manojlds/ralphi/ralphi-convert

Claude Code and agent skill by manojlds/ralphi

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Converts PRD markdown files to .ralphi/prd.json format for the Ralph autonomous agent loop. Use when asked to convert a PRD, create .ralphi/prd.json, or turn a PRD into Ralph format.

Install

npx vskill@latest install manojlds/ralphi/ralphi-convert

SKILL.md

Ralph PRD Converter

Convert a PRD markdown file into .ralphi/prd.json format for the Ralph autonomous agent loop.

Workflow

  1. Read the PRD markdown file provided by the user.
  2. Run a short planning pass before conversion:
  • Split oversized stories so each can be completed in one iteration
  • Order by dependencies (schema/backend before UI)
  • Add dependsOn links for blocked stories
  1. If .ralphi/prd.json already exists with a different branchName, archive it first to .ralphi/archive/YYYY-MM-DD-feature-name/ before overwriting.
  2. Convert the PRD content into structured JSON following the output format below.
  3. Write the result to .ralphi/prd.json.

Output Format

json
{
"project": "<project name>",
"branchName": "ralph/<feature-name-kebab-case>",
"description": "<brief project description>",
"userStories": [
{
"id": "US-001",
"title": "<story title>",
"description": "<story description>",
"acceptanceCriteria": ["<criterion 1>", "<criterion 2>"],
"priority": 1,
"status": "open",
"dependsOn": [],
"notes": ""
}
]
}

Story Sizing — The Number One Rule

Each story must be completable in one iteration (one context window).

Right-sized examples:

  • Add a database column
  • Add a UI component
  • Update a server action

Too big — split these:

  • Build entire dashboard
  • Add authentication

Story Ordering — Dependencies First

Order stories by dependency chain:

  1. Schema / database changes
  2. Server actions / backend logic
  3. UI components
  4. Dashboard / summary views

Acceptance Criteria — Must Be Verifiable

  • Good: "Add status column with default 'pending'"
  • Bad: "Works correctly"
  • Always include quality checks (lint, type-check, tests pass) as final criteria in each story.

Conversion Rules

  1. Each user story in the PRD becomes one JSON entry.
  2. IDs are sequential: US-001, US-002, etc.
  3. Priority is based on dependency order (1 = first).
  4. All stories start with status: "open", dependsOn: [], and empty notes.
  5. Add dependsOn IDs when a story is blocked by another story (dependency chain should still match priority order).
  6. branchName is kebab-case, prefixed with ralph/.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/manojlds/ralphi/ralphi-convert/badge)](https://verified-skill.com/skills/manojlds/ralphi/ralphi-convert)

Something wrong with this skill or its page? Tell us.