to-prd
Use when the user wants a PRD synthesized from the current conversation and codebase context (not an interview) and fed into the build pipeline as tracked, agent-ready work. Triggers include "turn this into a PRD", "write the PRD", "make issues from this", "spec this out for the team".
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- to-prd
- description
- Use when the user wants a PRD synthesized from the current conversation and codebase context (not an interview) and fed into the build pipeline as tracked, agent-ready work. Triggers include "turn this into a PRD", "write the PRD", "make issues from this", "spec this out for the team".
02 资源文件 67
- 参考文档checklist.md12.2 KB
- 参考文档instructions.md1.1 KB
- 许可证LICENSE1.0 KB
- 参考文档resources/knowledge/adr-quality-readiness-checklist.md24.8 KB
- 参考文档resources/knowledge/api-request.md16.7 KB
- 参考文档resources/knowledge/api-testing-patterns.md26.3 KB
- 参考文档resources/knowledge/auth-session.md15.8 KB
- 参考文档resources/knowledge/burn-in.md6.4 KB
- 参考文档resources/knowledge/ci-burn-in.md22.0 KB
- 参考文档resources/knowledge/component-tdd.md15.8 KB
- 参考文档resources/knowledge/contract-testing.md35.4 KB
- 参考文档resources/knowledge/data-factories.md15.0 KB
- 参考文档resources/knowledge/email-auth.md24.0 KB
- 参考文档resources/knowledge/error-handling.md22.4 KB
- 参考文档resources/knowledge/feature-flags.md22.7 KB
- 参考文档resources/knowledge/file-utils.md13.4 KB
- 参考文档resources/knowledge/fixture-architecture.md12.1 KB
- 参考文档resources/knowledge/fixtures-composition.md11.0 KB
- 参考文档resources/knowledge/intercept-network-call.md13.2 KB
- 参考文档resources/knowledge/log.md11.0 KB
- 参考文档resources/knowledge/network-error-monitor.md12.0 KB
- 参考文档resources/knowledge/network-first.md15.9 KB
- 参考文档resources/knowledge/network-recorder.md15.1 KB
- 参考文档resources/knowledge/nfr-criteria.md26.0 KB
- 参考文档resources/knowledge/overview.md9.4 KB
- 参考文档resources/knowledge/pact-consumer-di.md11.7 KB
- 参考文档resources/knowledge/pact-consumer-framework-setup.md24.3 KB
- 参考文档resources/knowledge/pact-mcp.md8.6 KB
- 参考文档resources/knowledge/pactjs-utils-consumer-helpers.md10.4 KB
- 参考文档resources/knowledge/pactjs-utils-overview.md10.2 KB
- 参考文档resources/knowledge/pactjs-utils-provider-verifier.md13.5 KB
- 参考文档resources/knowledge/pactjs-utils-request-filter.md7.1 KB
- 参考文档resources/knowledge/playwright-cli.md14.6 KB
- 参考文档resources/knowledge/playwright-config.md21.0 KB
- 参考文档resources/knowledge/probability-impact.md18.8 KB
- 参考文档resources/knowledge/recurse.md12.6 KB
- 参考文档resources/knowledge/risk-governance.md20.5 KB
- 参考文档resources/knowledge/selective-testing.md21.3 KB
- 参考文档resources/knowledge/selector-resilience.md19.3 KB
- 参考文档resources/knowledge/test-healing-patterns.md20.9 KB
- 参考文档resources/knowledge/test-levels-framework.md14.4 KB
- 参考文档resources/knowledge/test-priorities-matrix.md11.2 KB
- 参考文档resources/knowledge/test-quality.md24.0 KB
- 参考文档resources/knowledge/timing-debugging.md13.7 KB
- 参考文档resources/knowledge/visual-debugging.md17.1 KB
- 参考文档resources/knowledge/webhook-module-setup.md5.7 KB
- 参考文档resources/knowledge/webhook-providers.md6.3 KB
- 参考文档resources/knowledge/webhook-risk-guidance.md6.3 KB
- 参考文档resources/knowledge/webhook-template-matchers.md5.9 KB
- 参考文档resources/knowledge/webhook-testing-fundamentals.md3.1 KB
- 参考文档resources/knowledge/webhook-timeout-error.md5.6 KB
- 参考文档resources/knowledge/webhook-waiting-querying.md6.9 KB
- 资产文件resources/tea-index.csv10.0 KB
- 参考文档steps-c/step-01-preflight.md4.0 KB
- 参考文档steps-c/step-01b-resume.md3.7 KB
- 参考文档steps-c/step-02-select-framework.md2.9 KB
- 参考文档steps-c/step-03-scaffold-framework.md12.4 KB
- 参考文档steps-c/step-04-docs-and-scripts.md3.0 KB
- 参考文档steps-c/step-05-validate-and-summary.md2.1 KB
- 参考文档steps-e/step-01-assess.md1.2 KB
- 参考文档steps-e/step-02-apply-edit.md1.1 KB
- 参考文档steps-v/step-01-validate.md1.4 KB
- 参考文档validation-report-20260127-095021.md2.0 KB
- 参考文档validation-report-20260127-102401.md3.7 KB
- 参考文档workflow-plan.md519 B
- 参考文档workflow.md1.2 KB
- 参考文档workflow.yaml1.7 KB
03 SKILL.md 正文
To PRD
Overview
Synthesize a PRD from the current conversation + codebase understanding — do NOT interview the user, use what you already know — then feed it into the metaswarm build pipeline as tracked, agent-ready GitHub work decomposed into tracer-bullet vertical slices.
The native pipeline (the rewire)
mattpocock's original published to a generic tracker with a ready-for-agent label via a /setup-matt-pocock-skills config step. Here the PRD is the input to the workspace's gates, and there is no label-map:
-
Synthesize the PRD (template below). First pull the domain vocabulary and prior decisions from basic-memory + the event-ledger so wording matches what was already decided; respect prior decisions in the area you are touching. Compose with
grill-with-docsif the plan is contested — its captured decisions become this PRD's Implementation Decisions. -
Sketch the seams. Identify where the feature will be tested. Prefer existing seams to new ones; use the highest seam possible; if new seams are needed, propose them at the highest point. Confirm the seams match the user's expectations.
-
STOP at the Design Review Gate. Per the project workflow, a fresh design doc must pass
/review-design(the design-review-gate: PM, Architect, Designer, Security, CTO — all must approve) before planning. Do NOT skip straight to issues. For a smaller change, run at least the plan-review-gate before presenting. -
Decompose into tracer-bullet vertical slices. Each slice = one thin end-to-end path (UI -> logic -> data) that ships and is testable on its own. These become metaswarm work-units. List them in build order, each naming the seam it exercises.
-
Publish to GitHub. Use
gh issue create(or the metaswarm/create-issuecommand) — one parent PRD issue plus one issue per vertical slice (or sub-issues under the parent). Triage is the metaswarm gates, not a label.
Compose with
- prototype — a prototype snippet that nails a decision (reducer, state machine, schema, type shape) can be inlined in Implementation Decisions; see the template exception below.
- grill-with-docs — run a docs-aware grill first if the plan is contested; feed its captured decisions in.
- design-review-gate / plan-review-gate / create-issue — the gates and issue creation this PRD feeds.
PRD template
## Problem Statement
The problem the user is facing, from the user's perspective.
## Solution
The solution to the problem, from the user's perspective.
## User Stories
A LONG, numbered list. Each story: "As an <actor>, I want a <feature>, so that <benefit>."
Cover all aspects of the feature; be extensive.
## Vertical Slices (tracer bullets)
Numbered, in build order. Each slice is one thin end-to-end path that ships and is
testable on its own (a metaswarm work-unit). For each: the path it cuts and the seam
it exercises.
1. Slice — <thin end-to-end path> — seam: <where it is tested>
## Implementation Decisions
Modules built/modified, interfaces touched, technical clarifications, architectural
decisions, schema changes, API contracts, specific interactions.
Do NOT include specific file paths or code snippets — they go stale fast.
Exception: if a prototype produced a snippet that encodes a decision more precisely
than prose (state machine, reducer, schema, type shape), inline the decision-rich
bits and note it came from a prototype — not a working demo, just the important parts.
## Testing Decisions
What makes a good test here (test external behavior, not implementation details),
which modules will be tested, and prior art (similar tests already in the codebase).
## Out of Scope
What is explicitly not part of this PRD.
## Further Notes
Anything else.
Idea adapted from the to-prd skill in https://github.com/mattpocock/skills — MIT License, Copyright (c) 2026 Matt Pocock. This is a workspace-native rebuild: the publish path is rewired from a generic tracker + label-map to the metaswarm gates (design-review-gate / plan-review-gate) and GitHub issues via gh / create-issue, with tracer-bullet vertical-slice decomposition and basic-memory/event-ledger vocabulary grounding added. Original under MIT; full notice in LICENSE (this folder). Built 2026-06-30.
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files