메뉴
Use when the user says they are stepping away and the agent should continue without interactive approvals
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
Use when running e2e tests, debugging test failures, or fixing flaky tests. Covers failure taxonomy, fix rules, and workflow. Never changes source code logic or API without spec backing.
Use when auditing how well the shared agent instructions (AGENTS.md, skills) hold up in real sessions — sampling transcripts via recall, scoring them against the gap rubric, and turning findings into ratified amendments
Use when preparing clean, logical git commits from an existing working tree
Use when syncing a feature branch onto the latest origin base branch via git rebase.
Fetch latest from origin, prune remote-tracking refs, delete stale local branches and worktrees, and fast-forward important branches. Use when tidying up a worktree-based repo layout.
Use when preserving enough task context for another agent or future session to continue without the current conversation
| name | afk |
| description | Use when the user says they are stepping away and the agent should continue without interactive approvals |
The user is away: no interactive approval will arrive. Campaign protocol —
scope derivation, the unblocking ladder, terminal states, budgets — is the
loop-brief skill's; when a LOOP.md charter exists, run its iterations.
This skill adds the operational constraint: nothing you run may block on a
prompt.
Derive scope from committed artifacts: LOOP.md, handoffs, specs, recent
commit messages. Uncovered decisions climb the ladder — reversible interior
calls are made and logged as dated provisional Decisions, not accumulated.
Terminate per the loop's terminal states (done, blocked: needs N decisions with a numbered evidenced batch, or budget-exhausted), and
write back the charter — or a handoff when no charter exists — before
stopping.
