Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
Installs into .claude/skills of the current project.
Are you the author of Bug Triage?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/furkantokkan-bug-triage)
---
name: bug-triage
description: >-
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
---
# Bug Triage
Codex port of Claude Code Game Studios /bug-triage.
Use this skill when the task matches the workflow described below. Keep the
Codex version lightweight: load `references/claude-skill.md` only when the
original detailed Claude workflow is needed.
## Codex Workflow
1. Read repository-local instructions first: `AGENTS.md`, `CLAUDE.md`, the
nearest path-scoped instructions (`Assets/CLAUDE.md` for Unity when present),
and any referenced project docs.
2. Use this workflow's intent, but follow Codex tool and collaboration rules.
3. Apply SOLID, Clean Code, clear English naming, dependency boundaries, and
focused tests for new or changed expected behavior.
4. When a Claude workflow mentions a custom agent, treat it as a role reference.
Do the work locally unless the user explicitly asks for sub-agents or
parallel agent work.
5. For implementation tasks, make the change directly when the request is clear;
ask only when a decision cannot be safely inferred from local context.
6. Verify with the repository's available checks and summarize changed files,
tests run, and residual risk.
## Original Workflow Summary
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
Before assigning a duplicate, reconcile each report with tracked task
acceptance, preserved behavior, and defect ledgers. Route owned same-task
failures to `$task-bug [<ID>] "<feedback>"` as `TRACKED_TASK_DEFECT`;
`task-bug` resolves/dispatches and `task-cycle` alone creates/deduplicates
stable linked `D-xxx` rows and records. Keep standalone
triage only for unowned or genuinely separate bugs.
## Detailed Reference
- Original Claude skill: `references/claude-skill.md`
