메뉴
Use when the autopilot orchestrator restarts after a crash or interruption and must scan existing checkpoints, detect partial state, and determine the safe resume point. Not for direct user invocation; skip outside the orchestrator main thread.
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 the user invokes /slim-task or requests structured multi-phase task execution (structured task, SOP execution, parallel sub-agent dispatch) with blind-audit quality review.
Use when autopilot orchestrator enters Phase 1 to understand requirements, drive multi-round clarification, and produce the structured requirement packet checkpoint.
Use when the autopilot orchestrator enters Phase 5 after Phase 4 test case design has been approved and is about to choose an implementation path (parallel, serial, or TDD) and dispatch implementation work.
Use when the autopilot orchestrator reaches Phase 7 after Phase 6 tri-path reports are available and must finalize the delivery by collecting summaries, extracting knowledge, previewing Allure, and evaluating archive readiness.
Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "implement component", "figma to code", "figma 转代码", "figma 还原", "实现设计稿", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`. For full-screen design generation in Figma, use `figma-generate-design`.
Use when the autopilot orchestrator main thread is about to dispatch a phase-specific sub-agent via the Task tool and needs the JSON envelope contract, explicit path injection, and parameterized prompt templates. Not for direct user invocation; skip when the current context is not the autopilot orchestrator.
| name | autopilot-recovery |
| description | Use when the autopilot orchestrator restarts after a crash or interruption and must scan existing checkpoints, detect partial state, and determine the safe resume point. Not for direct user invocation; skip outside the orchestrator main thread. |
| user-invocable | false |
前置条件自检：本 Skill 仅在 autopilot 编排主线程中使用。如果当前上下文不是 autopilot 编排流程，请立即停止并忽略本 Skill。
在 autopilot 启动时（Phase 0.4）扫描已有 checkpoint，决定起始阶段。
state-snapshot.json 是恢复控制面的唯一主工件snapshot_hash 一致性，hash 不匹配时 fail-closed（拒绝自动继续）resume_from_phase、discarded_artifacts、replay_required_tasks、recovery_reason、recovery_confidence| 脚本 | 用途 |
|---|---|
runtime/scripts/recovery-decision.sh | 确定性恢复扫描（纯只读，JSON 输出，含 state-snapshot.json 校验） |
runtime/scripts/clean-phase-artifacts.sh | 统一清理阶段制品 + 事件过滤 + git 状态回退 + state-snapshot.json 清理 |
本 Skill 通过 recovery-decision.sh 间接使用 runtime/scripts/_common.sh 提供的以下共享函数：
| 函数 | 用途 |
|---|---|
scan_all_checkpoints(phase_results_dir, mode) | 按阶段顺序扫描全部 checkpoint，返回 JSON 结果 |
get_last_valid_phase(phase_results_dir, mode) | 返回最后一个 status=ok/warning 的阶段编号（含 gap 检测） |
get_gap_phases(phase_results_dir, mode) | 返回 gap 阶段列表 |
get_phase_sequence(mode) | 返回模式对应的阶段序列 |
get_next_phase_in_sequence(current, mode) | 返回序列中下一阶段编号 |
read_phase_commit_sha(project_root, phase, change_name) | 从 git 历史查找阶段 commit SHA（三级 fallback） |
read_lock_json_field(lock_file, field, default) | 提取锁文件 JSON 字段（mode、anchor_sha 等） |
| Step | 职责 | 详细协议 |
|---|---|---|
| 1 | 调用确定性扫描 | references/recovery-flow.md#step-1 |
| 1.5 | 自动继续判定 | references/recovery-flow.md#step-15 |
| 2 | 多 Change 选择 | references/recovery-flow.md#step-2 |
| 3 | 用户决策 | references/recovery-flow.md#step-3 |
| 4 | 执行恢复路径（路径 A/B/C） | references/recovery-flow.md#step-4 |
| 5 | 上下文重建 + Anchor SHA 验证 | references/recovery-flow.md#step-5 |
| 5.Mode | Mode 恢复 | references/recovery-flow.md#mode-恢复 |
执行前必须读取 references/recovery-flow.md 获取完整协议。 所有 Step、决策分支、JSON schema 字段、脚本调用、AskUserQuestion 文案、Anchor SHA 验证四分支等均以该文件为准。
崩溃恢复时需创建对应模式的阶段任务链，已完成的阶段直接标记为 completed，确保 blockedBy 依赖链正确。
Fixup Squash 时机: fixup 提交不在恢复阶段处理。Phase 7 归档时会自动执行
git rebase --autosquash将所有 fixup! 提交合并到对应的目标 commit 中。
| 模式 | 创建的任务 |
|---|---|
| full | Phase 1-7（7 个任务） |
| lite | Phase 1, 5, 6, 7（4 个任务） |
| minimal | Phase 1, 5, 7（3 个任务） |
当 config.phases.implementation.tdd_mode: true 时，Phase 5 恢复需扫描 phase5-tasks/task-N.json 的 tdd_cycle 字段，按状态映射到 RED/GREEN/REFACTOR 恢复点。完整协议（含状态映射表与恢复时验证步骤）详见 references/tdd-recovery.md。
scan-checkpoints-on-start.sh Hook 在会话启动时自动扫描 checkpoint 目录和 state-snapshot.json，输出摘要信息。本 Skill 在此基础上提供交互式恢复决策。
state-snapshot.json Schema 及消费方契约: 详见
references/state-snapshot-schema.md