By BradyHazell
Drafts Product Requirements Documents through conversational discovery. Acts as a PM, not a stenographer — challenges scope, surfaces hidden assumptions, and treats Open Questions as a first-class output so the PRD is genuinely useful as a source of truth for implementation.
Draft a new PRD (Product Requirements Document). Conversational discovery followed by structured drafting, with open questions surfaced explicitly. Saves to the path resolved by .prdrc.json (or ./prds/ by default).
Update an existing PRD. Handles three flows — resolving open questions during/after build, scope/content changes, and status promotion through the configured lifecycle. Reads the PRD, asks targeted delta questions, and produces an updated version with a changelog.
Validate a PRD for structural completeness, open-question hygiene, specificity, and internal consistency. Produces a validation report with a status (PASS / CONDITIONAL / FAIL) and a decision-readiness judgement.
Use this agent to turn a captured Feature Context block into a written PRD. Requires a Feature Context block in the conversation (produce one with the prd-interviewer agent first). Writes a structured PRD per the prd-template skill, with all required sections and only the triggered conditional sections. Surfaces open questions in the AI-readable Question/Answer format.
Use this agent at the start of any PRD drafting session to elicit the feature context from the user. Conducts a conversational discovery — not an interrogation — challenging assumptions, surfacing open questions, and producing a Feature Context block that the prd-drafter then turns into a PRD. Use proactively whenever the user invokes /prd-drafter:draft for a new feature.
Use this agent to update an existing PRD. Handles three common update flows — resolving open questions during/after build, expanding scope mid-flight, and promoting a PRD through its status lifecycle. Reads the existing PRD, asks targeted delta questions, and produces an updated version with bumped Version and updated Date.
Use this agent to validate a drafted or updated PRD for structural completeness, open-question hygiene, specificity, and internal consistency. Produces a validation report with a status (PASS / CONDITIONAL / FAIL) and a decision-readiness judgement. Use after any drafter or updater finishes, or when the user runs /prd-drafter:validate.
Conventions for PRD file naming, folder placement, status lifecycle, and project association. Reads .prdrc.json at the repo root for per-repo overrides, otherwise applies sensible defaults. Loaded by every agent in the prd-drafter plugin so drafts land in the right place with consistent naming.
Conversation approach for eliciting a PRD from a user. Defines how to ask questions (batched, not interrogative), when to challenge ideas, how to surface open questions, and how to adapt the template to the feature in front of you. Loaded by the prd-interviewer and prd-drafter agents.
End-to-end workflow for drafting a new Product Requirements Document. Conducts conversational discovery (acting as a PM, not a stenographer), composes the PRD with required and triggered conditional sections, surfaces open questions as first-class output, and saves to the path resolved by .prdrc.json. Use when the user asks to draft, create, write, or start a new PRD for a feature.
Quality checks for a drafted PRD. Defines structural completeness, open-question hygiene, common anti-patterns, and the validator's scoring rubric. Loaded by the prd-validator agent.
The PRD template and section structure used by the prd-drafter agent. Defines the canonical sections, when each one is required vs optional, and how to phrase open questions for AI-readable downstream consumption. Loaded by every drafter/updater/validator agent in this plugin.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A personal Claude Code plugin marketplace. The plugins also install into other agents (Codex, Cursor, Goose, etc.) via the npx skills CLI.
/plugin marketplace add BradyHazell/brady-plugins
/plugin install prd-drafter@brady-plugins
Update later:
/plugin marketplace update brady-plugins
/plugin update prd-drafter@brady-plugins
# Auto-detect installed agents
npx skills add BradyHazell/brady-plugins
# Or target a specific agent
npx skills add BradyHazell/brady-plugins -a codex
npx skills add BradyHazell/brady-plugins -a cursor
| Plugin | Version | Summary |
|---|---|---|
| prd-drafter | 1.0.0 | Drafts Product Requirements Documents through conversational discovery. Acts as a PM, not a stenographer — challenges scope, surfaces hidden assumptions, treats Open Questions as a first-class output. Configurable per-repo via .prdrc.json. |
Each plugin has its own README with full details — click the plugin name above.
This is a personal repo, but issues and PRs are welcome.
AGENTS.md at the repo root for conventions, versioning rules, and how to add a new plugin.AGENTS.md is your instruction manual.MIT — use, fork, modify freely with attribution.
npx claudepluginhub bradyhazell/brady-plugins --plugin prd-drafterMake your AI agent code with your project's architecture, rules, and decisions.
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation