AGENT SKILL

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".

适用职业产品经理
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

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:

  1. 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-docs if the plan is contested — its captured decisions become this PRD's Implementation Decisions.

  2. 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.

  3. 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.

  4. 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.

  5. Publish to GitHub. Use gh issue create (or the metaswarm /create-issue command) — 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

Prekzursil
Prekzursil/agent-skills-toolchain

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.

★ 0
Prekzursil
Prekzursil/agent-skills-toolchain

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.

Skill与智能体开发
★ 0
Prekzursil
Prekzursil/agent-skills-toolchain

visual-review

Take screenshots of web pages and UI using Playwright for visual review and iteration

演示文稿测试与质量
★ 0
Prekzursil
Prekzursil/agent-skills-toolchain

status

Diagnostic status report — shows metaswarm installation state, project setup, and potential issues

★ 0
Prekzursil
Prekzursil/agent-skills-toolchain

start

Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work

Skill与智能体开发
★ 0
Prekzursil
Prekzursil/agent-skills-toolchain

setup

Interactive project setup — detects your project, configures metaswarm, writes project-local files

★ 0