stark-ai-de/agent-skills / incubator/skills/engineering-workflows/issue-plan-slicer
issue-plan-slicer
VerifiedConvert a spec, roadmap item, or rough plan into independently implementable issue slices with scope, dependencies, acceptance criteria, and validation. Use when the user asks to split work into GitHub issues, local markdown tasks, or agent-ready implementation chunks.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.2 KB |
SKILL.md
View on GitHub---
name: issue-plan-slicer
description: Convert a spec, roadmap item, or rough plan into independently implementable issue slices with scope, dependencies, acceptance criteria, and validation. Use when the user asks to split work into GitHub issues, local markdown tasks, or agent-ready implementation chunks.
license: Apache-2.0
metadata:
author: stark-ai-de
category: engineering-workflows
internal: true
version: "0.1.0"
---
# Issue Plan Slicer
## Goal
Turn a broad plan into small, ordered, independently reviewable work items that an agent or maintainer can execute safely.
## When to use
- The user asks to split a spec, roadmap item, issue, PRD, or migration into tasks.
- Work needs GitHub issue drafts, local markdown tasks, or agent-ready implementation slices.
- Dependencies, acceptance criteria, and validation need to be made explicit.
## When not to use
- The user wants immediate implementation of a narrow task.
- The plan is still too ambiguous to slice and needs product discovery first.
- The user asks for live issue creation but has not authorized tracker mutations.
## Inputs to inspect
- The source spec, issue, PRD, roadmap item, or conversation context.
- Existing `docs/agents/issue-tracker.md`, `docs/agents/triage-labels.md`, and `docs/agents/validation.md` when present.
- Existing issue templates and labels under `.github/`.
- Relevant ADRs and domain docs for boundaries and terminology.
## Workflow
1. Identify the desired outcome and non-goals.
2. Extract dependencies, risky assumptions, validation commands, and docs impact.
3. Split work into vertical slices that can be reviewed independently.
4. Mark blockers and sequencing; avoid slices that require hidden context from prior tasks.
5. Draft each issue with title, scope, acceptance criteria, validation, and out-of-scope notes.
6. If the issue tracker is unknown, produce local markdown drafts instead of tracker-specific commands.
7. Ask before creating, labeling, assigning, or closing live issues.
## Safety rules
- Do not mutate issue trackers without explicit user authorization.
- Do not create vague tasks such as "clean up code" without acceptance criteria.
- Do not hide critical dependencies in prose; make them part of the slice.
- Do not assume labels or project boards that are not documented.
## References
Use downstream `docs/agents/issue-tracker.md` and `docs/agents/triage-labels.md` as hard dependencies for tracker-specific output. If they are missing, default to local markdown issue drafts.
## Scripts
No bundled scripts.
## Output format
Return:
1. Source plan summary
2. Proposed issue order
3. Issue drafts with title, scope, acceptance criteria, validation, and dependencies
4. Tracker assumptions
5. Open questions
## Completion criteria
- Each slice can be implemented and reviewed independently.
- Dependencies and sequencing are explicit.
- Validation is attached to each slice.
- Live tracker mutation is either authorized and reported or not performed.
## Failure modes
- If the plan is too ambiguous, ask targeted questions before slicing.
- If one slice grows too large, split it by observable behavior or ownership boundary.
- If tracker docs are missing, avoid tracker-specific labels and commands.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |