skills/prd/SKILL.md
Create agent-friendly Linear tickets with PRDs, sub-issues, and clear success criteria. Use when planning features or breaking down work for agentic coding.
npx skillsauth add alienfast/claude prdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an expert at breaking down features into well-structured, agent-friendly Linear tickets.
Use this skill when:
Understand the Request
Create the Epic/Parent Issue
Use linear issues create with:
Break Down into Sub-Issues Each sub-issue should:
Set Up Dependencies
Use --depends-on and --blocked-by to create proper dependency chains.
## Problem/Context
[1-2 sentences explaining why this work is needed]
## Requirements
### Must Have
- [ ] Requirement 1
- [ ] Requirement 2
### Nice to Have
- [ ] Optional feature
## Success Criteria
- [ ] Specific, testable criterion 1
- [ ] Specific, testable criterion 2
## Verification
```bash
# Commands to verify the work is complete
make test
npm run lint
## Example Commands
```bash
# Create parent issue with description from file
~/.claude/scripts/linear-stdin.sh tmp/prd-description.md issues create "User Authentication System" \
--team ENG \
--priority 2 \
-d -
# Create sub-issue with inline description (short enough for a flag)
linear issues create "Implement OAuth2 login flow" \
--team ENG \
--parent ENG-100 \
--description "Implement OAuth2 with Google provider..."
# Create sub-issue with longer description from file
~/.claude/scripts/linear-stdin.sh tmp/sub-issue-description.md issues create "Add JWT refresh tokens" \
--team ENG \
--parent ENG-100 \
-d -
# Set dependencies
linear issues update ENG-102 --blocked-by ENG-101
Important: For any description or body content longer than a single line, write it to tmp/ first and use ~/.claude/scripts/linear-stdin.sh to pass it via stdin. Do NOT use shell operators (<, |, $()) in Bash commands — they trigger permission prompts regardless of allow-list rules.
Before creating tickets, search for existing related work:
# Find existing work on this topic
linear search "authentication" --team ENG
# Check if dependencies already exist
linear search "OAuth" --has-dependencies --team ENG
# Look for potential blockers
linear search "user database" --team ENG
Pro tip: Use /link-deps skill after creating tickets to discover and establish dependencies.
agent-ready label for tickets ready for AI implementation--blocked-by and --depends-on to show work ordertesting
End-to-end Linear issue macro — runs /start then /finish in sequence, gated on the /quality-review verdict. Worktree mode is opt-in via the `wt` token, mirroring /start. Pauses only for plan approval and the deferred-items filing decision; otherwise autonomous. Use when the user says 'full PL-XX', 'ship PL-XX end-to-end', or invokes /full.
development
Adversarial implementation review with triage and fix loop. Hard-gates on `pnpm check`, delegates to the quality-reviewer agent for categorized findings (Critical/High/Medium/Nice-to-Have/Approved), then triages and fixes findings via the developer agent. Loops until a re-review surfaces no new Critical/High/Medium findings (convergence), with a soft ceiling of 5 cycles before asking the user how to proceed; option 3 of that prompt terminates with verdict `escalated-to-architect`. Use when the user says 'review my work', 'check this implementation', 'adversarial review', 'quality review', or invokes /quality-review.
testing
Triage and prioritize Linear backlog. Analyzes issues for staleness, blockers, and suggests priorities based on dependencies and capacity.
testing
Start working on a Linear issue — check blockers, assign, move to In Progress, create branch, plan implementation, execute with checkpoint updates, review and triage findings. Use when the user says 'start issue', 'work on PL-XX', 'begin PL-XX', or invokes /start.