stark-ai-de/agent-skills / incubator/skills/repo-maintenance/issue-triage
issue-triage
VerifiedTriage repository issues through a maintainer decision tree. Use when the user asks to classify issues, apply labels, identify missing information, mark ready-for-agent work, split vague reports, or clean up an issue inbox.
Issue Triage
Goal
Classify issues into actionable maintainer states, propose labels and responses, and identify what is needed before an agent or human should work on them.
When to use
- The user asks to triage GitHub, GitLab, Linear, or markdown issues.
- An inbox needs labels, status, duplicate detection, or missing information checks.
- A vague issue needs to be split into smaller work items.
When not to use
- The user asks for implementation rather than issue classification.
- The task is reviewing a pull request; use
pr-review. - The issue appears security-sensitive and should go through private reporting first.
Inputs
- Issue title, body, comments, labels, assignees, linked PRs, and project state.
- Repository docs, contribution rules, issue templates, and label conventions.
- Live tracker data when the user asks for real issue changes.
Inputs to inspect
- Inspect issue content, linked code/docs, existing labels, and tracker state needed to classify the issue.
- Check repository triage conventions before inventing labels.
Process
- Read the issue and linked context.
- Determine category: bug, feature, docs, question, duplicate, wontfix, maintenance, or security.
- Determine readiness: needs reporter, needs maintainer, ready for agent, ready for human, blocked, or duplicate.
- Propose labels and a concise maintainer response.
- Split broad issues into concrete follow-up issues when needed.
- Ask for approval before applying labels, closing, assigning, or editing issues unless the user explicitly authorized those actions.
Workflow
Use the process above to produce a proposed triage result first. Apply live issue changes only when the user has explicitly authorized that action.
Decision points
- If reproduction steps are missing for a bug, mark
needs-info. - If expected behavior is a product decision, mark
needs-maintainer. - If scope and validation are clear, mark
ready-for-agent. - If the report may be security-sensitive, avoid public detail and escalate to the security policy.
Safety rules
- Do not close or label live issues without approval.
- Do not expose security details in public responses.
- Do not promise timelines or maintainer commitments.
References
Read only when needed:
references/triage-state-machine.mdfor readiness states.references/label-mapping.mdfor common labels.
Scripts
No bundled scripts.
Output format
Return:
- Triage decision
- Category
- Readiness state
- Suggested labels
- Missing information
- Draft response
- Recommended next action
Failure modes
- If issue details are unavailable, ask for the issue body, URL, or tracker access.
- If live tracker permissions fail, return the proposed changes as a draft.
- If duplicate status is uncertain, name the suspected duplicate and evidence gap.
Completion criteria
- Every issue has a category, readiness state, and next action.
- Proposed tracker changes are separated from actions already taken.
- Missing information is specific enough for the reporter or maintainer to answer.
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: 471k | 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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |