Docs AI Prd
Write PRDs, specs, and project context optimized for coding assistants (Claude Code, Cursor, Copilot, Custom GPTs). Includes CLAUDE.md generation, session planning, and templates for creating documentation that tools can execute effectively.
Install
/plugin marketplace add Freddy-CHEN-ux/00_claude_skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add Freddy-CHEN-ux/00_claude_skills --skill docs-ai-prdgit clone --depth 1 https://github.com/Freddy-CHEN-ux/00_claude_skills.git /tmp/00_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/00_claude_skills/skills/docs-ai-prd ~/.claude/skills/docs-ai-prdPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# PRDs & Project Context — Quick Reference Create product requirements and project context that humans and coding assistants can execute effectively. This skill combines **PRD/spec templates** with **project context generation** so implementation work is faster and less ambiguous. **Two complementary capabilities:** 1. **PRDs & Specs** - Requirements, specs, stories, and acceptance criteria for delivery 2. **Project Context** - Document architecture, conventions, and tribal knowledge for onboarding --- **Modern Best Practices (Dec 2025)**: - Decision-first: document the decision, owner, and due date (not just background). - Testability: every requirement has acceptance criteria and explicit non-goals. - Metrics: define formula + timeframe + data source; add guardrails for side effects. - Change control: version docs and keep updates diff-friendly (small deltas, dated changes). - Safety: privacy, security, and accessibility are requirements, not “later”. ## Do / Avoid (Dec 2025) ### Do - Start with a short executive summary (decision, users, scope, success, risks). - Define acceptance criteria in testable language (Gherkin or equivalent). - Keep requirements unambiguous (“must/should/may”) and tie each to evidence. - Link to supporting docs instead of pasting long appendices into the PRD. ### Avoid - Vague requirements (“fast”, “easy”, “intuitive”) without measurable definitions. - Mixing draft notes, open questions, and final requirements without labels.
Details
- Skill name
docs-ai-prd- Repository
- Freddy-CHEN-ux/00_claude_skills
- Path
skills/docs-ai-prd/SKILL.md- Repo updated
- 10 January 2026
FAQ
What does the Docs AI Prd skill do?
Write PRDs, specs, and project context optimized for coding assistants (Claude Code, Cursor, Copilot, Custom GPTs). Includes CLAUDE.md generation, session planning, and templates for creating documentation that tools can execute effectively.
How do I install the Docs AI Prd skill?
Claude Code plugin: /plugin marketplace add Freddy-CHEN-ux/00_claude_skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Docs AI Prd popular?
It lives in Freddy-CHEN-ux/00_claude_skills, which has 8 GitHub stars and 3 forks.
Related skills
Add Integration
8Freddy-CHEN-ux/00_claude_skills
Build a new API integration for Nexus. Load when user mentions "add integration", "new integration", "integrate with", "connect to [service]", or "build [service] integration". Interactive workflow that discovers API endpoints, plans the integration, and creates a project for implementation.
AI Agents
8Freddy-CHEN-ux/00_claude_skills
Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, and observability (modern best practices)
AI LLM
8Freddy-CHEN-ux/00_claude_skills
Production LLM engineering skill. Covers strategy selection (prompting vs RAG vs fine-tuning), dataset design, PEFT/LoRA, evaluation workflows, deployment handoff to inference serving, and lifecycle operations with cost/safety controls.
Domain Modeling Made Functional
5vnovakovits/claude-skills
Apply Scott Wlaschin's "Domain Modeling Made Functional" (Pragmatic Bookshelf, 2018), the functional rendering of domain-driven design. Covers making illegal states unrepresentable with algebraic data types, workflows as type signatures (Command → Result<Events, DomainError>), errors as values on a railway (domain errors, infrastructure errors, panics), single-case wrappers against primitive obsession, aggregates as a choice of states, functional core and imperative shell with the impureim (read-calculate-write) sandwich, and dependency rejection, where the domain takes data and returns decisi
Dispatching Parallel Agents
8Freddy-CHEN-ux/00_claude_skills
Use when multiple independent tasks can run simultaneously. Enables efficient parallel work execution with specialized agents.
Edge Functions
8Freddy-CHEN-ux/00_claude_skills
Use when working with Deno edge functions, LLM integration, or embedding generation. Load for Deno.serve patterns, Zod request validation, OpenRouter LLM calls, and error handling. Covers function structure, CORS, and the call-llm/generate-embedding patterns.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.