Engineer production-ready code with AI agent skills
Breaks plans, specs, or PRDs into independently-grabbable vertical-slice issues using tracer-bullet methodology for end-to-end feature delivery.
Maintainer of this project? Claim this page to edit the listing.
1.0.1Add to Favorites
Why it matters
Transform AI coding agents from verbose, misaligned code generators into disciplined engineering partners that build maintainable, well-tested applications through structured workflows, shared language, and feedback loops.
Outcomes
What it gets done
Align agent understanding through grilling sessions that build shared vocabulary and document architectural decisions
Drive test-driven development with red-green-refactor loops that ensure code actually works
Maintain codebase architecture by preventing entropy and rescuing projects from becoming unmaintainable
Debug systematically using structured diagnostic workflows instead of random code changes
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/ag-to-issues | bash Overview
To Issues
Transforms plans, specs, or PRDs into vertical-slice issues on your project tracker, where each issue cuts through all integration layers end-to-end. Use when you need to break down a plan into independently-grabbable issues using tracer-bullet vertical slices rather than horizontal layer-by-layer decomposition.
What it does
To Issues transforms high-level plans, specifications, or PRDs into a set of independently-grabbable issues on your project issue tracker. Each issue represents a tracer-bullet vertical slice that cuts through all integration layers end-to-end, ensuring every slice delivers a narrow but complete path through schema, API, UI, and tests.
When to use - and when NOT to
Use this skill when you need to break down a plan, spec, or PRD into actionable issues that can be picked up independently. It's designed for creating vertical slices where each issue is demoable or verifiable on its own, rather than horizontal slices that only touch one layer.
Do NOT use this skill if you prefer horizontal layer-by-layer decomposition, or if your workflow doesn't benefit from end-to-end vertical slicing.
Inputs and outputs
You provide a plan, spec, or PRD in the conversation context, or pass an issue reference (issue number, URL, or path) for the skill to fetch from your issue tracker.
You receive a proposed breakdown as a numbered list. The skill asks whether the granularity feels right, whether dependency relationships are correct, and whether any slices should be merged or split further. After you approve the breakdown, the skill publishes formatted issues to your issue tracker in dependency order.
Integrations
Requires a configured issue tracker that has been set up via /setup-matt-pocock-skills. The skill fetches issues from and publishes to this tracker, using the project's triage label vocabulary.
Who it's for
This skill is for users who need to decompose plans into independently-grabbable vertical slices. The published issues are considered ready for AFK agents and use the tracer-bullet approach to ensure each issue delivers a complete, testable path through the entire stack.
Source README
To Issues
When to Use
Use when this workflow matches the user request: Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Source: mattpocock/skills (MIT).
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.
Look for opportunities to prefactor the code to make the implementation easier. "Make the change easy, then make the easy change."
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.
- 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
- Any prefactoring should be done first
4. Quiz the user
Present the proposed breakdown as a numbered list. For each slice, show:
- Title: short descriptive name
- 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?
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.
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.
Do NOT close or modify any parent issue.
Limitations
- Requires the upstream tool, account, API key, or local setup when the workflow names one.
- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.
- Validate generated artifacts or recommendations against the user's real sources before treating them as final.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.