skills/ralph/SKILL.md
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
npx skillsauth add realroc/skills ralphInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.
Take a PRD (markdown file or text) and convert it to prd.json in your ralph directory.
{
"project": "[Project Name]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[Feature description from PRD title/intro]",
"userStories": [
{
"id": "US-001",
"title": "[Story title]",
"description": "As a [user], I want [feature] so that [benefit]",
"acceptanceCriteria": [
"Criterion 1",
"Criterion 2",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
}
]
}
Each story must be completable in ONE Ralph iteration (one context window).
Ralph spawns a fresh Amp instance per iteration with no memory of previous work. If a story is too big, the LLM runs out of context before finishing and produces broken code.
Rule of thumb: If you cannot describe the change in 2-3 sentences, it is too big.
Stories execute in priority order. Earlier stories must not depend on later ones.
Correct order:
Wrong order:
Each criterion must be something Ralph can CHECK, not something vague.
status column to tasks table with default 'pending'""Typecheck passes"
For stories with testable logic, also include:
"Tests pass"
"Verify in browser using dev-browser skill"
Frontend stories are NOT complete until visually verified. Ralph will use the dev-browser skill to navigate to the page, interact with the UI, and confirm changes work.
passes: false and empty notesralph/If a PRD has big features, split them:
Original:
"Add user notification system"
Split into:
Each is one focused change that can be completed and verified independently.
Input PRD:
# Task Status Feature
Add ability to mark tasks with different statuses.
## Requirements
- Toggle between pending/in-progress/done on task list
- Filter list by status
- Show status badge on each task
- Persist status in database
Output prd.json:
{
"project": "TaskApp",
"branchName": "ralph/task-status",
"description": "Task Status Feature - Track task progress with status indicators",
"userStories": [
{
"id": "US-001",
"title": "Add status field to tasks table",
"description": "As a developer, I need to store task status in the database.",
"acceptanceCriteria": [
"Add status column: 'pending' | 'in_progress' | 'done' (default 'pending')",
"Generate and run migration successfully",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
},
{
"id": "US-002",
"title": "Display status badge on task cards",
"description": "As a user, I want to see task status at a glance.",
"acceptanceCriteria": [
"Each task card shows colored status badge",
"Badge colors: gray=pending, blue=in_progress, green=done",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 2,
"passes": false,
"notes": ""
},
{
"id": "US-003",
"title": "Add status toggle to task list rows",
"description": "As a user, I want to change task status directly from the list.",
"acceptanceCriteria": [
"Each row has status dropdown or toggle",
"Changing status saves immediately",
"UI updates without page refresh",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 3,
"passes": false,
"notes": ""
},
{
"id": "US-004",
"title": "Filter tasks by status",
"description": "As a user, I want to filter the list to see only certain statuses.",
"acceptanceCriteria": [
"Filter dropdown: All | Pending | In Progress | Done",
"Filter persists in URL params",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 4,
"passes": false,
"notes": ""
}
]
}
Before writing a new prd.json, check if there is an existing one from a different feature:
prd.json if it existsbranchName differs from the new feature's branch nameprogress.txt has content beyond the header:
archive/YYYY-MM-DD-feature-name/prd.json and progress.txt to archiveprogress.txt with fresh headerThe ralph.sh script handles this automatically when you run it, but if you are manually updating prd.json between runs, archive first.
Before writing prd.json, verify:
development
Screen MongoDB conversation collections for script-driven abuse (prompt-injection templates, curl/empty user agents, probe-word floods, sessionless calls, multi-account IPs). Produces a two-tier triage report (confirmed abuse / suspicious) plus a multi-account IP list and a ban candidate CSV. Use when asked to find script callers, prompt-injection attempts, abnormal high-frequency users, accounts bypassing the web UI, or "who is using my AI as a cron job".
development
Audit or rewrite a prompt into a six-section issue spec (Goal / Constraints / Non-goals / Verification / Architecture notes / Existing context) before any code gets generated. Use when the user pastes a vague request and asks for implementation, or explicitly says they want to frame an issue properly. Triggers on: prompt spec, audit this prompt, check my prompt, what's missing in this prompt, frame this issue, rewrite as a prompt spec, convert to issue spec, make this an issue, issue framing.
testing
GitHire's six-step AI-native engineering method: frame the issue, sandbox, AI execute, AI review, architect decision, ship. Use when planning or executing real work with AI agents — issue framing, prompt writing, PR review gating, architect handoff — or anytime humans-frame-AI-execute-architects-verify applies. Triggers on: use githire, githire methodology, issue-first onboarding, ai-native workflow, frame this issue, prompt spec, architect review, first PR for a candidate, hire through real PRs.
development
Geolocate a batch of IPv4 addresses and produce a Markdown distribution table — Chinese IPs broken down by province (incl. HK/MO/TW), foreign IPs by country, with counts and percentages. Optionally exports CSV. Uses the free ip-api.com batch endpoint (no key, no signup, HTTP only, 15 batches × 100 IPs per minute). Use when the user pastes a list of IPs and asks for "IP 分布", "IP 归属地分布", "省份分布", "where are these IPs from", "geolocate these IPs", or wants an IP-region breakdown table.