controller
Top-level workflow controller that manages phase transitions for OCMUI bug resolution
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Top-level workflow controller that manages phase transitions for OCMUI bug resolution
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Root cause analysis for bugs
Create PR description and recommend Jira updates
Implement bug fix following UHC Portal standards
Create draft pull request
Systematically reproduce bugs in a controlled environment
Bug scrubbing and triage for OCMUI Interruption Catcher duties
| name | controller |
| description | Top-level workflow controller that manages phase transitions for OCMUI bug resolution |
You are the workflow controller. Your job is to manage the OCMUI bugfix workflow by executing phases and handling transitions between them.
Scrub (/scrub) — .claude/skills/scrub/SKILL.md
Evaluate unscrubbed bugs from the Defect Manager Dashboard. Determine if it's a bug, check reproducibility, verify priority, identify blockers.
Reproduce (/reproduce) — .claude/skills/reproduce/SKILL.md
Systematically reproduce the bug in a controlled environment.
Diagnose (/diagnose) — .claude/skills/diagnose/SKILL.md
Trace the root cause through code analysis, git history, and hypothesis testing.
Fix (/fix) — .claude/skills/fix/SKILL.md
Implement the fix following UHC Portal standards (TypeScript, React, PatternFly).
Test (/test) — .claude/skills/test/SKILL.md
Write unit tests (Jest/RTL), run yarn test-changes, create e2e tests (Playwright) if needed.
Document (/document) — .claude/skills/document/SKILL.md
Create PR description using team template, recommend Jira updates.
PR (/pr) — .claude/skills/pr/SKILL.md
Push to fork and create a draft pull request.
Phases can be skipped or reordered at the user's discretion.
.claude/skills/controller/SKILL.md)." This is very important so the user knows the workflow is working, learns about the available phases, and so skills can find their way back here.After each phase completes, present the user with options — not just one next step. Use the typical flow as a baseline, but adapt to what actually happened.
scrub → reproduce → diagnose → fix → test → document → pr
After presenting results, consider what just happened, then offer options that make sense:
Continuing to the next step — often the next phase in the flow is the best option
Skipping forward — sometimes phases aren't needed:
/fix alongside /reproduce/scrub, go to /reproduce/diagnose or /fix immediatelyGoing back — sometimes earlier work needs revision:
/fix to rework the implementation/scrub to reassess/diagnose again with new informationEnding early — not every bug needs the full pipeline:
/fix → /test → /pr/testLead with your top recommendation, then list alternatives briefly:
Recommended next step: /test — verify the fix with unit tests and coverage check.
Other options:
- /document — if you've already tested manually and want to prepare the PR
- /pr — if you're confident and want to submit immediately
After /scrub:
/diagnose or /fix immediatelyAfter /fix:
/test to run yarn test-changes and verify coverageAfter /test:
/test to add more tests/document to prepare PR descriptionAfter /document: