pkg/embedded/templates/specledger/skills/sl-issue-tracking/SKILL.md
# sl Issue Tracking ## Overview `sl issue` is the built-in issue tracker for SpecLedger. Use it for multi-session work with complex dependencies; use TodoWrite for simple single-session tasks. ## When to Use sl issue vs TodoWrite ### Use sl issue when: - **Multi-session work** - Tasks spanning multiple compaction cycles or days - **Complex dependencies** - Work with blockers, prerequisites, or hierarchical structure - **Knowledge work** - Strategic documents, research, or tasks with fuzzy bo
npx skillsauth add specledger/specledger pkg/embedded/templates/specledger/skills/sl-issue-trackingInstall 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.
sl issue is the built-in issue tracker for SpecLedger. Use it for multi-session work with complex dependencies; use TodoWrite for simple single-session tasks.
Key insight: If resuming work after 2 weeks would be difficult without sl issue, use sl issue. If the work can be picked up from a markdown skim, TodoWrite is sufficient.
At session start, always check for available work:
# Find ready-to-work issues (not blocked by dependencies)
sl issue ready
# Check in-progress issues
sl issue list --status in_progress
# See all open issues (including blocked)
sl issue list --status open
Report format:
Create new issue:
sl issue create --title "Fix login bug" --type bug
sl issue create --title "Add OAuth" --type feature --priority 0
sl issue create --title "Write tests" --description "Unit tests for auth module"
List issues:
sl issue list # All open issues
sl issue list --status in_progress # In-progress only
sl issue list --all # All issues across all specs
sl issue list --label "phase:setup" # Filter by label
sl issue list --tree # Show dependency tree
Find ready issues (unblocked):
sl issue ready # Issues ready to work on (not blocked)
sl issue ready --all # Ready issues across all specs
sl issue ready --json # JSON output for scripting
Show issue details:
sl issue show SL-abc123 # Full details
sl issue show SL-abc123 --tree # Show dependency context (blocks/blocked by)
Update issue:
sl issue update SL-abc123 --status in_progress
sl issue update SL-abc123 --priority 0
sl issue update SL-abc123 --notes "COMPLETED: Login endpoint. NEXT: Session middleware"
Close issue:
sl issue close SL-abc123 --reason "Implemented in PR #42"
| Type | Description |
|------|-------------|
| task | Standard work item (default) |
| bug | Defect or problem |
| feature | New functionality |
| epic | Large work with subtasks |
| chore | Maintenance or cleanup |
| Priority | Description |
|----------|-------------|
| 0 | Critical (highest) |
| 1 | High |
| 2 | Normal (default) |
| 3 | Low |
Use labels for categorization:
spec:<slug> - Feature spec this issue belongs tophase:<name> - Setup, US1, polish, etc.story:<id> - User story traceabilitycomponent:<area> - Mapping to plan-defined modulesUpdate issue notes at these checkpoints:
Critical triggers:
Notes format:
COMPLETED: Specific deliverables
IN PROGRESS: Current state + next immediate step
BLOCKERS: What's preventing progress
KEY DECISIONS: Important context or user guidance
NEXT: Immediate next action
Example:
sl issue update SL-abc123 --notes "COMPLETED: JWT auth with RS256. KEY DECISION: RS256 over HS256 per security review. IN PROGRESS: Password reset flow. BLOCKERS: Waiting on user decision for token expiry. NEXT: Implement rate limiting."
During exploration or implementation, proactively file issues for:
sl issue create --title "Found: auth doesn't handle profile permissions"
Mark issues in_progress when starting work:
sl issue update SL-abc123 --status in_progress
Update throughout work and close when complete:
sl issue close SL-abc123 --reason "Implemented with tests passing"
For complex multi-step work, structure issues with dependencies:
# Create epic
sl issue create --title "Implement user authentication" --type epic
# Create subtasks
sl issue create --title "Set up OAuth credentials" --type task
sl issue create --title "Implement authorization flow" --type task
# Link dependencies
sl issue link SL-epic blocks SL-credentials
sl issue link SL-credentials blocks SL-flow
Link issues:
sl issue link SL-abc123 blocks SL-def456 # abc123 blocks def456
sl issue link SL-abc123 related SL-xyz789 # related but not blocking
View dependencies:
sl issue show SL-abc123 # Shows linked issues
sl issue show SL-abc123 --tree # Shows dependency context
sl issue list --tree # Shows all issues as dependency tree
Find unblocked work:
sl issue ready # Issues not blocked by open dependencies
Before closing an issue, verify:
Use sl issue show <id> to review issue details before closing.
Both tools complement each other at different timescales:
TodoWrite (short-term working memory - this hour):
sl issue (long-term episodic memory - this week/month):
Pattern:
If issues seem lost:
sl issue list --all # See all issues across specs
If issue not found:
Lock file issues:
.issues.jsonl.lock) prevent concurrent accessFor full flag details, run sl issue <subcommand> --help.
testing
Manage agent skills from the skills.sh registry — search, install, audit, and remove community-built skills
testing
# sl Dependency Management **When to Load**: Triggered when tasks involve cross-repo specification dependencies, `sl deps` commands, artifact caching, or multi-repo dependency resolution. ## Overview `sl deps` manages external specification dependencies between repositories. Dependencies are declared in `specledger.yaml`, cached locally at `~/.specledger/cache/`, and optionally symlinked into your project's artifacts directory for direct access. ## Subcommands | Command | Purpose | Output M
tools
# sl-comment Skill **When to Load**: Triggered when AI commands mention "review comments", "comment", or reference `sl comment` CLI. ## Overview The `sl comment` CLI provides review comment management for SpecLedger projects. Comments are stored in Supabase and accessed via the PostgREST API. ## Subcommands | Command | Purpose | Output Mode | |---------|---------|-------------| | `sl comment list [branch-name] [-R owner/repo]` | List all comments (compact) | Truncated previews, reply counts
development
# sl Audit Skill ## Overview Codebase reconnaissance skill for understanding project structure, tech stack, and module organization. This skill provides patterns for efficient codebase exploration without AI orchestration overhead. **Layer**: L3 (Skill) - Passive context injection **Use when**: You need to understand an unfamiliar codebase or validate architecture assumptions ## When to Load Load this skill when: - First encounter with an unfamiliar codebase - Need to understand project str