Ai native prd architect
Skill DYAI2025/Plumbline/config/claude/skills/ai-native-prd-architect
Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?
npx -y skills add DYAI2025/Plumbline --skill ai-native-prd-architectAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when turning a feature idea into an implementation-ready PRD with traceable REQ IDs, acceptance criteria, NFRs, risks, data model, and task slices for /agileteam Phase 0.
SKILL.md
1.0 KB, as published. Nobody here has run it
AI-native PRD Architect
Produce a buildable, testable PRD without filling gaps by guessing.
Workflow
- Restate the goal and target repository.
- Create stable
REQ-###identifiers. - Define scope, non-goals, actors, data model, interfaces, constraints, NFRs, security/privacy risks, rollout and rollback notes.
- Write Given/When/Then acceptance criteria for every REQ.
- Build a traceability matrix with
REQ,test,task,evidence,wired-in-prod?, andevidence-classcolumns. - Mark unknowns explicitly as
MISSING,OPEN QUESTION,ASSUMPTION, orBLOCKER.
Hard rules
- Never close a missing requirement through plausibility. Ask the user or call
brainstorming. - Every task must trace back to at least one REQ.
- Every REQ must have at least one machine-checkable acceptance signal.