catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-11 02:33:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: enhance documentation generation process with improved structure and quality guidelines

Browse Source
This commit is contained in:
catlog22
2025-11-03 15:17:37 +08:00
parent cdc0af90ba
commit b18647353b
3 changed files with 339 additions and 277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
.claude/agents/doc-generator.md
View File

@@ -26,6 +26,81 @@ You are an expert technical documentation specialist. Your responsibility is to
- **Template-Based**: You apply specified templates to generate consistent and high-quality documentation. - **Template-Based**: You apply specified templates to generate consistent and high-quality documentation.
- **Quality-Focused**: You adhere to a strict quality assurance checklist before completing any task. - **Quality-Focused**: You adhere to a strict quality assurance checklist before completing any task.
## Documentation Quality Principles
### 1. Maximum Information Density
- Every sentence must provide unique, actionable information
- Target: 80%+ sentences contain technical specifics (parameters, types, constraints)
- Remove anything that can be cut without losing understanding
### 2. Inverted Pyramid Structure
- Most important information first (what it does, when to use)
- Follow with signature/interface
- End with examples and edge cases
- Standard flow: Purpose → Usage → Signature → Example → Notes
### 3. Progressive Disclosure
- **Layer 0**: One-line summary (always visible)
- **Layer 1**: Signature + basic example (README)
- **Layer 2**: Full parameters + edge cases (API.md)
- **Layer 3**: Implementation + architecture (ARCHITECTURE.md)
- Use cross-references instead of duplicating content
### 4. Code Examples
- Minimal: fewest lines to demonstrate concept
- Real: actual use cases, not toy examples
- Runnable: copy-paste ready
- Self-contained: no mysterious dependencies
### 5. Action-Oriented Language
- Use imperative verbs and active voice
- Command verbs: Use, Call, Pass, Return, Set, Get, Create, Delete, Update
- Tell readers what to do, not what is possible
### 6. Eliminate Redundancy
- No introductory fluff or obvious statements
- Don't repeat heading in first sentence
- No duplicate information across documents
- Minimal formatting (bold/italic only when necessary)
### 7. Document-Specific Guidelines
**API.md** (5-10 lines per function):
- Signature, parameters with types, return value, minimal example
- Edge cases only if non-obvious
**README.md** (30-100 lines):
- Purpose (1-2 sentences), when to use, quick start, link to API.md
- No architecture details (link to ARCHITECTURE.md)
**ARCHITECTURE.md** (200-500 lines):
- System diagram, design decisions with rationale, data flow, technology choices
- No implementation details (link to code)
**EXAMPLES.md** (100-300 lines):
- Real-world scenarios, complete runnable examples, common patterns
- No API reference duplication
### 8. Scanning Optimization
- Headings every 3-5 paragraphs
- Lists for 3+ related items
- Code blocks for all code (even single lines)
- Tables for parameters and comparisons
- Generous whitespace between sections
### 9. Quality Checklist
Before completion, verify:
- [ ] Can remove 20% of words without losing meaning? (If yes, do it)
- [ ] 80%+ sentences are technically specific?
- [ ] First paragraph answers "what" and "when"?
- [ ] Reader can find any info in <10 seconds?
- [ ] Most important info in first screen?
- [ ] Examples runnable without modification?
- [ ] No duplicate information across files?
- [ ] No empty or obvious statements?
- [ ] Headings alone convey the flow?
- [ ] All code blocks syntactically highlighted?
## Optimized Execution Model ## Optimized Execution Model
**Key Principle**: Lightweight metadata loading + targeted content analysis **Key Principle**: Lightweight metadata loading + targeted content analysis

354
.claude/commands/memory/docs.md
View File

@@ -65,62 +65,42 @@ Lightweight planner that analyzes project structure, decomposes documentation wo
### Phase 1: Initialize Session ### Phase 1: Initialize Session
#### Step 1: Create Session and Generate Config #### Step 1: Get Target Path and Project Name
```bash ```bash
# Create session structure and initialize config in one step # Get current directory as target path
bash( bash(pwd)
# 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="$2"; shift 2 ;;
--cli-generate) cli_generate=true; shift ;;
*) shift ;;
esac
done
# Detect paths # Get project name from current directory
project_root=$(git rev-parse --show-toplevel 2>/dev/null || pwd) bash(basename "$(pwd)")
if [[ "$path" == /* ]] || [[ "$path" == [A-Z]:* ]]; then
target_path="$path"
else
target_path=$(cd "$path" 2>/dev/null && pwd || echo "$PWD/$path")
fi
# Extract project name from target_path # Get project root from git
project_name=$(basename "$target_path") bash(git rev-parse --show-toplevel 2>/dev/null || pwd)
# Create session # Generate timestamp for session ID
timestamp=$(date +%Y%m%d-%H%M%S) bash(date +%Y%m%d-%H%M%S)
session="WFS-docs-${timestamp}" ```
mkdir -p ".workflow/${session}"/{.task,.process,.summaries}
touch ".workflow/.active-${session}"
# Generate single config file with all info **Output**:
cat > ".workflow/${session}/.process/config.json" <<EOF - `target_path`: `/d/Claude_dms3`
{ - `project_name`: `Claude_dms3`
"session_id": "${session}", - `project_root`: `/d/Claude_dms3`
"timestamp": "$(date -Iseconds)", - `timestamp`: `20240120-143022`
"path": "${path}",
"target_path": "${target_path}",
"project_root": "${project_root}",
"project_name": "${project_name}",
"mode": "${mode}",
"tool": "${tool}",
"cli_generate": ${cli_generate}
}
EOF
echo "✓ Session initialized: ${session}" #### Step 2: Create Session Structure
echo "✓ Target: ${target_path}" ```bash
echo "✓ Mode: ${mode}" # Create session directories (replace timestamp with actual value)
echo "✓ Tool: ${tool}, CLI generate: ${cli_generate}" bash(mkdir -p .workflow/WFS-docs-20240120-143022/.task)
) bash(mkdir -p .workflow/WFS-docs-20240120-143022/.process)
bash(mkdir -p .workflow/WFS-docs-20240120-143022/.summaries)
# Mark session as active
bash(touch .workflow/.active-WFS-docs-20240120-143022)
```
#### Step 3: Create Config File
```bash
# Create config.json with session info (replace values with actual data)
bash(echo '{"session_id":"WFS-docs-20240120-143022","timestamp":"2024-01-20T14:30:22+08:00","path":".","target_path":"/d/Claude_dms3","project_root":"/d/Claude_dms3","project_name":"Claude_dms3","mode":"full","tool":"gemini","cli_generate":false}' | jq '.' > .workflow/WFS-docs-20240120-143022/.process/config.json)
``` ```
**Output**: **Output**:
@@ -195,69 +175,57 @@ bash(jq '. + {analysis: {total: "15", code: "8", navigation: "7", top_level: "3"
### Phase 3: Detect Update Mode ### Phase 3: Detect Update Mode
#### Step 1: Count Existing Documentation in .workflow/docs/{project_name}/ #### Step 1: Get Project Name from Config
```bash ```bash
# Check .workflow/docs/{project_name}/ directory and count existing files # Read project name from config
bash( bash(jq -r '.project_name' .workflow/WFS-docs-20240120-143022/.process/config.json)
project_name=$(jq -r '.project_name' .workflow/WFS-docs-20240120/.process/config.json)
if [[ -d ".workflow/docs/${project_name}" ]]; then
find .workflow/docs/${project_name} -name "*.md" 2>/dev/null | wc -l
else
echo "0"
fi
)
``` ```
**Output**: `5` (existing docs in .workflow/docs/{project_name}/) **Output**: `Claude_dms3`
#### Step 2: List Existing Documentation #### Step 2: Count Existing Documentation
```bash ```bash
# List existing files in .workflow/docs/{project_name}/ (for task context) # Count existing docs (replace project_name with actual value)
bash( bash(find .workflow/docs/Claude_dms3 -name "*.md" 2>/dev/null | wc -l || echo 0)
project_name=$(jq -r '.project_name' .workflow/WFS-docs-20240120/.process/config.json) ```
if [[ -d ".workflow/docs/${project_name}" ]]; then
find .workflow/docs/${project_name} -name "*.md" 2>/dev/null > .workflow/WFS-docs-20240120/.process/existing-docs.txt **Output**: `5` (existing docs) or `0` (no docs)
else
touch .workflow/WFS-docs-20240120/.process/existing-docs.txt #### Step 3: List Existing Documentation Files
fi ```bash
) # List existing docs to file (replace project_name and session)
bash(find .workflow/docs/Claude_dms3 -name "*.md" 2>/dev/null > .workflow/WFS-docs-20240120-143022/.process/existing-docs.txt || touch .workflow/WFS-docs-20240120-143022/.process/existing-docs.txt)
# Display existing docs
bash(cat .workflow/WFS-docs-20240120-143022/.process/existing-docs.txt)
``` ```
**Output** (existing-docs.txt): **Output** (existing-docs.txt):
``` ```
.workflow/docs/my_app/src/modules/auth/API.md .workflow/docs/Claude_dms3/src/modules/auth/API.md
.workflow/docs/my_app/src/modules/auth/README.md .workflow/docs/Claude_dms3/src/modules/auth/README.md
.workflow/docs/my_app/lib/core/README.md .workflow/docs/Claude_dms3/lib/core/README.md
.workflow/docs/my_app/README.md .workflow/docs/Claude_dms3/README.md
``` ```
#### Step 3: Update Config with Update Status #### Step 4: Update Config with Update Status
```bash ```bash
# Determine update status (create or update) and update config # If existing_count > 0, update config with "update" mode (replace session and count)
bash( bash(jq '. + {update_mode: "update", existing_docs: 5}' .workflow/WFS-docs-20240120-143022/.process/config.json > .workflow/WFS-docs-20240120-143022/.process/config.json.tmp && mv .workflow/WFS-docs-20240120-143022/.process/config.json.tmp .workflow/WFS-docs-20240120-143022/.process/config.json)
project_name=$(jq -r '.project_name' .workflow/WFS-docs-20240120/.process/config.json)
existing_count=$(find .workflow/docs/${project_name} -name "*.md" 2>/dev/null | wc -l)
if [[ $existing_count -gt 0 ]]; then
jq ". + {update_mode: \"update\", existing_docs: $existing_count}" .workflow/WFS-docs-20240120/.process/config.json > .workflow/WFS-docs-20240120/.process/config.json.tmp && mv .workflow/WFS-docs-20240120/.process/config.json.tmp .workflow/WFS-docs-20240120/.process/config.json
else
jq '. + {update_mode: "create", existing_docs: 0}' .workflow/WFS-docs-20240120/.process/config.json > .workflow/WFS-docs-20240120/.process/config.json.tmp && mv .workflow/WFS-docs-20240120/.process/config.json.tmp .workflow/WFS-docs-20240120/.process/config.json
fi
)
# Display strategy summary # Or if existing_count = 0, use "create" mode
bash( bash(jq '. + {update_mode: "create", existing_docs: 0}' .workflow/WFS-docs-20240120-143022/.process/config.json > .workflow/WFS-docs-20240120-143022/.process/config.json.tmp && mv .workflow/WFS-docs-20240120-143022/.process/config.json.tmp .workflow/WFS-docs-20240120-143022/.process/config.json)
mode=$(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:" #### Step 5: Display Strategy Summary
echo " - Path: $(jq -r '.target_path' .workflow/WFS-docs-20240120/.process/config.json)" ```bash
echo " - Mode: $mode ($([ "$mode" = "full" ] && echo "complete docs" || echo "modules only"))" # Read config values
echo " - Update: $update_mode ($existing existing files)" bash(jq -r '.mode' .workflow/WFS-docs-20240120-143022/.process/config.json)
echo " - Tool: $tool, CLI generate: $cli_gen" bash(jq -r '.update_mode' .workflow/WFS-docs-20240120-143022/.process/config.json)
) bash(jq -r '.existing_docs' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.tool' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.cli_generate' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.target_path' .workflow/WFS-docs-20240120-143022/.process/config.json)
``` ```
### Phase 4: Decompose Tasks ### Phase 4: Decompose Tasks
@@ -277,98 +245,92 @@ Level 3: Architecture & Examples (mode=full only, depends on Level 2)
└─ IMPL-006: Generate HTTP API (optional) └─ IMPL-006: Generate HTTP API (optional)
``` ```
#### Step 1: Generate Level 1 Tasks (Module Trees) #### Step 1: Read Top-Level Directories
```bash ```bash
# Read top-level directories and create tasks # Read top-level directories list
bash( bash(cat .workflow/WFS-docs-20240120-143022/.process/top-level-dirs.txt)
task_count=0
while read -r top_dir; do
task_count=$((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**: **Output**:
``` ```
Creating IMPL-001 for 'src/modules' src/modules
Creating IMPL-002 for 'src/utils' src/utils
Creating IMPL-003 for 'lib' lib
``` ```
#### Step 2: Generate Level 2-3 Tasks (Full Mode Only) #### Step 2: Count Directories for Task Generation
```bash ```bash
# Check documentation mode # Count how many tasks to create
bash(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json) bash(wc -l < .workflow/WFS-docs-20240120-143022/.process/top-level-dirs.txt)
# 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
)
``` ```
**Output**: `3` (will generate IMPL-001, IMPL-002, IMPL-003)
#### Step 3: Check Documentation Mode
```bash
# Check if full or partial mode
bash(jq -r '.mode' .workflow/WFS-docs-20240120-143022/.process/config.json)
```
**Output**: `full` or `partial`
#### Step 4: Check for HTTP API Endpoints (Optional)
```bash
# Search for API endpoint patterns
bash(grep -r "router\.|@Get\|@Post" src/ 2>/dev/null && echo "API_FOUND" || echo "NO_API")
```
**Output**: `API_FOUND` or `NO_API`
**Task Generation Summary**:
- **Partial mode**: Generate only IMPL-001, IMPL-002, IMPL-003 (module trees)
- **Full mode without API**: Generate IMPL-001 to IMPL-005
- **Full mode with API**: Generate IMPL-001 to IMPL-006
### Phase 5: Generate Task JSONs ### Phase 5: Generate Task JSONs
#### Step 1: Extract Configuration #### Step 1: Read Configuration Values
```bash ```bash
# Read config values from JSON # Read tool selection
bash(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json) bash(jq -r '.tool' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.cli_generate' .workflow/WFS-docs-20240120/.process/config.json)
```
**Output**: `tool=gemini`, `cli_generate=false` # Read cli_generate flag
bash(jq -r '.cli_generate' .workflow/WFS-docs-20240120-143022/.process/config.json)
#### Step 2: Determine CLI Command Strategy # Read mode
```bash bash(jq -r '.mode' .workflow/WFS-docs-20240120-143022/.process/config.json)
# 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**: **Output**:
``` - `tool`: `gemini`
mode=analysis - `cli_generate`: `false`
placement=pre_analysis - `mode`: `full`
approval_flag=
```
#### Step 3: Build Tool-Specific Commands #### Step 2: Determine CLI Strategy
```bash
# Generate command templates based on tool selection
bash(
tool=$(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json)
if [[ "$tool" == "codex" ]]; then **If cli_generate = false**:
echo "codex -C \${dir} --full-auto exec \"...\" --skip-git-repo-check -s danger-full-access" - MODE: `analysis`
else - Placement: `pre_analysis`
echo "bash(cd \${dir} && ${tool} ${approval_flag} -p \"...\")" - Approval flag: (none)
# Direct CLI commands for gemini/qwen - Command pattern: `cd dir && gemini -p "..."`
fi
) **If cli_generate = true**:
``` - MODE: `write`
- Placement: `implementation_approach`
- Approval flag: `--approval-mode yolo`
- Command pattern: `cd dir && gemini --approval-mode yolo -p "..."`
**If tool = codex**:
- Command pattern: `codex -C dir --full-auto exec "..." --skip-git-repo-check -s danger-full-access`
#### Step 3: Generate Task JSON Files
Tasks are generated based on:
- Top-level directories from Phase 4
- Configuration from config.json
- Task templates (see Task Templates section below)
Each task JSON is written to `.workflow/WFS-docs-20240120-143022/.task/IMPL-XXX.json`
## Task Templates ## Task Templates
@@ -782,38 +744,48 @@ bash(
### Session Management ### Session Management
```bash ```bash
# Create session and initialize config (all in one) # Generate timestamp
bash( bash(date +%Y%m%d-%H%M%S)
session="WFS-docs-$(date +%Y%m%d-%H%M%S)"
mkdir -p ".workflow/${session}"/{.task,.process,.summaries} # Create session directories (replace timestamp)
touch ".workflow/.active-${session}" bash(mkdir -p .workflow/WFS-docs-20240120-143022/.task)
cat > ".workflow/${session}/.process/config.json" <<EOF bash(mkdir -p .workflow/WFS-docs-20240120-143022/.process)
{"session_id":"${session}","timestamp":"$(date -Iseconds)","path":".","mode":"full","tool":"gemini","cli_generate":false} bash(mkdir -p .workflow/WFS-docs-20240120-143022/.summaries)
EOF
echo "Session: ${session}" # Mark as active
) bash(touch .workflow/.active-WFS-docs-20240120-143022)
# Get project name
bash(basename "$(pwd)")
# Create config (replace values)
bash(echo '{"session_id":"WFS-docs-20240120-143022","timestamp":"2024-01-20T14:30:22+08:00","path":".","target_path":"/d/project","project_name":"project","mode":"full","tool":"gemini","cli_generate":false}' | jq '.' > .workflow/WFS-docs-20240120-143022/.process/config.json)
# Read session config # Read session config
bash(cat .workflow/WFS-docs-20240120/.process/config.json) bash(cat .workflow/WFS-docs-20240120-143022/.process/config.json)
# Extract config values # Extract config values
bash(jq -r '.tool' .workflow/WFS-docs-20240120/.process/config.json) bash(jq -r '.tool' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.mode' .workflow/WFS-docs-20240120/.process/config.json) bash(jq -r '.mode' .workflow/WFS-docs-20240120-143022/.process/config.json)
bash(jq -r '.project_name' .workflow/WFS-docs-20240120-143022/.process/config.json)
# List session tasks # List session tasks
bash(ls .workflow/WFS-docs-20240120/.task/*.json) bash(ls .workflow/WFS-docs-20240120-143022/.task/*.json)
``` ```
### Analysis Commands ### Analysis Commands
```bash ```bash
# Discover and classify folders (scans project source) # Discover and classify folders
bash(~/.claude/scripts/get_modules_by_depth.sh | ~/.claude/scripts/classify-folders.sh) bash(~/.claude/scripts/get_modules_by_depth.sh | ~/.claude/scripts/classify-folders.sh > .workflow/WFS-docs-20240120-143022/.process/folder-analysis.txt)
# Count existing docs (in .workflow/docs/{project_name}/ directory) # Count existing docs (replace project_name)
bash(if [[ -d ".workflow/docs/${project_name}" ]]; then find .workflow/docs/${project_name} -name "*.md" 2>/dev/null | wc -l; else echo "0"; fi) bash(find .workflow/docs/my_project -name "*.md" 2>/dev/null | wc -l || echo 0)
# List existing documentation (in .workflow/docs/{project_name}/ directory) # List existing documentation (replace project_name)
bash(if [[ -d ".workflow/docs/${project_name}" ]]; then find .workflow/docs/${project_name} -name "*.md" 2>/dev/null; fi) bash(find .workflow/docs/my_project -name "*.md" 2>/dev/null || echo "No docs found")
# Check if docs directory exists
bash(test -d .workflow/docs/my_project && echo "exists" || echo "not exists")
``` ```
## Template Reference ## Template Reference

187
.claude/commands/memory/skill-memory.md
View File

@@ -40,77 +40,61 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Bash(*), Read(*), Write(*)
**Goal**: Parse command arguments and check existing documentation **Goal**: Parse command arguments and check existing documentation
**Actions**: **Step 1: Get Target Path and Project Name**
```bash ```bash
# Parse arguments # Get current directory (or use provided path)
bash( bash(pwd)
path="${1:-.}"
tool="gemini"
regenerate=""
mode="full"
shift
while [[ $# -gt 0 ]]; do
case "$1" in
--tool) tool="$2"; shift 2 ;;
--regenerate) regenerate="--regenerate"; shift ;;
--mode) mode="$2"; shift 2 ;;
*) shift ;;
esac
done
# Detect paths # Get project name from directory
project_root=$(git rev-parse --show-toplevel 2>/dev/null || pwd) bash(basename "$(pwd)")
if [[ "$path" == /* ]] || [[ "$path" == [A-Z]:* ]]; then
target_path="$path"
else
target_path=$(cd "$path" 2>/dev/null && pwd || echo "$PWD/$path")
fi
project_name=$(basename "$target_path") # Get project root
docs_path=".workflow/docs/${project_name}" bash(git rev-parse --show-toplevel 2>/dev/null || pwd)
echo "PROJECT_NAME: ${project_name}"
echo "TARGET_PATH: ${target_path}"
echo "DOCS_PATH: ${docs_path}"
echo "TOOL: ${tool}"
echo "MODE: ${mode}"
echo "REGENERATE: ${regenerate}"
)
# Check existing documentation
bash(
project_name="[from previous output]"
docs_path=".workflow/docs/${project_name}"
regenerate="[from previous output]"
if [[ -d "$docs_path" ]]; then
doc_count=$(find "$docs_path" -name "*.md" 2>/dev/null | wc -l)
echo "EXISTING_DOCS: $doc_count"
# Handle --regenerate flag: delete existing docs
if [[ -n "$regenerate" ]]; then
echo "REGENERATE: Deleting existing docs at ${docs_path}"
rm -rf "$docs_path"
echo "EXISTING_DOCS: 0 (after regenerate)"
fi
else
echo "EXISTING_DOCS: 0"
fi
)
``` ```
**Parse Output**: **Output**:
- `PROJECT_NAME`: Project name (store as `projectName`) - `target_path`: `/d/my_project`
- `TARGET_PATH`: Full target path (store as `targetPath`) - `project_name`: `my_project`
- `DOCS_PATH`: Documentation path (store as `docsPath`) - `project_root`: `/d/my_project`
- `TOOL`: CLI tool selection (store as `tool`)
- `MODE`: Documentation mode (store as `mode`)
- `REGENERATE`: Regenerate flag (store as `regenerateFlag`)
- `EXISTING_DOCS`: Existing doc count (store as `existingDocs`)
**Validation**: **Step 2: Set Default Parameters**
- Target path exists ```bash
- Project name extracted # Default values (use these unless user specifies otherwise):
# - tool: "gemini"
# - mode: "full"
# - regenerate: false (no --regenerate flag)
```
**Step 3: Check Existing Documentation**
```bash
# Check if docs directory exists (replace project_name with actual value)
bash(test -d .workflow/docs/my_project && echo "exists" || echo "not_exists")
# Count existing documentation files
bash(find .workflow/docs/my_project -name "*.md" 2>/dev/null | wc -l || echo 0)
```
**Output**:
- `docs_exists`: `exists` or `not_exists`
- `existing_docs`: `5` (or `0` if no docs)
**Step 4: Handle --regenerate Flag (If Specified)**
```bash
# If user specified --regenerate, delete existing docs directory
bash(rm -rf .workflow/docs/my_project 2>/dev/null || true)
# Verify deletion
bash(test -d .workflow/docs/my_project && echo "still_exists" || echo "deleted")
```
**Summary**:
- `PROJECT_NAME`: `my_project`
- `TARGET_PATH`: `/d/my_project`
- `DOCS_PATH`: `.workflow/docs/my_project`
- `TOOL`: `gemini` (default) or user-specified
- `MODE`: `full` (default) or user-specified
- `REGENERATE`: `false` (default) or `true` if --regenerate flag
- `EXISTING_DOCS`: `0` (after regenerate) or actual count
**TodoWrite**: Mark phase 1 completed, phase 2 in_progress **TodoWrite**: Mark phase 1 completed, phase 2 in_progress
@@ -178,38 +162,69 @@ SlashCommand(command="/workflow:execute")
**Goal**: Create SKILL.md at `.claude/skills/{project_name}/SKILL.md` **Goal**: Create SKILL.md at `.claude/skills/{project_name}/SKILL.md`
**Actions**: **Step 1: Load Project README**
1. **Load project README for description**:
```bash ```bash
bash( # Read README for project description (replace project_name)
project_name="[from Phase 1]" bash(cat .workflow/docs/my_project/README.md 2>/dev/null | head -50 || echo "No README found")
cat .workflow/docs/${project_name}/README.md 2>/dev/null | head -50 || echo "No README found"
)
``` ```
2. **Discover documentation structure**: **Step 2: Discover All Documentation Files**
```bash ```bash
bash( # List all documentation files (replace project_name)
project_name="[from Phase 1]" bash(find .workflow/docs/my_project -name "*.md" 2>/dev/null | sort)
find .workflow/docs/${project_name} -name "*.md" 2>/dev/null | sort
)
``` ```
3. **Extract module directories**: **Output**:
```bash ```
bash( .workflow/docs/my_project/README.md
project_name="[from Phase 1]" .workflow/docs/my_project/ARCHITECTURE.md
find .workflow/docs/${project_name} -mindepth 1 -maxdepth 2 -type d 2>/dev/null | sed "s|.workflow/docs/${project_name}/||" | sort -u .workflow/docs/my_project/src/modules/auth/API.md
) .workflow/docs/my_project/src/modules/auth/README.md
``` ```
4. **Generate SKILL.md**: **Step 3: Count Documentation Files**
```bash
# Count total docs (replace project_name)
bash(find .workflow/docs/my_project -name "*.md" 2>/dev/null | wc -l)
```
Use the `Write` tool to create `.claude/skills/{project_name}/SKILL.md` with: **Output**: `12` files
**Step 4: Extract Module Directories**
```bash
# Find module directories (1-2 levels deep, replace project_name)
bash(find .workflow/docs/my_project -mindepth 1 -maxdepth 2 -type d 2>/dev/null | sed 's|.workflow/docs/my_project/||' | sort -u)
```
**Output**:
```
src
src/modules
src/utils
lib
lib/core
```
**Step 5: Count Module Directories**
```bash
# Count modules (replace project_name)
bash(find .workflow/docs/my_project -mindepth 1 -maxdepth 2 -type d 2>/dev/null | wc -l)
```
**Output**: `5` modules
**Step 6: Create Skills Directory**
```bash
# Create directory for SKILL.md (replace project_name)
bash(mkdir -p .claude/skills/my_project)
```
**Step 7: Generate SKILL.md**
Use the `Write` tool to create `.claude/skills/my_project/SKILL.md` with:
- YAML frontmatter (name, description from README) - YAML frontmatter (name, description from README)
- Progressive loading guide (Level 0-3) - Progressive loading guide (Level 0-3)
- Module index with relative paths to `../../.workflow/docs/{project_name}/` - Module index with relative paths to `../../.workflow/docs/my_project/`
**SKILL.md Structure**: **SKILL.md Structure**:
```markdown ```markdown