agent planning skill risk: low
Plan to Vertical Slice Issues
Break a plan, spec, or PRD into tracer-bullet vertical slice issues for an issue tracker. Follow a five-step process: gather context, optionally explore the codebase, draft HITL or…
- External action: medium
SKILL 1 file
SKILL.md
--- name: to-issues description: "Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues." --- # To Issues Break a plan into independently-grabbable issues using vertical slices (tracer bullets). The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not. ## Process ### 1. Gather context Work from whatever is already in the conversation context. If the user passes an issue reference (issue number, URL, or path) as an argument, fetch it from the issue tracker and read its full body and comments. ### 2. Explore the codebase (optional) If you have not already explored the codebase, do so to understand the current state of the code. Issue titles and descriptions should use the project's domain glossary vocabulary, and respect ADRs in the area you're touching. ### 3. Draft vertical slices Break the plan 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> ### 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 this addresses (if the source material has them) 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. Publish the issues to the issue tracker For each approved slice, publish a new issue to the issue tracker. Use the issue body template below. These issues are considered ready for AFK agents, so publish them with the correct triage label unless instructed otherwise. Publish issues in dependency order (blockers first) so you can reference real issue identifiers in the "Blocked by" field. <issue-template> ## Parent A reference to the parent issue on the issue tracker (if the source was an existing issue, otherwise omit this section). ## What to build 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 can (state machine, reducer, schema, type shape), inline it here and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits. ## Acceptance criteria - [ ] Criterion 1 - [ ] Criterion 2 - [ ] Criterion 3 ## Blocked by - A reference to the blocking ticket (if any) Or "None - can start immediately" if no blockers. </issue-template> Do NOT close or modify any parent issue.
REQUIRED CONTEXT
- plan, spec, or PRD
- issue tracker and triage label vocabulary
OPTIONAL CONTEXT
- issue reference (number/URL/path)
- codebase state
ROLES & RULES
- Work from whatever is already in the conversation context
- Fetch the issue from the issue tracker if an issue reference is passed
- Explore the codebase if not already done
- Use the project's domain glossary vocabulary and respect ADRs
- Break the plan into tracer bullet issues
- Each slice delivers a narrow but COMPLETE path through every layer
- A completed slice is demoable or verifiable on its own
- Prefer many thin slices over few thick ones
- Prefer AFK over HITL where possible
- Present the proposed breakdown as a numbered list
- Publish issues in dependency order
- Do NOT close or modify any parent issue
EXPECTED OUTPUT
- Format
- markdown
- Schema
- markdown_sections · Parent, What to build, Acceptance criteria, Blocked by
- Constraints
-
- present proposed breakdown as numbered list with Title, Type, Blocked by, User stories covered
- use issue-template for final published issues
- publish in dependency order
SUCCESS CRITERIA
- Break the plan into independently-grabbable tracer bullet issues
- Each issue is a thin vertical slice through all layers
- Quiz the user on granularity, dependencies, and HITL/AFK labels
- Iterate until the user approves
- Publish approved slices to the issue tracker using the template
CAVEATS
- Dependencies
-
- issue tracker and triage label vocabulary
- Missing context
-
- Name or type of issue tracker
- Project-specific domain glossary or ADR references
- How to invoke the setup command or obtain required labels
- Ambiguities
-
- Does not define how to obtain or use the 'issue tracker and triage label vocabulary'.
- 'Explore the codebase (optional)' gives no method, scope, or depth for exploration.
QUALITY
- OVERALL
- 0.76
- CLARITY
- 0.82
- SPECIFICITY
- 0.78
- REUSABILITY
- 0.75
- COMPLETENESS
- 0.72
IMPROVEMENT SUGGESTIONS
- Add an explicit placeholder for the issue tracker name and label vocabulary so the prompt can be reused without editing.
- Replace the single setup command with a generic instruction: 'Confirm that the issue tracker, labels, and project glossary are available before proceeding.'
USAGE
Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.
MORE FOR AGENT
- Consciousness Council Multi-Perspective Deliberation agent planning
- Multi-Agent Architecture Patterns Guide agent planning
- TDD Implementation Plan Writer agent planning
- A/B Test Design and Analysis Guide agent planning
- Autonomous EDA Design Space Explorer agent planning
- Autonomous Design Space Exploration Loop agent planning
- Website Architecture Planning Expert agent planning
- BDI RDF Mental State Modeler agent planning
- Collaborative Software Design Brainstorming Process agent planning
- WWA Product Backlog Item Creator agent planning
- Structured Development Plan Outliner agent planning
- ML Ablation Study Planner agent planning
- Ansoff Matrix Growth Strategy Analyzer agent planning
- Team OKR Brainstorming Product Leader agent planning
- Context Engineering Fundamentals agent planning
- Product Monetization Strategy Developer agent planning
- LLM Project Pipeline Development Methodology agent planning
- What-If Scenario Analysis Oracle agent planning
- Business Model Canvas Generator agent planning
- Implementation Plan Execution Workflow agent planning
- Concise Coding Task Planner agent planning
- Domain Model Plan Grilling Interviewer agent planning
- Latent Briefing KV Cache Compaction agent planning
- Product Roadmap Outcome Transformer agent planning
- Puzzle Activity Planner with Generator Links agent planning