Add new commands, skills, and agents; remove token loading script
- Add groom, plan-issues, and roadmap commands - Add skills for backlog-grooming, forgejo, issue-writing, roadmap-planning - Add agents directory structure - Remove load-forgejo-token.sh and SessionStart hook (using fj auth instead) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
83
skills/backlog-grooming/SKILL.md
Normal file
83
skills/backlog-grooming/SKILL.md
Normal file
@@ -0,0 +1,83 @@
|
||||
# Backlog Grooming
|
||||
|
||||
How to review and improve existing issues.
|
||||
|
||||
## Grooming Checklist
|
||||
|
||||
For each issue, verify:
|
||||
|
||||
### 1. Title Clarity
|
||||
- [ ] Starts with action verb
|
||||
- [ ] Specific and descriptive
|
||||
- [ ] Understandable without reading description
|
||||
|
||||
### 2. Description Quality
|
||||
- [ ] Has clear summary
|
||||
- [ ] Explains the "why"
|
||||
- [ ] Provides enough context
|
||||
|
||||
### 3. Acceptance Criteria
|
||||
- [ ] Criteria exist
|
||||
- [ ] Each criterion is testable
|
||||
- [ ] Criteria are specific (not vague)
|
||||
- [ ] Complete set (nothing missing)
|
||||
|
||||
### 4. Scope
|
||||
- [ ] Not too broad (can complete in reasonable time)
|
||||
- [ ] Not too narrow (meaningful unit of work)
|
||||
- [ ] Clear boundaries (what's included/excluded)
|
||||
|
||||
### 5. Dependencies
|
||||
- [ ] Dependencies identified
|
||||
- [ ] No circular dependencies
|
||||
- [ ] Blocking issues are tracked
|
||||
|
||||
### 6. Labels
|
||||
- [ ] Type label (bug/feature/etc)
|
||||
- [ ] Priority if applicable
|
||||
- [ ] Component labels if applicable
|
||||
|
||||
## Common Issues to Fix
|
||||
|
||||
### Vague Titles
|
||||
- Bad: "Fix bug"
|
||||
- Good: "Fix login form validation on empty email"
|
||||
|
||||
### Missing Acceptance Criteria
|
||||
Add specific, testable criteria based on the description.
|
||||
|
||||
### Scope Creep
|
||||
If issue covers multiple features, split into separate issues.
|
||||
|
||||
### Stale Issues
|
||||
- Close if no longer relevant
|
||||
- Update if context has changed
|
||||
- Add "needs-triage" label if unclear
|
||||
|
||||
### Duplicate Issues
|
||||
- Close duplicate with reference to original
|
||||
- Merge relevant details into original
|
||||
|
||||
## Grooming Workflow
|
||||
|
||||
1. **Fetch open issues**: `fj issue search -s open`
|
||||
2. **Review each issue** against checklist
|
||||
3. **Improve or flag** issues that need work
|
||||
4. **Update issue** with improvements: `fj issue edit <n> --body "..."`
|
||||
5. **Add labels** as needed: `fj issue label add <n> <label>`
|
||||
|
||||
## Questions to Ask
|
||||
|
||||
When grooming, consider:
|
||||
- "Could a developer start work on this today?"
|
||||
- "How will we know when this is done?"
|
||||
- "Is the scope clear?"
|
||||
- "Are dependencies explicit?"
|
||||
|
||||
## Batch Grooming
|
||||
|
||||
When grooming multiple issues:
|
||||
1. List all open issues
|
||||
2. Categorize by quality (ready, needs-work, stale)
|
||||
3. Focus on "needs-work" issues
|
||||
4. Present summary of changes made
|
||||
Reference in New Issue
Block a user