agentleFS
paureispaureis/pau-skills/skills/planning/to-issues/SKILL.md

to-issues

Skill2 starsChanged 22 days agoMITView on GitHub

Break a plan, spec or PRD into independently grabbable issues, each a thin vertical slice through every layer, ordered by dependency and filed after approval. Use when the user says 'break this into tasks', 'create issues', 'create tickets', 'make tasks from this', 'split this into slices' or 'break this down'.

130 other projects use a version of this, 98 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use decision-mapping, modern-go 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.
  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 7 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

  • victorgarciaesgiSkill

    zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

    Also in 49 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

  • simo97Skill

    request-refactor-plan

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

    Also in 18 projects that use this

  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 18 projects that use this

  • +2 more from jidechao
  • +2 more from simo97

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 123 edited versions we read keep these.

  • 5

    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: "Do these slices look right?

    line 41
  2. Distinctive:

    Don't close, modify, or update the parent PRD or issue.

    line 79
  3. Distinctive:

    Vertical, not horizontal: Every slice crosses all relevant layers.

    line 83
  4. Distinctive:

    Use the project's domain vocabulary: If CONTEXT.md defines "Evaluation," don't call it "Assessment" in the issue title.

    line 84
  5. Distinctive:

    Small enough to be independently testable: If a slice can't be verified on its own, it's not a real slice: it's half of one.

    line 85

“Common” is measured: kept by at least 6 in 10 of the 123 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

To Issues

Break a plan, PRD, or feature description into independently-grabbable issues using vertical slices.

Process

1. Gather the source

Work from whatever is already in the conversation context. If the user passes an issue reference, URL, or document, read its full content. If you haven't already explored the codebase, do so to understand the current state of the code.

2. Break into vertical slices

Each issue is a thin vertical slice that cuts through ALL integration layers end-to-end, NOT a horizontal slice of one layer.

Vertical slice (correct): "Add an order history page with its API endpoint, data query, and a basic list UI": crosses DB, API, and frontend.

Horizontal slice (wrong): "Create database schema for order history" then "Build API endpoint" then "Build frontend page": each layer isolated, no end-to-end feedback until all three are done.

Slices may be:

  • AFK: can be implemented and merged without human interaction. These are self-contained enough for an AI agent to pick up.
  • HITL: requires human interaction: an architectural decision, design review, or manual verification step.

Mark each slice clearly as AFK or HITL.

3. Present for approval

Present the slices as a numbered list with:

  • Title: concise, action-oriented
  • Type: AFK or HITL
  • Dependencies: which slices block this one (by number)
  • Scope: one-sentence description of the end-to-end behavior

Ask: "Do these slices look right? Want to add, remove, or reorder any?"

4. Create the issues

Once approved, create each issue (as a file, a GitHub issue, or a ticket in whatever tracker the project uses). For each issue:

Issue Template

## Description
A concise description of this vertical slice. Describe the end-to-end
behavior, not layer-by-layer implementation. Avoid 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 it here and note it came from a prototype.

## Acceptance Criteria
- [ ] [Observable behavior 1]
- [ ] [Observable behavior 2]
- [ ] [Edge case handled]

## Dependencies
Blocked by: [issue references, if any]

## Slice Type
AFK / HITL

## Notes
Any context the implementer needs: domain vocabulary, relevant ADRs,
or links to the parent PRD.

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

5. Do NOT modify the source

Don't close, modify, or update the parent PRD or issue. The slices reference it; they don't replace it.

Rules

  • Vertical, not horizontal. Every slice crosses all relevant layers. No "database-only" or "frontend-only" slices unless the change genuinely is one layer.
  • Use the project's domain vocabulary. If CONTEXT.md defines "Evaluation," don't call it "Assessment" in the issue title.
  • Small enough to be independently testable. If a slice can't be verified on its own, it's not a real slice: it's half of one.
  • Order by dependencies. Present and create in dependency order so each issue can reference its blockers.
  • Don't over-slice. 3-8 slices for a typical feature. If you're past 12, you're probably slicing too thin or the feature needs to be split into separate PRDs.

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.