev/null || true)
```
**Get module structure:**
*If no --path parameter:*
```bash
bash(~/.claude/scripts/get_modules_by_depth.sh list)
```
*If --path parameter specified:*
```bash
bash(cd <target-path> && ~/.claude/scripts/get_modules_by_depth.sh list)
```
**Example with path:**
```bash
# Update only .claude directory
bash(cd .claude && ~/.claude/scripts/get_modules_by_depth.sh list)
# Update specific feature directory
bash(cd src/features/auth && ~/.claude/scripts/get_modules_by_depth.sh list)
```
**Parse Output**:
- Extract module paths from `depth:N|path:<PATH>|...` format
- Count total modules
- Identify which modules have/need CLAUDE.md
**Example output:**
```
depth:5|path:./.claude/workflows/cli-templates/prompts/analysis|files:5|has_claude:no
depth:4|path:./.claude/commands/cli/mode|files:3|has_claude:no
depth:3|path:./.claude/commands/cli|files:6|has_claude:no
depth:0|path:.|files:14|has_claude:yes
```
**Validation**:
- If --path specified, directory exists and is accessible
- Module list contains depth and path information
- At least one module exists
- All paths are relative to target directory (if --path used)
---
### Phase 2: Plan Presentation
**Decision Logic**:
- **Simple projects (≤20 modules)**: Present plan to user, wait for approval
- **Complex projects (>20 modules)**: Delegate to memory-bridge agent
**Plan format:**
```
📋 Update Plan:
Tool: gemini
Total modules: 31
NEW CLAUDE.md files (30):
- ./.claude/workflows/cli-templates/prompts/analysis/CLAUDE.md
- ./.claude/commands/cli/mode/CLAUDE.md
- ... (28 more)
UPDATE existing CLAUDE.md files (1):
- ./CLAUDE.md
⚠️ Confirm execution? (y/n)
```
**User Confirmation Required**: No execution without explicit approval
---
### Phase 3: Depth-Parallel Execution
**Pattern**: Process highest depth first, parallel within depth, sequential across depths.
**Command structure:**
```bash
bash(cd <module-path> && ~/.claude/scripts/update_module_claude.sh "." "full" "<tool>" &)
```
**Example - Depth 5 (8 modules):**
```bash
bash(cd ./.claude/workflows/cli-templates/prompts/analysis && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
```bash
bash(cd ./.claude/workflows/cli-templates/prompts/development && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
```bash
bash(cd ./.claude/workflows/cli-templates/prompts/documentation && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
```bash
bash(cd ./.claude/workflows/cli-templates/prompts/implementation && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
*Wait for depth 5 completion...*
**Example - Depth 4 (7 modules):**
```bash
bash(cd ./.claude/commands/cli/mode && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
```bash
bash(cd ./.claude/commands/workflow/brainstorm && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
*Continue for remaining depths (3 → 2 → 1 → 0)...*
**Execution Rules**:
- Each command is separate bash() call
- Up to 4 concurrent jobs per depth
- Wait for all jobs in current depth before proceeding
- Extract path from `depth:N|path:<PATH>|...` format
- All paths relative to target directory (current dir or --path value)
**Path Context**:
- Without --path: Paths relative to current directory
- With --path: Paths relative to specified target directory
- Module discovery runs in target directory context
---
### Phase 4: Safety Verification
**Check modified files:**
```bash
bash(git diff --cached --name-only | grep -v "CLAUDE.md" || echo "✅ Only CLAUDE.md files modified")
```
**Expected output:**
```
✅ Only CLAUDE.md files modified
```
**If non-CLAUDE.md files detected:**
```
⚠️ Warning: Non-CLAUDE.md files were modified
Modified files: src/index.ts, package.json
→ Run: git restore --staged .
```
**Display final status:**
```bash
bash(git status --short)
```
**Example output:**
```
A .claude/workflows/cli-templates/prompts/analysis/CLAUDE.md
A .claude/commands/cli/mode/CLAUDE.md
M CLAUDE.md
... (30 more files)
```
## Command Pattern Reference
**Single module update:**
```bash
bash(cd <module-path> && ~/.claude/scripts/update_module_claude.sh "." "full" "<tool>" &)
```
**Components**:
- `cd <module-path>` - Navigate to module (from `path:` field)
- `&&` - Ensure cd succeeds
- `update_module_claude.sh` - Update script
- `"."` - Current directory
- `"full"` - Full update mode
- `"<tool>"` - gemini/qwen/codex
- `&` - Background execution
**Path extraction:**
```bash
# From: depth:5|path:./src/auth|files:10|has_claude:no
# Extract: ./src/auth
# Command: bash(cd ./src/auth && ~/.claude/scripts/update_module_claude.sh "." "full" "gemini" &)
```
## Complex Projects Strategy
For projects >20 modules, delegate to memory-bridge agent:
```javascript
Task(
subagent_type="memory-bridge",
description="Complex project full update",
prompt=`
CONTEXT:
- Total modules: ${module_count}
- Tool: ${tool}
- Mode: full
MODULE LIST:
${modules_output}
REQUIREMENTS:
1. Use TodoWrite to track each depth level
2. Process depths N→0 sequentially, max 4 parallel per depth
3. Command: cd "<path>" && update_module_claude.sh "." "full" "${tool}" &
4. Extract path from "depth:N|path:<PATH>|..." format
5. Verify all modules processed
6. Run safety check
7. Display git status
`
)
```
## Error Handling
- **Invalid path parameter**: Report error if --path directory doesn't exist, abort execution
- **Module discovery failure**: Report error, abort execution
- **User declines approval**: Abort execution, no changes made
- **Safety check failure**: Automatic staging revert, report modified files
- **Update script failure**: Report failed modules, continue with remaining
## Coordinator Checklist
✅ Parse `--tool` parameter (default: gemini)
✅ Parse `--path` parameter (optional, default: current directory)
✅ Execute git cache in current directory
✅ Execute module discovery (with cd if --path specified)
✅ Parse module list, count total modules
✅ Determine strategy based on module count (≤20 vs >20)
✅ Present plan with exact file paths
**Wait for user confirmation** (simple projects only)
✅ Organize modules by depth
✅ For each depth (highest to lowest):
- Launch up to 5 parallel updates
- Wait for depth completion
- Proceed to next depth
✅ Run safety check after all updates
✅ Display git status
✅ Report completion summary
## Tool Parameter Reference
**Gemini** (default):
- Best for: Documentation generation, pattern recognition, architecture review
- Context window: Large, handles complex codebases
- Output style: Comprehensive, detailed explanations
**Qwen**:
- Best for: Architecture analysis, system design documentation
- Context window: Large, similar to Gemini
- Output style: Structured, systematic analysis
**Codex**:
- Best for: Implementation validation, code quality analysis
- Capabilities: Mathematical reasoning, autonomous development
- Output style: Technical, implementation-focused
## Path Parameter Reference
**Use Cases**:
**Update configuration directory only:**
```bash
/memory:update-full --path .claude
```
- Updates only .claude directory and subdirectories
- Useful after workflow or command modifications
- Faster than full project update
**Update specific feature module:**
```bash
/memory:update-full --path src/features/auth
```
- Updates authentication feature and sub-modules
- Ideal for feature-specific documentation
- Isolates scope for targeted updates
**Update nested structure:**
```bash
/memory:update-full --path .claude/workflows/cli-templates
```
- Updates deeply nested directory tree
- Maintains relative path structure in output
- All module paths relative to specified directory
**Best Practices**:
- Use `--path` when working on specific features/modules
- Omit `--path` for project-wide architectural changes
- Combine with `--tool` for specialized documentation needs
- Verify directory exists before execution (automatic validation)

View File

@@ -0,0 +1,306 @@
---
name: update-related
description: Context-aware CLAUDE.md documentation updates based on recent changes
argument-hint: "[--tool gemini|qwen|codex]"
---
# Related Documentation Update (/memory:update-related)
## Coordinator Role
**This command orchestrates context-aware CLAUDE.md updates** for modules affected by recent changes using intelligent change detection.
**Execution Model**:
1. **Change Detection**: Analyze git changes to identify affected modules
2. **Complexity Analysis**: Evaluate change count and determine strategy
3. **Plan Presentation**: Show user which modules need updates
4. **Depth-Parallel Execution**: Update affected modules by depth (highest to lowest)
5. **Safety Verification**: Ensure only CLAUDE.md files modified
**Tool Selection**:
- `--tool gemini` (default): Documentation generation, pattern recognition
- `--tool qwen`: Architecture analysis, system design docs
- `--tool codex`: Implementation validation, code quality analysis
## Core Rules
1. **Detect Changes First**: Use git diff to identify affected modules before updates
2. **Wait for Approval**: Present plan, no execution without user confirmation
3. **Related Mode**: Update only changed modules and their parent contexts
4. **Depth-Parallel**: Same depth runs parallel (max 4 jobs), different depths sequential
5. **Safety Check**: Verify only CLAUDE.md files modified, revert if source files touched
6. **No Background Bash Tool**: Never use `run_in_background` parameter in bash() calls; use shell `&` for parallelism
## Execution Workflow
### Phase 1: Change Detection & Analysis
**Refresh code index:**
```bash
bash(mcp__code-index__refresh_index)
```
**Detect changed modules:**
```bash
bash(~/.claude/scripts/detect_changed_modules.sh list)
```
**Cache git changes:**
```bash
bash(git add -A 2>/dev/null || true)
```
**Parse Output**:
- Extract changed module paths from `depth:N|path:<PATH>|...` format
- Count affected modules
- Identify which modules have/need CLAUDE.md updates
**Example output:**
```
depth:3|path:./src/api/auth|files:5|types:[ts]|has_claude:no|change:new
depth:2|path:./src/api|files:12|types:[ts]|has_claude:yes|change:modified
depth:1|path:./src|files:8|types:[ts]|has_claude:yes|change:parent
depth:0|path:.|files:14|has_claude:yes|change:parent
```
**Fallback behavior**:
- If no git changes detected, use recent modules (first 10 by depth)
**Validation**:
- Changed module list contains valid paths
- At least one affected module exists
---
### Phase 2: Plan Presentation
**Decision Logic**:
- **Simple changes (≤15 modules)**: Present plan to user, wait for approval
- **Complex changes (>15 modules)**: Delegate to memory-bridge agent
**Plan format:**
```
📋 Related Update Plan:
Tool: gemini
Changed modules: 4
NEW CLAUDE.md files (1):
- ./src/api/auth/CLAUDE.md [new module]
UPDATE existing CLAUDE.md files (3):
- ./src/api/CLAUDE.md [parent of changed auth/]
- ./src/CLAUDE.md [parent context]
- ./CLAUDE.md [root level]
⚠️ Confirm execution? (y/n)
```
**User Confirmation Required**: No execution without explicit approval
---
### Phase 3: Depth-Parallel Execution
**Pattern**: Process highest depth first, parallel within depth, sequential across depths.
**Command structure:**
```bash
bash(cd <module-path> && ~/.claude/scripts/update_module_claude.sh "." "related" "<tool>" &)
```
**Example - Depth 3 (new module):**
```bash
bash(cd ./src/api/auth && ~/.claude/scripts/update_module_claude.sh "." "related" "gemini" &)
```
*Wait for depth 3 completion...*
**Example - Depth 2 (modified parent):**
```bash
bash(cd ./src/api && ~/.claude/scripts/update_module_claude.sh "." "related" "gemini" &)
```
*Wait for depth 2 completion...*
**Example - Depth 1 & 0 (parent contexts):**
```bash
bash(cd ./src && ~/.claude/scripts/update_module_claude.sh "." "related" "gemini" &)
```
```bash
bash(cd . && ~/.claude/scripts/update_module_claude.sh "." "related" "gemini" &)
```
*Wait for all depths completion...*
**Execution Rules**:
- Each command is separate bash() call
- Up to 4 concurrent jobs per depth
- Wait for all jobs in current depth before proceeding
- Use "related" mode (not "full") for context-aware updates
- Extract path from `depth:N|path:<PATH>|...` format
**Related Mode Behavior**:
- Updates module based on recent git changes
- Includes parent context for better documentation coherence
- More efficient than full updates for iterative development
---
### Phase 4: Safety Verification
**Check modified files:**
```bash
bash(git diff --cached --name-only | grep -v "CLAUDE.md" || echo "✅ Only CLAUDE.md files modified")
```
**Expected output:**
```
✅ Only CLAUDE.md files modified
```
**If non-CLAUDE.md files detected:**
```
⚠️ Warning: Non-CLAUDE.md files were modified
Modified files: src/api/auth/index.ts, package.json
→ Run: git restore --staged .
```
**Display final statistics:**
```bash
bash(git diff --stat)
```
**Example output:**
```
.claude/workflows/cli-templates/prompts/analysis/CLAUDE.md | 45 +++++++++++++++++++++
src/api/CLAUDE.md | 23 +++++++++--
src/CLAUDE.md | 12 ++++--
CLAUDE.md | 8 ++--
4 files changed, 82 insertions(+), 6 deletions(-)
```
## Command Pattern Reference
**Single module update:**
```bash
bash(cd <module-path> && ~/.claude/scripts/update_module_claude.sh "." "related" "<tool>" &)
```
**Components**:
- `cd <module-path>` - Navigate to module (from `path:` field)
- `&&` - Ensure cd succeeds
- `update_module_claude.sh` - Update script
- `"."` - Current directory
- `"related"` - Related mode (context-aware, change-based)
- `"<tool>"` - gemini/qwen/codex
- `&` - Background execution
**Path extraction:**
```bash
# From: depth:3|path:./src/api/auth|files:5|change:new|has_claude:no
# Extract: ./src/api/auth
# Command: bash(cd ./src/api/auth && ~/.claude/scripts/update_module_claude.sh "." "related" "gemini" &)
```
**Mode comparison:**
- `"full"` - Complete module documentation regeneration
- `"related"` - Context-aware update based on recent changes (faster)
## Complex Changes Strategy
For changes affecting >15 modules, delegate to memory-bridge agent:
```javascript
Task(
subagent_type="memory-bridge",
description="Complex project related update",
prompt=`
CONTEXT:
- Total modules: ${change_count}
- Tool: ${tool}
- Mode: related
MODULE LIST:
${changed_modules_output}
REQUIREMENTS:
1. Use TodoWrite to track each depth level
2. Process depths N→0 sequentially, max 4 parallel per depth
3. Command: cd "<path>" && update_module_claude.sh "." "related" "${tool}" &
4. Extract path from "depth:N|path:<PATH>|..." format
5. Verify all ${change_count} modules processed
6. Run safety check
7. Display git diff --stat
`
)
```
## Error Handling
- **No changes detected**: Use fallback mode (recent 10 modules)
- **Change detection failure**: Report error, abort execution
- **User declines approval**: Abort execution, no changes made
- **Safety check failure**: Automatic staging revert, report modified files
- **Update script failure**: Report failed modules, continue with remaining
## Coordinator Checklist
✅ Parse `--tool` parameter (default: gemini)
✅ Refresh code index for accurate change detection
✅ Detect changed modules via detect_changed_modules.sh
✅ Cache git changes to protect current state
✅ Parse changed module list, count affected modules
✅ Apply fallback if no changes detected (recent 10 modules)
✅ Determine strategy based on change count (≤15 vs >15)
✅ Present plan with exact file paths and change types
**Wait for user confirmation** (simple changes only)
✅ Organize modules by depth
✅ For each depth (highest to lowest):
- Launch up to 4 parallel updates with "related" mode
- Wait for depth completion
- Proceed to next depth
✅ Run safety check after all updates
✅ Display git diff statistics
✅ Report completion summary
## Usage Examples
```bash
# Daily development update (default: gemini)
/memory:update-related
# After feature work with specific tool
/memory:update-related --tool qwen
# Code quality review after implementation
/memory:update-related --tool codex
```
## Tool Parameter Reference
**Gemini** (default):
- Best for: Documentation generation, pattern recognition
- Use case: Daily development updates, feature documentation
- Output style: Comprehensive, contextual explanations
**Qwen**:
- Best for: Architecture analysis, system design
- Use case: Structural changes, API design updates
- Output style: Structured, systematic documentation
**Codex**:
- Best for: Implementation validation, code quality
- Use case: After implementation, refactoring work
- Output style: Technical, implementation-focused
## Comparison with Full Update
| Aspect | Related Update | Full Update |
|--------|----------------|-------------|
| **Scope** | Changed modules only | All project modules |
| **Speed** | Fast (minutes) | Slower (10-30 min) |
| **Use case** | Daily development | Major refactoring |
| **Mode** | `"related"` | `"full"` |
| **Trigger** | After commits | After major changes |
| **Complexity threshold** | ≤15 modules | ≤20 modules |