agentleFS
craigcossairtcraigcossairt/trellis/.claude/skills/prd-to-issues/SKILL.md

prd-to-issues

Skill5 starsChanged 11 days agoMITView on GitHub

Break a PRD into independently-grabbable tracker issues using tracer-bullet vertical slices. Use when asked to 'PRD to issues', 'break this PRD into tickets', 'create implementation tickets from a PRD', 'turn PRD into issues'.

35 other projects use a version of this, 28 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use prd-to-plan, request-refactor-plan and 10 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.
  • HK-hubSkill

    prd-to-plan

    Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

    Also in 11 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 11 projects that use this

  • ShopifySkill

    triage-issue

    Triage a GitHub issue — classify priority (P0/P1/P2), search for duplicates, and apply labels.

    Also in 13 projects that use this

  • simo97Skill

    design-an-interface

    Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

    Also in 10 projects that use this

  • AnasX7Skill

    scaffold-exercises

    Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

    Also in 6 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 7 projects that use this

  • +5 more from simo97

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 5 are common, 8 are distinctive, and 0 are very specific to this project.

  • 5

    Common

    Most of the 35 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for the PRD issue number (or URL).

    line 15
  2. Distinctive:

    If the PRD is not already in your context window, fetch it (with comments).

    line 17
  3. Common:

    If you have not already explored the codebase, do so to understand the current state of the code.

    line 21
  4. Distinctive:

    ALL integration layers end-to-end, NOT a horizontal slice of one layer.

    line 26
  5. Distinctive:

    Prefer AFK over HITL where possible.

    line 30
  6. Common:

    Prefer many thin slices over few thick ones </vertical-slice-rules>

    line 35
  7. Distinctive:

    Prefactoring goes first, as its own issue: If a slice is only easy once some existing code is reshaped, make the reshaping an issue that …

    line 40
  8. Distinctive:

    A wide refactor is three issues: expand, migrate, contract: When a change touches every caller of something (a renamed column, a new …

    line 44
  9. Common:

    Should any slices be merged or split further?

    line 62
  10. Common:

    Create issues in dependency order (blockers first) so you can reference real issue numbers in the "Blocked by" field.

    line 71
  11. Distinctive:

    Before creating each issue, check every criterion against the code as it is now.

    line 109
  12. Distinctive:

    If you cannot make it fail today, the criterion is either already done (drop it) or too vague to check (rewrite it).

    line 116
  13. Common:

    Do NOT close or modify the parent PRD issue.

    line 124

“Common” is measured: kept by at least 6 in 10 of the 35 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 to Issues

Break a PRD into independently-grabbable issues in the project's tracker using vertical slices (tracer bullets).

Process

1. Locate the PRD

Ask the user for the PRD issue number (or URL).

If the PRD is not already in your context window, fetch it (with comments).

2. Explore the codebase (optional)

If you have not already explored the codebase, do so to understand the current state of the code.

3. Draft vertical slices

Break the PRD into tracer bullet issues. Each issue is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.

Slices may be 'HITL' or 'AFK'. HITL slices require human interaction, such as an architectural decision or a design review. AFK slices can be implemented and merged without human interaction. Prefer AFK over HITL where possible.

<vertical-slice-rules> - Each slice delivers a narrow but COMPLETE path through every layer (schema, API, UI, tests) - A completed slice is demoable or verifiable on its own - Prefer many thin slices over few thick ones </vertical-slice-rules>

Two kinds of work are not vertical slices, and each has its own place in the order:

  • Prefactoring goes first, as its own issue. If a slice is only easy once some existing code is reshaped, make the reshaping an issue that changes no behavior, and have the slice blocked by it. A slice that carries its own refactor is two changes in one diff, and a reviewer can check neither.
  • A wide refactor is three issues: expand, migrate, contract. When a change touches every caller of something (a renamed column, a new function signature), add the new form beside the old one, move the callers over, then remove the old form. Each step leaves the project working on its own, so the work can stop after any of them.

4. Quiz the user

Present the proposed breakdown as a numbered list. For each slice, show:

  • Title: short descriptive name
  • Type: HITL / AFK
  • Blocked by: which other slices (if any) must complete first
  • User stories covered: which user stories from the PRD this addresses

Ask the user:

  • Does the granularity feel right? (too coarse / too fine)
  • Are the dependency relationships correct?
  • Should any slices be merged or split further?
  • Are the correct slices marked as HITL and AFK?

Iterate until the user approves the breakdown.

5. Create the issues

For each approved slice, create a tracker issue. Use the issue body template below.

Create issues in dependency order (blockers first) so you can reference real issue numbers in the "Blocked by" field.

<issue-template> ## Parent PRD

#<prd-issue-number>

What to build

A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation. Reference specific sections of the parent PRD rather than duplicating content.

Acceptance criteria

Each criterion names what you would observe if it were NOT met.

  • Criterion 1 - fails today because: <the observation, at the starting commit>
  • Criterion 2 - fails today because: <...>
  • Criterion 3 - fails today because: <...>

Blocked by

  • Blocked by #<issue-number> (if any)

Or "None - can start immediately" if no blockers.

User stories addressed

Reference by number from the parent PRD:

  • User story 3
  • User story 7
</issue-template>

Acceptance criteria that can fail

Before creating each issue, check every criterion against the code as it is now. A criterion that is already true at the starting commit proves nothing when it is true at the end. "The settings page works" passes before anyone touches it. "Saving a display name longer than 40 characters shows the length error; today it saves silently" can only pass once the work is done.

For each criterion, write down the observation that would show it false, and confirm that observation holds at the starting commit: run the command, open the page, or read the code path. If you cannot make it fail today, the criterion is either already done (drop it) or too vague to check (rewrite it). This matters most for AFK slices, where nobody is watching the run that declares the issue finished.

One kind stays although it passes today: a criterion that guards what the work must not break ("people who are signed in stay signed in"). Keep it, and label it must stay true, so that nobody reads its passing as proof the work was done.

Do NOT close or modify the parent PRD issue.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.