Claude-skill-registry agent-ops-tasks
Create, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operations, or JSON export.
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/agent-ops-tasks" ~/.claude/skills/majiayu000-claude-skill-registry-agent-ops-tasks && rm -rf "$T"
manifest:
skills/data/agent-ops-tasks/SKILL.mdsource content
Issue Management
Works with or without
CLI installed. All operations can be performed via direct file editing.aoc
CRITICAL: Issue Management ONLY
This skill manages issues. It NEVER implements code.
- ✅ Create, refine, list, search, triage issues
- ✅ Move issues between priority files
- ❌ NEVER implement features or fix bugs
- ❌ NEVER modify code files
After any issue operation, ALWAYS offer a handoff — never auto-proceed.
Reference: See REFERENCE.md for templates, CLI commands, JSON export.
Issue ID Format
Format:
{TYPE}-{NUMBER}@{HASH}
Example: BUG-0023@efa54f, FEAT-0001@c2d4e6
Types:
BUG | FEAT | CHORE | ENH | SEC | PERF | DOCS | TEST | REFAC | PLAN
Minimal Issue Template
## {TYPE}-{NUMBER}@{HASH} — {title} id: {TYPE}-{NUMBER}@{HASH} title: "{title}" type: {type} status: todo | in_progress | done priority: critical | high | medium | low description: {brief description} details: references/{TYPE}-{NUMBER}@{HASH}.md ### Acceptance Criteria - [ ] Criterion 1 ### Log - YYYY-MM-DD: Created
Issue Size Guardrails
- Keep backlog items minimal: title, metadata, 1–2 sentence description, acceptance criteria if known.
- If an issue needs more than ~20 lines, move details to a reference file in
and link it in the issue..agent/issues/references/ - Reference files should contain research, long descriptions, examples, diagrams, or interview notes.
- Never embed large code blocks or research dumps directly in backlog items.
Reference File Format
- Path:
.agent/issues/references/{ISSUE-ID}.md - Include a short header and a link back to the issue.
- Example:
# {ISSUE-ID} — {title} Moved from backlog.md on YYYY-MM-DD. ## Context ...
File Organization
| File | Priority |
|---|---|
| Blockers, production issues |
| Important, address soon |
| Standard work |
| Nice-to-have |
| Unprioritized ideas |
| Completed/archived |
Operations
Create Issue
- Analyze request for type, title, priority, scope, criteria
- Use
for missing infoagent-ops-interview - Generate ID from
.agent/issues/.counter - Create issue, append to priority file
- STOP AND HANDOFF
Mandatory Handoff
✅ Issue created: {ISSUE-ID}: {title} What's next? 1. Start implementing (requires confirmation) 2. Create more issues 3. Do nothing
Refine Issue
Triggers for refinement:
- Generic titles ("Fix bugs")
- Missing acceptance criteria
- Confidence marked
low
Procedure: Interview for scope, criteria, dependencies, risks.
Change Priority
- Remove from current file
- Update
fieldpriority - Add log entry
- Append to new file
Triage Backlog
For each backlog item: assign priority or skip/delete.
Issue Discovery
Other skills invoke discovery when they find potential work:
| Skill | Triggers |
|---|---|
| Warnings, failures, missing coverage |
| Sub-tasks, prerequisites |
| Bugs, security, tech debt |
Procedure:
- Collect findings
- Categorize by type/priority
- Present summary to user
- Create issues on confirmation
- Offer next actions
Quality Checklist
- Valid ID format
- Action-oriented title
- Testable acceptance criteria
- Appropriate confidence level