ralph
RALPH — Autonomous PRD Implementation
RALPH (Repeated Autonomous Loop for PRD Handling) implements a PRD stored as GitHub issues — autonomously, with TDD, and a code review gate after every iteration.
The Pipeline
This skill is the execution engine for a 4-step coding workflow:
| Step | Command | What It Does |
|---|---|---|
| 1 | /grill-me |
Stress-test your idea with relentless questions before building |
| 2 | /write-a-prd |
Turn the idea into an engineering spec (PRD) as a GitHub issue |
| 3 | /prd-to-issues |
Break the PRD into vertical-slice sub-issues with dependencies |
| 4 | /ralph |
Implement each sub-issue autonomously with TDD + code review |
Steps 1-3 use skills from Matt Pocock. Install them:
npx skills@latest add mattpocock/skills -s grill-me
More from thecraighewitt/skills
shape
Use when you have a rough product idea and want a complete PRD without sitting through an interactive grilling. Claude walks the full decision tree (edge cases, modules, schema, testing, security), self-answers with software-engineering best practices, streams the Q&A live so you can override, and writes the PRD locally with an option to push as a GitHub issue.
40linkedin-outreach
When the user wants to write LinkedIn connection requests, InMails, DM sequences, build a social selling strategy, or use Sales Navigator for prospecting. Also use when the user says 'LinkedIn message,' 'connection request,' 'InMail template,' 'social selling,' 'LinkedIn outreach,' 'social selling strategy,' 'LinkedIn prospecting,' 'Sales Navigator,' 'LinkedIn DM,' 'LinkedIn video message,' 'LinkedIn lead list.' For email outreach, see cold-email. For multi-channel sequences, see outbound-sequence. For profile research, see lead-research.
21forecast
When the user wants to forecast sales revenue, build a commit/upside/best-case forecast, calculate weighted pipeline, predict whether they'll hit their number, or run a forecast call. Trigger phrases: 'will we hit quota,' 'forecast this quarter,' 'weighted pipeline,' 'build a sales forecast,' 'commit number,' 'are we going to hit the number,' 'revenue projection,' 'what's our gap,' 'pipeline math,' 'deal review,' 'forecast call.' For pipeline data that feeds the forecast, see pipeline-review. For comp plans tied to quota, see sales-comp.
18discovery-call
When the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect. Also use when the user says 'prep for a discovery call,' 'write discovery questions,' 'help me qualify this deal,' 'qualify a lead,' 'first call with a prospect,' 'initial meeting.' For deep buyer research before the call, see buyer-persona. For post-call analysis, see call-debrief.
18referral-intro
When the user wants to ask for a warm introduction, build a referral program, or systematize their referral channel. Also use when the user says 'get me an intro,' 'ask for a referral,' 'write a forwardable email,' 'warm introduction,' 'partner referral,' 'reference request,' 'intro email,' 'leverage my network,' 'referral program,' 'ask for an intro at dinner,' or 'track referrals in CRM.' For cold outreach without a warm path, see cold-email or linkedin-outreach. For sequencing referral asks into a cadence, see outbound-sequence. For running the meeting after a referral intro is made, see discovery-call.
18win-loss-analysis
When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes. Trigger phrases: 'why did we lose that deal,' 'win-loss review,' 'analyze our closed deals,' 'what are we losing to,' 'deal post-mortem,' 'why do we keep losing to [competitor],' 'deal autopsy,' 'competitive losses,' 'why did we win that deal.' For individual call analysis, see call-debrief. For competitive positioning, see competitive-intel. For buyer understanding, see buyer-persona.
18