sterlingcrispin/ralphinit
Start a ralph style looping session
npx skills add https://github.com/sterlingcrispin/claude_slash_commands --skill ralphinit
You are initializing a new project for agent-driven development. The user has provided a current_SYSTEM-PLAN.md file in the current working directory that describes the system architecture and goals.
Read current_SYSTEM-PLAN.md and create two companion documents:
These three current_* files will serve as the foundation for an automated agent that works in a continuous development loop, picking up tasks and making progress incrementally.
First, read current_SYSTEM-PLAN.md in the current directory to understand:
Write a comprehensive PRD with testable requirements extracted from the system plan. Structure it as:
# [Project Name] - Product Requirements Document
**Last Updated:** [today's date]
---
## Requirements
[
{
"category": "functional|integration|architecture|performance|usability|maintainability|milestone|constraint",
"description": "Clear, testable requirement statement",
"steps": [
"Step 1 to verify this requirement",
"Step 2...",
"Step 3...",
"Step 4...",
"Step 5..."
],
"passes": false
},
...
]
## Summary Statistics
| Category | Count |
|----------|-------|
| Functional | X |
| Integration | X |
| ... | ... |
| **Total** | **X** |
## Development Stages Mapping
Map requirements to development stages from the system plan.
## Open Questions
List any ambiguities or decisions that need user input.
"passes": falsefunctional, integration, architecture, performance, usability, maintainability, milestone, constraintWrite a progress journal structured for continuous agent development:
# [Project Name] Progress Journal
**Purpose:** Track progress on implementation. Useful for context continuity between sessions.
**Last Updated:** [today's date]
---
## Current Status: [STAGE NAME] NOT STARTED
Brief description of where we are.
---
## Project Context Quick Reference
### What We Have
- Key existing assets (data, models, infrastructure)
### Key Files
- List important files and their purposes
### Core Design Decisions (from plan)
1. Decision 1
2. Decision 2
...
---
## Development Stages Checklist
### Stage 1: [Name]
**Goal:** [from system plan]
- [ ] Task 1
- [ ] Task 2
- [ ] Task 3
**Validation:** [how to know this stage is complete]
---
### Stage 2: [Name]
...
---
## Session Log
### [Date] - Session 1
**Work Done:**
- (empty - will be filled as work progresses)
**Next Session Should:**
- Start with first task from Stage 1
---
## Architecture Quick Reference
[Include a simplified architecture diagram or component list from the system plan]
---
## Key Interfaces (for quick reference)
[Extract key interfaces/APIs from the system plan that the agent will need to implement]
---
## Notes & Decisions Log
*Add notes here as implementation decisions are made*
---
## Open Questions
[Copy from system plan or identify new ones]
After creating both files:
current_PRD.md and current_PROGRESS.mdTake sterlingcrispin/ralphinit from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.