Prd

• Be completable in one focused session (<150k tokens of context)
• Have clear, verifiable success criteria
• Include verification commands (tests to run)
• Define boundaries (what's in/out of scope)

Ticket Structure

## 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

Boundaries

In Scope

• What this ticket covers

Out of Scope

• What should be separate tickets

## 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.

Discovering Related Work

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.

Best Practices

1. Size tickets appropriately - Each should be 1-4 hours of focused work
2. Include test commands - Always specify how to verify completion
3. Be explicit about scope - Prevent scope creep with clear boundaries
4. Use Labels - Add agent-ready label for tickets ready for AI implementation
5. Establish dependencies - Use --blocked-by and --depends-on to show work order
6. Search first - Check for existing related issues before creating duplicates