agentleFS
yokeloopyokeloop/yoke/skills/prd/SKILL.md

prd

Skill1 starsChanged 4 months agoMITView on GitHub

Turns the current conversation and codebase understanding into a PRD, publishes it as a GitHub issue, and saves a local copy in .yoke/ai. Does not interview — synthesizes what is already known. Activates when the user writes "prd", "create a prd", "write a prd", "turn this into a prd", "product requirements doc", "draft requirements".

125 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use context-optimize, usecase and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • gabriellstSkill

    usecase

    Create an application use case. Use when implementing business operations like CreateOrder, ProcessPayment, CancelBooking. Use this skill for any command/mutation that orchestrates domain logic, whether simple CRUD or complex multi-step transactions with sagas. Dispatch hub — routes to typescript/go variants by file extension.

    Also in 3 projects that use this

  • jidechaoSkill

    modern-go

    Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.

    Also in 3 projects that use this

  • ulises-jeremiasSkill

    trd

    WHAT — Draft and review a Technical Requirements Document (TRD) using the template, typically

    Also in 3 projects that use this

  • jidechaoSkill

    loop-it

    Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.

    Also in 3 projects that use this

  • snarktankSkill

    ralph

    Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

    Also in 16 projects that use this

  • +2 more from jidechao

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 102 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If gh is not authenticated or there is no GitHub remote, keep the local copy only and tell the user where it is.

    line 33
  2. Distinctive:

    Do NOT include specific file paths or code snippets.

    line 69
  3. Very specific:

    Use the project's domain glossary and respect ADRs.

    line 94

“Common” is measured: kept by at least 6 in 10 of the 102 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PRD

Turn the current conversation and codebase understanding into a PRD. Do NOT interview the user — synthesize what is already known.

Process

  1. Explore the repo to understand the codebase, if not already done. Follow the domain-doc consumer rules in ${CLAUDE_PLUGIN_ROOT}/skills/grill-docs/reference/domain-docs.md: read .yoke/context.md and the relevant .yoke/adr/, use the glossary's vocabulary throughout the PRD, and flag any ADR the PRD contradicts. Also read the git memory of the modules the PRD touches per ${CLAUDE_PLUGIN_ROOT}/skills/gca/reference/history-reading.md — active Constraint: entries and past Rejected: approaches belong in Implementation Decisions.
  2. Sketch the major modules to build or modify. Look for deep modules to extract that can be tested in isolation. A deep module encapsulates substantial functionality behind a simple, testable interface that rarely changes. Decide the module breakdown and which modules are test-worthy yourself, and record both in the PRD's Implementation Decisions and Testing Decisions sections — do not stop to interview the user.
  3. Write the PRD using the template below.
  4. Build the slug — an English kebab-case description, prefixed with a ticket id only if one exists in context (e.g. 86-balance-on-accounts, otherwise dark-mode-settings). Derive the PRD title from the slug's human-readable form and add it as a top-level # <title> heading at the top of the PRD body. Save a local copy to .yoke/ai/<slug>/<slug>-prd.md (mkdir -p .yoke/ai/<slug> first).
  5. Publish to GitHub. Follow ${CLAUDE_PLUGIN_ROOT}/skills/issues/reference/github-issues.md for the gh conventions and triage labels. First check it is safe to publish: only when an open GitHub issue already carries the same title, ask the user whether to update it (gh issue edit <n> --body-file ...) or create a new one. A stale local .yoke/ai/<slug>/<slug>-prd.md with no matching open issue is not ambiguous — overwrite it and create the issue without asking. Otherwise:

    gh issue create --title "<PRD title>" --body-file .yoke/ai/<slug>/<slug>-prd.md

    Apply the ready-for-agent label per the reference (create it if the repo lacks it, unless the user objects). Then set the issue's type to Feature per the reference's "Issue types" section — a best-effort API call after creation; if the repo has no issue types, leave it untyped and warn rather than failing. Write the resulting issue URL into the local PRD artifact as a **Tracking:** <URL> line directly under the # <title> heading, so /yoke:issues can later use it as the parent for sub-issue linking; skip the write if a **Tracking:** line already exists. Finally, print the issue URL.

    If gh is not authenticated or there is no GitHub remote, keep the local copy only and tell the user where it is.

<prd-template>

Problem Statement

The problem the user faces, from the user's perspective.

Solution

The solution to the problem, from the user's perspective.

User Stories

A LONG, numbered list of user stories. Each follows this format:

  1. As an <actor>, I want a <feature>, so that <benefit>
<user-story-example> 1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending </user-story-example>

Make it extensive — cover every aspect of the feature.

Implementation Decisions

A list of implementation decisions. This can include:

  • The modules that will be built/modified
  • The interfaces of those modules that will be modified
  • Technical clarifications from the developer
  • 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 can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits.

Testing Decisions

A list of testing decisions. Include:

  • A description of what makes a good test (only test external behavior, not implementation details)
  • Which modules will be tested
  • Prior art for the tests (i.e. similar tests in the codebase)

Out of Scope

What is out of scope for this PRD.

Further Notes

Any further notes about the feature.

</prd-template>

Rules

  • Synthesize from existing context — don't interview the user.
  • Use the project's domain glossary and respect ADRs. Pair with /yoke:grill-docs upstream to build that vocabulary.
  • To break the PRD into implementation tickets, hand off to /yoke:issues.
  • Language: match the conversation language, or follow the project-level definition in CLAUDE.md / AGENTS.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.