원클릭으로
professor-triage
Analyze GitHub issues against the current codebase and perform automated triage with priority assessment
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Analyze GitHub issues against the current codebase and perform automated triage with priority assessment
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | professor-triage |
| description | Analyze GitHub issues against the current codebase and perform automated triage with priority assessment |
| scope | harness |
| version | 2.4.0 |
| user-invocable | true |
| effort | high |
| context | fork |
| argument-hint | [issue-numbers...] [--label <label>] [--state <state>] [--since <date>] |
Analyze GitHub issues against the current codebase. For each issue, search relevant code, assess impact and blast radius, determine whether the issue has already been resolved, and perform low-risk triage actions with evidence.
Full phase detail: guides/professor-triage/phases.md
Checklist: guides/professor-triage/checklists.md
/professor-triage
/professor-triage 587 589 590
/professor-triage --label codex-release
/professor-triage --since 2026-03-20
| Phase | Name | Owner | Notes |
|---|---|---|---|
| 1 | Gather | Orchestrator | Fetch issue metadata and labels |
| 2 | Codebase Analysis | Explore agents | Parallel code search and evidence mapping |
| 3 | Cross-Analyze | Orchestrator or synthesis agent | Duplicate, priority, and action decisions |
| 4 | Multi-Perspective Output | delegated analysis agents | Architect, colleague, professor synthesis, artifact |
| 5 | Act | mgr-gitnerd | Labels, comments, close decisions |
| Phase | Agent | Claude compatibility Agent mode |
|---|---|---|
| Phase 2 codebase search | Explore | bypassPermissions when active |
| Phase 4A Senior Architect | general-purpose | bypassPermissions when active |
| Phase 4B Project Colleague | general-purpose | bypassPermissions when active |
| Phase 4C Professor Synthesis | general-purpose | bypassPermissions when active |
| Phase 4D triage comment | mgr-gitnerd | bypassPermissions when active |
| Phase 4E artifact report | general-purpose | bypassPermissions when active |
| Phase 5 GitHub actions | mgr-gitnerd | bypassPermissions when active |
Agent selection constraint: artifact-writing delegated agents need Bash access for compatibility-path bypasses. Do not use an agent whose tool policy prevents the required artifact protocol.
Codex-native artifacts go under .codex/outputs/sessions/YYYY-MM-DD/professor-triage-HHmmss.md and may be written with the repo's normal file-write APIs.
If a delegated task must create, inspect, or modify Claude compatibility artifacts under .claude/**, .claude/outputs/**, or templates/.claude/**, include this block in the delegated prompt:
Sensitive-path compatibility note:
1. Keep Codex-native .codex/** artifacts on the normal file-write path.
2. On Claude Code v2.1.121+ with bypassPermissions, direct writes to .claude/skills/, .claude/agents/, and .claude/commands/ are allowed.
3. On Claude Code v2.1.126+ with bypassPermissions, broader protected paths such as .claude/**, .git/**, and .vscode/** are also covered.
4. Use /tmp/professor-triage-<timestamp>.md only as a legacy fallback when the runtime is older or still prompts, then verify the resulting diff.
This protocol must be inline in the delegate prompt; relying on this SKILL.md being present in the parent context is not enough.
Automatic, low-risk actions:
verify-done only after evidence is current.P1/P2/P3 when supported by analysis.Confirmation required: issue reopen, new issue creation, epic rewrites, or issue body modification.
Claude compatibility Agent calls only (R010 “Delegated Permission Ownership”): Pass mode: "bypassPermissions" when the active Claude session uses bypass permissions. Native Codex spawn_agent has no mode parameter; use the installed agent_type and active Codex runtime permissions instead.
6-stage structured development cycle with stage-based tool restrictions
Multi-angle release quality verification using parallel expert review teams
Full Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.
Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline
Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile