prd-to-issues
PRD to Issues
Break a PRD into independently-grabbable Linear issues using vertical slices (tracer bullets).
Process
1. Locate the PRD
Ask the user for the PRD Linear issue identifier (e.g. TEAM-123).
If the PRD is not already in your context window, fetch it using the Linear MCP get_issue tool.
2. Explore the codebase (optional)
If you have not already explored the codebase, do so to understand the current state of the code.
3. Draft vertical slices
Break the PRD 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.
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 from the PRD this addresses
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?
- Which Linear team should the issues be created in?
Iterate until the user approves the breakdown.
5. Create the Linear issues
For each approved slice, create a Linear issue using the Linear MCP save_issue tool (title, description, team). Use the issue body template below.
Create issues in dependency order (blockers first) so you can reference real Linear identifiers in the blockedBy and relatedTo fields.
- Set
relatedTo: [<prd-issue-id>]on every child issue to link back to the parent PRD - Set
blockedBy: [<issue-id>, ...]to express intra-slice dependencies using Linear's native relations
What to build
A concise description of this vertical slice. Describe the end-to-end behavior, not layer-by-layer implementation. Reference specific sections of the parent PRD rather than duplicating content.
Acceptance criteria
- Criterion 1
- Criterion 2
- Criterion 3
User stories addressed
Reference by number from the parent PRD:
- User story 3
- User story 7
Do NOT close or modify the parent PRD issue.
More from maxmurr/agents-skills
submit-pr
Submit implementation as a pull request. Runs tests, creates a PR with the Linear issue linked, and posts the PR URL as a comment on the Linear issue. Use when implementation is complete and user wants to open a PR, submit work, or create a pull request.
2index-knowledge
Generate hierarchical AGENTS.md + CLAUDE.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation with both file types.
2tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
1atdd
Outside-in TDD with double-loop (acceptance + unit). Use when user wants acceptance-test-driven development, outside-in TDD, London-school TDD, GOOS-style development, or wants to drive design from user-facing behavior inward.
1write-a-prd
Create a PRD through user interview, codebase exploration, and module design, then submit as a Linear issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
1start-issue
Kick off implementation of a Linear issue. Fetches the issue and its parent PRD, creates a git branch using Linear's suggested branch name, and presents a consolidated context summary ready for development. Use when starting work on a Linear issue, picking up a ticket, or when user says "start issue TEAM-123", "work on TEAM-123", or "pick up TEAM-123".
1