| 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).
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.
.agent-state/ is local-only and not committed to the repo. It is gitignored and exists only on the current machine. PRDs and issue files written here are agent working state — never reference .agent-state/ paths from committed artifacts (source, PR descriptions, commits, issues on the tracker, RFCs). When the issue is posted to the tracker, the tracker copy is the source of truth.
Identify the active PRD. PRDs live in .agent-state/prds/<slug>/PRD.md. From the conversation context, infer which slug this run is about:
- If only one PRD directory exists, use it.
- If multiple exist, pick the one the conversation is iterating on. Ask the user only if it's genuinely ambiguous.
All subsequent file paths in this skill are scoped to that PRD's directory.
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.
- 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
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, create a file <repository-root>/.agent-state/prds/<slug>/issue-X.md, where <slug> is the active PRD identified in step 1. Issue numbers restart at 1 within each PRD.
Create issues in dependency order (blockers first) so you can reference real issue identifiers in the "Blocked by" field.
---
status: todo
title: Short descriptive name (same as the slice title)
blocked_by: [1, 2]
---
Parent
A reference to the PRD at .agent-state/prds/<slug>/PRD.md.
What to build
A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation.
Acceptance criteria
status, title, and blocked_by MUST be present in the frontmatter — the next-issue script reads them. Use blocked_by: [] when there are no blockers.