mcpbeat Sign in

Ralphinit Agent Skill

Start a ralph style looping session

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
201
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/sterlingcrispin/claude_slash_commands --skill ralphinit

The instruction itself

9 sections, as written by the author

Initialize Project Documentation from System Plan

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.

Your Task

Read current_SYSTEM-PLAN.md and create two companion documents:

  • current_PRD.md - A comprehensive Product Requirements Document
  • current_PROGRESS.md - A progress tracking journal

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.


Step 1: Read the System Plan

First, read current_SYSTEM-PLAN.md in the current directory to understand:

  • Project goals and context
  • Architecture and components
  • Design decisions
  • Development stages/phases
  • Success criteria
  • Any constraints or scope limitations

Step 2: Create current_PRD.md

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.

PRD Guidelines:

  • Extract ALL testable requirements from the system plan - be thorough
  • Each requirement must have 4-6 concrete verification steps
  • Start all requirements with "passes": false
  • Use categories: functional, integration, architecture, performance, usability, maintainability, milestone, constraint
  • Functional requirements should cover every component mentioned in the architecture
  • Include milestone requirements that map to the plan's success criteria
  • Aim for 40-100 requirements depending on project complexity
  • Requirements should be specific enough that pass/fail is unambiguous

Step 3: Create current_PROGRESS.md

Write 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]

Progress Guidelines:

  • Structure should make it easy for an agent to:
  • Quickly understand current state
  • Find the next task to work on
  • Record what was done
  • Track which PRD requirements have been satisfied
  • Include enough architecture context that the agent doesn't need to re-read the full system plan every session
  • Checklist items should map to PRD requirements where possible
  • Leave session log empty - it will be filled as work progresses

Step 4: Verify and Report

After creating both files:

  • Confirm both files were written successfully
  • Report the total number of requirements in the PRD
  • Report the number of development stages identified
  • List any open questions or ambiguities that need user clarification

Important Notes

  • The system plan is the source of truth - don't invent requirements not implied by the plan
  • Be comprehensive - the agent will rely on these documents to know what to build
  • Keep formatting consistent - these files will be read programmatically
  • Use the exact filenames: current_PRD.md and current_PROGRESS.md
  • All three files should be in the current working directory

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take sterlingcrispin/ralphinit from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

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.