{"id":"78b766f4-d7db-43af-a9b0-57b137e28137","shortId":"yJjHuw","kind":"skill","title":"prd","tagline":"Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.","description":"# Product Requirements Document (PRD)\n\n## Overview\n\nDesign comprehensive, production-grade Product Requirements Documents (PRDs) that bridge the gap between business vision and technical execution. This skill works for modern software systems, ensuring that requirements are clearly defined.\n\n## When to Use\n\nUse this skill when:\n\n- Starting a new product or feature development cycle\n- Translating a vague idea into a concrete technical specification\n- Defining requirements for AI-powered features\n- Stakeholders need a unified \"source of truth\" for project scope\n- User asks to \"write a PRD\", \"document requirements\", or \"plan a feature\"\n\n---\n\n## Operational Workflow\n\n### Phase 1: Discovery (The Interview)\n\nBefore writing a single line of the PRD, you **MUST** interrogate the user to fill knowledge gaps. Do not assume context.\n\n**Ask about:**\n\n- **The Core Problem**: Why are we building this now?\n- **Success Metrics**: How do we know it worked?\n- **Constraints**: Budget, tech stack, or deadline?\n\n### Phase 2: Analysis & Scoping\n\nSynthesize the user's input. Identify dependencies and hidden complexities.\n\n- Map out the **User Flow**.\n- Define **Non-Goals** to protect the timeline.\n\n### Phase 3: Technical Drafting\n\nGenerate the document using the **Strict PRD Schema** below.\n\n---\n\n## PRD Quality Standards\n\n### Requirements Quality\n\nUse concrete, measurable criteria. Avoid \"fast\", \"easy\", or \"intuitive\".\n\n```diff\n# Vague (BAD)\n- The search should be fast and return relevant results.\n- The UI must look modern and be easy to use.\n\n# Concrete (GOOD)\n+ The search must return results within 200ms for a 10k record dataset.\n+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.\n+ The UI must follow the 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.\n```\n\n---\n\n## Strict PRD Schema\n\nYou **MUST** follow this exact structure for the output:\n\n### 1. Executive Summary\n\n- **Problem Statement**: 1-2 sentences on the pain point.\n- **Proposed Solution**: 1-2 sentences on the fix.\n- **Success Criteria**: 3-5 measurable KPIs.\n\n### 2. User Experience & Functionality\n\n- **User Personas**: Who is this for?\n- **User Stories**: `As a [user], I want to [action] so that [benefit].`\n- **Acceptance Criteria**: Bulleted list of \"Done\" definitions for each story.\n- **Non-Goals**: What are we NOT building?\n\n### 3. AI System Requirements (If Applicable)\n\n- **Tool Requirements**: What tools and APIs are needed?\n- **Evaluation Strategy**: How to measure output quality and accuracy.\n\n### 4. Technical Specifications\n\n- **Architecture Overview**: Data flow and component interaction.\n- **Integration Points**: APIs, DBs, and Auth.\n- **Security & Privacy**: Data handling and compliance.\n\n### 5. Risks & Roadmap\n\n- **Phased Rollout**: MVP -> v1.1 -> v2.0.\n- **Technical Risks**: Latency, cost, or dependency failures.\n\n---\n\n## Implementation Guidelines\n\n### DO (Always)\n\n- **Define Testing**: For AI systems, specify how to test and validate output quality.\n- **Iterate**: Present a draft and ask for feedback on specific sections.\n\n### DON'T (Avoid)\n\n- **Skip Discovery**: Never write a PRD without asking at least 2 clarifying questions first.\n- **Hallucinate Constraints**: If the user didn't specify a tech stack, ask or label it as `TBD`.\n\n---\n\n## Example: Intelligent Search System\n\n### 1. Executive Summary\n\n**Problem**: Users struggle to find specific documentation snippets in massive repositories.\n**Solution**: An intelligent search system that provides direct answers with source citations.\n**Success**:\n\n- Reduce search time by 50%.\n- Citation accuracy >= 95%.\n\n### 2. User Stories\n\n- **Story**: As a developer, I want to ask natural language questions so I don't have to guess keywords.\n- **AC**:\n  - Supports multi-turn clarification.\n  - Returns code blocks with \"Copy\" button.\n\n### 3. AI System Architecture\n\n- **Tools Required**: `codesearch`, `grep`, `webfetch`.\n\n### 4. Evaluation\n\n- **Benchmark**: Test with 50 common developer questions.\n- **Pass Rate**: 90% must match expected citations.","tags":["prd","awesome","copilot","github","agent-skills","agents","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"capabilities":["skill","source-github","skill-prd","topic-agent-skills","topic-agents","topic-awesome","topic-custom-agents","topic-github-copilot","topic-hacktoberfest","topic-prompt-engineering"],"categories":["awesome-copilot"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/github/awesome-copilot/prd","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add github/awesome-copilot","source_repo":"https://github.com/github/awesome-copilot","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 33270 github stars · SKILL.md body (4,064 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:52:20.935Z","embedding":null,"createdAt":"2026-04-18T20:24:30.748Z","updatedAt":"2026-05-18T18:52:20.935Z","lastSeenAt":"2026-05-18T18:52:20.935Z","tsv":"'-2':304,313 '-5':321 '1':121,298,303,312,490 '10':268 '100':282 '10k':258 '2':172,324,465,525 '200ms':255 '3':199,320,364,559 '4':387,568 '5':409 '50':521,573 '85':266 '90':579 '95':524 'ac':547 'accept':346 'access':284 'accuraci':386,523 'achiev':265,281 'action':342 'ai':15,93,365,431,560 'ai-pow':14,92 'algorithm':263 'alway':427 'analysi':27,173 'answer':512 'api':375,399 'applic':369 'architectur':390,562 'ask':107,146,446,462,480,535 'assum':144 'auth':402 'avoid':220,454 'bad':227 'benchmark':270,570 'benefit':345 'block':555 'bridg':43 'budget':166 'build':154,363 'bullet':348 'busi':47 'button':558 'citat':515,522,583 'clarif':552 'clarifi':466 'clear':63 'code':554 'codesearch':565 'common':574 'complex':184 'complianc':408 'compon':395 'comprehens':34 'concret':86,217,247 'constraint':165,470 'context':145 'copi':557 'core':149 'cost':420 'criteria':219,319,347 'cycl':79 'data':392,405 'dataset':260 'dbs':400 'deadlin':170 'defin':64,89,190,428 'definit':352 'depend':181,422 'design':33,278 'develop':78,531,575 'didn':474 'diff':225 'direct':511 'discoveri':122,456 'document':8,30,40,112,204,499 'done':351 'draft':201,444 'easi':222,244 'ensur':59 'eval':271 'evalu':378,569 'exact':293 'exampl':486 'execut':19,51,299,491 'expect':582 'experi':326 'failur':423 'fast':221,232 'featur':17,77,95,117 'feedback':448 'fill':139 'find':497 'first':468 'fix':317 'flow':189,393 'follow':275,291 'function':327 'gap':45,141 'generat':2,202 'goal':193,358 'good':248 'grade':37 'grep':566 'guess':545 'guidelin':425 'hallucin':469 'handl':406 'hidden':183 'high':4 'high-qual':3 'idea':83 'identifi':180 'implement':424 'includ':18 'input':179 'integr':397 'intellig':487,506 'interact':396 'interrog':135 'interview':124 'intuit':224 'iter':441 'keyword':546 'know':162 'knowledg':140 'kpis':323 'label':482 'languag':537 'latenc':419 'least':464 'lighthous':283 'line':129 'list':349 'look':240 'map':185 'massiv':502 'match':581 'measur':218,322,382 'metric':158 'modern':56,241 'multi':550 'multi-turn':549 'must':134,239,251,264,274,290,580 'mvp':414 'natur':536 'need':97,377 'never':457 'new':74 'non':192,357 'non-goal':191,356 'oper':118 'output':297,383,439 'overview':32,391 'pain':308 'pass':577 'persona':329 'phase':120,171,198,412 'plan':115 'point':309,398 'power':16,94 'prd':1,31,111,132,208,211,287,460 'prds':9,41 'precis':267 'present':442 'privaci':404 'problem':150,301,493 'product':6,28,36,38,75 'production-grad':35 'project':104 'propos':310 'protect':195 'provid':510 'qualiti':5,212,215,384,440 'question':467,538,576 'rate':578 'record':259 'reduc':517 'relev':235 'repositori':503 'requir':7,29,39,61,90,113,214,367,371,564 'result':236,253 'return':234,252,553 'risk':26,410,418 'roadmap':411 'rollout':413 'schema':209,288 'scope':105,174 'score':285 'search':229,250,262,488,507,518 'section':451 'secur':403 'sentenc':305,314 'singl':128 'skill':53,70 'skill-prd' 'skip':455 'snippet':500 'softwar':11,57 'solut':311,504 'sourc':100,514 'source-github' 'specif':24,88,389,450,498 'specifi':433,476 'stack':168,479 'stakehold':96 'standard':213 'start':72 'statement':302 'stori':22,335,355,527,528 'strategi':379 'strict':207,286 'structur':294 'struggl':495 'success':157,318,516 'summari':20,300,492 'support':548 'synthes':175 'system':12,58,279,366,432,489,508,561 'tbd':485 'tech':167,478 'technic':23,50,87,200,388,417 'test':429,436,571 'time':519 'timelin':197 'tool':370,373,563 'topic-agent-skills' 'topic-agents' 'topic-awesome' 'topic-custom-agents' 'topic-github-copilot' 'topic-hacktoberfest' 'topic-prompt-engineering' 'translat':80 'truth':102 'turn':551 'ui':238,273 'unifi':99 'use':67,68,205,216,246 'user':21,106,137,177,188,325,328,334,338,473,494,526 'v1.1':415 'v2.0':416 'vagu':82,226 'valid':438 'vercel/next.js':277 'vision':48 'want':340,533 'webfetch':567 'within':254 'without':461 'work':54,164 'workflow':119 'write':109,126,458","prices":[{"id":"d7025b27-5375-44ec-a7c3-5297ccdc6225","listingId":"78b766f4-d7db-43af-a9b0-57b137e28137","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"github","category":"awesome-copilot","install_from":"skills.sh"},"createdAt":"2026-04-18T20:24:30.748Z"}],"sources":[{"listingId":"78b766f4-d7db-43af-a9b0-57b137e28137","source":"github","sourceId":"github/awesome-copilot/prd","sourceUrl":"https://github.com/github/awesome-copilot/tree/main/skills/prd","isPrimary":false,"firstSeenAt":"2026-04-18T21:50:39.886Z","lastSeenAt":"2026-05-18T18:52:20.935Z"},{"listingId":"78b766f4-d7db-43af-a9b0-57b137e28137","source":"skills_sh","sourceId":"github/awesome-copilot/prd","sourceUrl":"https://skills.sh/github/awesome-copilot/prd","isPrimary":true,"firstSeenAt":"2026-04-18T20:24:30.748Z","lastSeenAt":"2026-05-07T22:40:14.853Z"}],"details":{"listingId":"78b766f4-d7db-43af-a9b0-57b137e28137","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"github","slug":"prd","github":{"repo":"github/awesome-copilot","stars":33270,"topics":["agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"license":"mit","html_url":"https://github.com/github/awesome-copilot","pushed_at":"2026-05-18T01:26:59Z","description":"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","skill_md_sha":"b19e77a252c14eed2b8fd1b506aa100fa2010fb3","skill_md_path":"skills/prd/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/github/awesome-copilot/tree/main/skills/prd"},"layout":"multi","source":"github","category":"awesome-copilot","frontmatter":{"name":"prd","license":"MIT","description":"Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis."},"skills_sh_url":"https://skills.sh/github/awesome-copilot/prd"},"updatedAt":"2026-05-18T18:52:20.935Z"}}