/manual
Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria.
$ npx -y skills add Taoidle/plan-cascade --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/manual
Context preview
What this command does when you run it.
Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria.
Command definition
manual.mddescription: "Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria."
Hybrid Ralph - Load Manual PRD
You are loading an existing Product Requirements Document (PRD) from a file.
Step 1: Parse PRD Path
Get the PRD path from arguments:
PRD_PATH="{{args|first arg or 'prd.json'}}"Step 2: Verify PRD Exists
if [ ! -f "$PRD_PATH" ]; then
echo "ERROR: PRD file not found: $PRD_PATH"
echo "Please provide a valid path to a prd.json file"
exit 1
fiStep 3: Read and Validate PRD
Read the PRD file and validate structure:
Required fields:
- `metadata.description`
- `goal`
- `stories` array
Each story must have:
- `id`
- `title`
- `description`
- `priority` (high/medium/low)
- `dependencies` (array of story IDs)
- `acceptance_criteria` (array)
If validation fails, show specific errors and suggest fixes.
Step 4: Copy PRD to Current Directory (if needed)
If the PRD is not already `prd.json` in the current directory:
if [ "$PRD_PATH" != "prd.json" ]; then
cp "$PRD_PATH" prd.json
echo "Copied PRD to prd.json"
fiStep 5: Initialize Supporting Files (if missing)
Create `findings.md` if it doesn't exist:
if [ ! -f "findings.md" ]; then
cat > findings.md << 'EOF'
# Findings
Research and discovery notes will be accumulated here.
Use <!-- @tags: story-id --> to tag sections for specific stories.
EOF
fiCreate `progress.txt` if it doesn't exist:
if [ ! -f "progress.txt" ]; then
cat > progress.txt << 'EOF'
# Progress Log
Story execution progress will be tracked here.
EOF
fiStep 6: Display PRD Review
Show a comprehensive PRD review:
============================================================
PRD REVIEW
============================================================
## Goal
{goal from PRD}
## Objectives
- {objective 1}
- {objective 2}
...
## Stories Summary
Total Stories: {count}
By Priority:
High: {count}
Medium: {count}
Low: {count}
## All Stories
### story-001: {title} [High]
Description: {description}
Dependencies: {none or list}
Acceptance Criteria:
- {criterion 1}
- {criterion 2}
...
### story-002: {title} [Medium]
...
## Execution Batches
Batch 1 (parallel):
- story-001
- story-002
Batch 2:
- story-003 (depends on: story-001)
...
============================================================Step 7: Show Next Steps
PRD loaded successfully!
Next steps:
- /approve - Approve PRD and start execution
- /edit - Edit PRD manually
- /show-dependencies - View dependency graph
Notes
- Validates all dependency references exist
- Shows warnings for orphan stories (no dependencies, nothing depends on them)
- Detects circular dependencies if any exist
Read more
description: "Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria."
Hybrid Ralph - Load Manual PRD
You are loading an existing Product Requirements Document (PRD) from a file.
Step 1: Parse PRD Path
Get the PRD path from arguments:
PRD_PATH="{{args|first arg or 'prd.json'}}"Step 2: Verify PRD Exists
if [ ! -f "$PRD_PATH" ]; then
echo "ERROR: PRD file not found: $PRD_PATH"
echo "Please provide a valid path to a prd.json file"
exit 1
fiStep 3: Read and Validate PRD
Read the PRD file and validate structure:
Required fields:
- `metadata.description`
- `goal`
- `stories` array
Each story must have:
- `id`
- `title`
- `description`
- `priority` (high/medium/low)
- `dependencies` (array of story IDs)
- `acceptance_criteria` (array)
If validation fails, show specific errors and suggest fixes.
Step 4: Copy PRD to Current Directory (if needed)
If the PRD is not already `prd.json` in the current directory:
if [ "$PRD_PATH" != "prd.json" ]; then
cp "$PRD_PATH" prd.json
echo "Copied PRD to prd.json"
fiStep 5: Initialize Supporting Files (if missing)
Create `findings.md` if it doesn't exist:
if [ ! -f "findings.md" ]; then
cat > findings.md << 'EOF'
# Findings
Research and discovery notes will be accumulated here.
Use <!-- @tags: story-id --> to tag sections for specific stories.
EOF
fiCreate `progress.txt` if it doesn't exist:
if [ ! -f "progress.txt" ]; then
cat > progress.txt << 'EOF'
# Progress Log
Story execution progress will be tracked here.
EOF
fiStep 6: Display PRD Review
Show a comprehensive PRD review:
============================================================
PRD REVIEW
============================================================
## Goal
{goal from PRD}
## Objectives
- {objective 1}
- {objective 2}
...
## Stories Summary
Total Stories: {count}
By Priority:
High: {count}
Medium: {count}
Low: {count}
## All Stories
### story-001: {title} [High]
Description: {description}
Dependencies: {none or list}
Acceptance Criteria:
- {criterion 1}
- {criterion 2}
...
### story-002: {title} [Medium]
...
## Execution Batches
Batch 1 (parallel):
- story-001
- story-002
Batch 2:
- story-003 (depends on: story-001)
...
============================================================Step 7: Show Next Steps
PRD loaded successfully! Next steps: - /approve - Approve PRD and start execution - /edit - Edit PRD manually - /show-dependencies - View dependency graph
Notes
- Validates all dependency references exist
- Shows warnings for orphan stories (no dependencies, nothing depends on them)
- Detects circular dependencies if any exist
AI-Powered Cascading Development Framework Transform complex projects into parallel executable tasks with intelligent decomposition and multi-provider execution Why Plan Cascade? • Product Editions • Quick Start • Architecture
Repo: Taoidle/plan-cascade
Other commands on plan-cascade.
- /approve
Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story, and monitors progress. Usage: /plan-cascade:approve [--flow <quick|standard|full>] [--tdd <off|on|auto>] [--confirm]
Open command - /auto
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration.
Open command - /check-gitignore
Check and update .gitignore to exclude Plan Cascade temporary files. Ensures planning files won't be accidentally committed to version control.
Open command - /complete
Complete a worktree task. Verifies all phases are complete, commits code changes (excluding planning files), merges to target branch, and removes worktree. Can be run from any directory. Usage: /plan-cascade:complete [target-branch]
Open command - /dashboard
Show execution status dashboard. Usage: /plan-cascade:dashboard [--verbose|-v] [--json]
Open command - /design-generate
Generate a technical design document. Auto-detects level: project-level from mega-plan.json, or feature-level from prd.json. Provides architectural context for story execution.
Open command

