prd

Name: prd
Author: github

21kinstalls4.6kforks

How to install prd?

github/awesome-copilot/prd

$npx -y skills add github/awesome-copilot --skill prd

Installs into the current project.

Summary

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

Files · 1

View on GitHub

SKILL.md

1	# Product Requirements Document (PRD)
2
3	## Overview
4
5	Design 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.
6
7	## When to Use
8
9	Use this skill when:
10
11	- Starting a new product or feature development cycle
12	- Translating a vague idea into a concrete technical specification
13	- Defining requirements for AI-powered features
14	- Stakeholders need a unified "source of truth" for project scope
15	- User asks to "write a PRD", "document requirements", or "plan a feature"
16
17	---
18
19	## Operational Workflow
20
21	### Phase 1: Discovery (The Interview)
22
23	Before writing a single line of the PRD, you MUST interrogate the user to fill knowledge gaps. Do not assume context.
24
25	Ask about:
26
27	- The Core Problem: Why are we building this now?
28	- Success Metrics: How do we know it worked?
29	- Constraints: Budget, tech stack, or deadline?
30
31	### Phase 2: Analysis & Scoping
32
33	Synthesize the user's input. Identify dependencies and hidden complexities.
34
35	- Map out the User Flow.
36	- Define Non-Goals to protect the timeline.
37
38	### Phase 3: Technical Drafting
39
40	Generate the document using the Strict PRD Schema below.
41
42	---
43
44	## PRD Quality Standards
45
46	### Requirements Quality
47
48	Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".
49
50	```diff
51	# Vague (BAD)
52	- The search should be fast and return relevant results.
53	- The UI must look modern and be easy to use.
54
55	# Concrete (GOOD)
56	+ The search must return results within 200ms for a 10k record dataset.
57	+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
58	+ The UI must follow the 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.
59	```
60
61	---
62
63	## Strict PRD Schema
64
65	You MUST follow this exact structure for the output:
66
67	### 1. Executive Summary
68
69	- Problem Statement: 1-2 sentences on the pain point.
70	- Proposed Solution: 1-2 sentences on the fix.
71	- Success Criteria: 3-5 measurable KPIs.
72
73	### 2. User Experience & Functionality
74
75	- User Personas: Who is this for?
76	- User Stories: `As a [user], I want to [action] so that [benefit].`
77	- Acceptance Criteria: Bulleted list of "Done" definitions for each story.
78	- Non-Goals: What are we NOT building?
79
80	### 3. AI System Requirements (If Applicable)
81
82	- Tool Requirements: What tools and APIs are needed?
83	- Evaluation Strategy: How to measure output quality and accuracy.
84
85	### 4. Technical Specifications
86
87	- Architecture Overview: Data flow and component interaction.
88	- Integration Points: APIs, DBs, and Auth.
89	- Security & Privacy: Data handling and compliance.
90
91	### 5. Risks & Roadmap
92
93	- Phased Rollout: MVP -> v1.1 -> v2.0.
94	- Technical Risks: Latency, cost, or dependency failures.
95
96	---
97
98	## Implementation Guidelines
99
100	### DO (Always)
101
102	- Define Testing: For AI systems, specify how to test and validate output quality.
103	- Iterate: Present a draft and ask for feedback on specific sections.
104
105	### DON'T (Avoid)
106
107	- Skip Discovery: Never write a PRD without asking at least 2 clarifying questions first.
108	- Hallucinate Constraints: If the user didn't specify a tech stack, ask or label it as `TBD`.
109
110	---
111
112	## Example: Intelligent Search System
113
114	### 1. Executive Summary
115
116	Problem: Users struggle to find specific documentation snippets in massive repositories.
117	Solution: An intelligent search system that provides direct answers with source citations.
118	Success:
119
120	- Reduce search time by 50%.
121	- Citation accuracy >= 95%.
122
123	### 2. User Stories
124
125	- Story: As a developer, I want to ask natural language questions so I don't have to guess keywords.
126	- AC:
127	- Supports multi-turn clarification.
128	- Returns code blocks with "Copy" button.
129
130	### 3. AI System Architecture
131
132	- Tools Required: `codesearch`, `grep`, `webfetch`.
133
134	### 4. Evaluation
135
136	- Benchmark: Test with 50 common developer questions.
137	- Pass Rate: 90% must match expected citations.

People who liked this also viewed

6 picks

Type

prd

21kinstalls4.6kforks

View on GitHub

How to install prd?

github/awesome-copilot/prd

$npx -y skills add github/awesome-copilot --skill prd

Installs into the current project.

Summary

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

Files · 1

View on GitHub

SKILL.md

1	# Product Requirements Document (PRD)
2
3	## Overview
4
5	Design 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.
6
7	## When to Use
8
9	Use this skill when:
10
11	- Starting a new product or feature development cycle
12	- Translating a vague idea into a concrete technical specification
13	- Defining requirements for AI-powered features
14	- Stakeholders need a unified "source of truth" for project scope
15	- User asks to "write a PRD", "document requirements", or "plan a feature"
16
17	---
18
19	## Operational Workflow
20
21	### Phase 1: Discovery (The Interview)
22
23	Before writing a single line of the PRD, you MUST interrogate the user to fill knowledge gaps. Do not assume context.
24
25	Ask about:
26
27	- The Core Problem: Why are we building this now?
28	- Success Metrics: How do we know it worked?
29	- Constraints: Budget, tech stack, or deadline?
30
31	### Phase 2: Analysis & Scoping
32
33	Synthesize the user's input. Identify dependencies and hidden complexities.
34
35	- Map out the User Flow.
36	- Define Non-Goals to protect the timeline.
37
38	### Phase 3: Technical Drafting
39
40	Generate the document using the Strict PRD Schema below.
41
42	---
43
44	## PRD Quality Standards
45
46	### Requirements Quality
47
48	Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".
49
50	```diff
51	# Vague (BAD)
52	- The search should be fast and return relevant results.
53	- The UI must look modern and be easy to use.
54
55	# Concrete (GOOD)
56	+ The search must return results within 200ms for a 10k record dataset.
57	+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
58	+ The UI must follow the 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.
59	```
60
61	---
62
63	## Strict PRD Schema
64
65	You MUST follow this exact structure for the output:
66
67	### 1. Executive Summary
68
69	- Problem Statement: 1-2 sentences on the pain point.
70	- Proposed Solution: 1-2 sentences on the fix.
71	- Success Criteria: 3-5 measurable KPIs.
72
73	### 2. User Experience & Functionality
74
75	- User Personas: Who is this for?
76	- User Stories: `As a [user], I want to [action] so that [benefit].`
77	- Acceptance Criteria: Bulleted list of "Done" definitions for each story.
78	- Non-Goals: What are we NOT building?
79
80	### 3. AI System Requirements (If Applicable)
81
82	- Tool Requirements: What tools and APIs are needed?
83	- Evaluation Strategy: How to measure output quality and accuracy.
84
85	### 4. Technical Specifications
86
87	- Architecture Overview: Data flow and component interaction.
88	- Integration Points: APIs, DBs, and Auth.
89	- Security & Privacy: Data handling and compliance.
90
91	### 5. Risks & Roadmap
92
93	- Phased Rollout: MVP -> v1.1 -> v2.0.
94	- Technical Risks: Latency, cost, or dependency failures.
95
96	---
97
98	## Implementation Guidelines
99
100	### DO (Always)
101
102	- Define Testing: For AI systems, specify how to test and validate output quality.
103	- Iterate: Present a draft and ask for feedback on specific sections.
104
105	### DON'T (Avoid)
106
107	- Skip Discovery: Never write a PRD without asking at least 2 clarifying questions first.
108	- Hallucinate Constraints: If the user didn't specify a tech stack, ask or label it as `TBD`.
109
110	---
111
112	## Example: Intelligent Search System
113
114	### 1. Executive Summary
115
116	Problem: Users struggle to find specific documentation snippets in massive repositories.
117	Solution: An intelligent search system that provides direct answers with source citations.
118	Success:
119
120	- Reduce search time by 50%.
121	- Citation accuracy >= 95%.
122
123	### 2. User Stories
124
125	- Story: As a developer, I want to ask natural language questions so I don't have to guess keywords.
126	- AC:
127	- Supports multi-turn clarification.
128	- Returns code blocks with "Copy" button.
129
130	### 3. AI System Architecture
131
132	- Tools Required: `codesearch`, `grep`, `webfetch`.
133
134	### 4. Evaluation
135
136	- Benchmark: Test with 50 common developer questions.
137	- Pass Rate: 90% must match expected citations.

People who liked this also viewed

6 picks

Type