diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-ops-tasks
agent-ops-tasks
VerifiedCreate, refine, and manage issues. Use for creating new issues from loose ideas, refining ambiguous issues, bulk operations, or JSON export.
Issue Management
Works with or without aoc CLI installed. All operations can be performed via direct file editing.
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
.agent/issues/references/and link it in the issue. - 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 |
|---|---|
.agent/issues/critical.md | Blockers, production issues |
.agent/issues/high.md | Important, address soon |
.agent/issues/medium.md | Standard work |
.agent/issues/low.md | Nice-to-have |
.agent/issues/backlog.md | Unprioritized ideas |
.agent/issues/history.md | Completed/archived |
Operations
Create Issue
- Analyze request for type, title, priority, scope, criteria
- Use
agent-ops-interviewfor missing info - 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
priorityfield - 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 |
|---|---|
baseline | Warnings, failures, missing coverage |
planning | Sub-tasks, prerequisites |
critical-review | 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
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 468k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |