execute

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Execute

Apply the changes that

plan.md

describes. Stay strictly inside the plan; never improvise.

应用

plan.md

中描述的变更。严格遵循计划内容，切勿自行发挥。

Gate (run first)

Gate（先执行）

Read
```
.handoff/config.md
```
. If missing, abort:
❌ No config found. Run
```
/setup-handoff
```
first.
Read
```
.handoff/plan.md
```
. If missing, abort:
❌ No plan found. Run
```
/plan
```
first.
Both present → proceed.
If plan has
```
## Phases
```
and a phase is marked
```
[🔄]
```
, only that phase's change list is in scope. Phases marked
```
[x]
```
are already done; phases marked
```
[ ]
```
are future work for later cycles.

读取
```
.handoff/config.md
```
。若文件缺失，则终止操作：
❌ 未找到配置文件，请先运行
```
/setup-handoff
```
。
读取
```
.handoff/plan.md
```
。若文件缺失，则终止操作：
❌ 未找到计划文件，请先运行
```
/plan
```
。
若两者均存在，则继续执行。
若计划包含
```
## Phases
```
章节且某阶段标记为
```
[🔄]
```
，则仅该阶段的变更列表在处理范围内。标记为
```
[x]
```
的阶段已完成；标记为
```
[ ]
```
的阶段为后续周期的待办工作。

Output language

输出语言

All output from this skill — conversational replies to the user, status messages, blocker reports, AND

task.md

notes — uses the language specified by

config.md

response_language

. Default if config missing or field absent:

en

. Code edits, file paths, command syntax, and shell command output stay in their native language.

本技能的所有输出——包括对用户的对话回复、状态消息、阻塞报告以及

task.md

中的注释——均使用

config.md

中

response_language

指定的语言。若配置文件缺失或该字段未设置，默认语言为

en

。代码编辑内容、文件路径、命令语法和Shell命令输出保持其原生语言不变。

Workflow

工作流

Read
```
plan.md
```
end-to-end.
Create
```
.handoff/task.md
```
with one checkbox per change list entry plus one per sync command.
Check for parallelization. If
```
plan.md
```
has a
```
## Parallelization
```
section AND your host agent supports parallel subagent dispatch (e.g., Claude Code's Task tool), dispatch one subagent per independent group instead of applying sequentially in step 4. The dispatcher (this skill instance) owns
```
task.md
```
updates; subagents apply file edits only and report completion per file. Wait for all subagents before running sync commands (step 5). If a subagent hits a blocker, follow the blocker protocol in boundaries.md. If host doesn't support parallel dispatch or no
```
## Parallelization
```
section exists, fall back to sequential application below.
Interaction with risk tags: in parallel dispatch mode, the per-item compile-check granularity from step 4 does NOT apply — subagents do file edits only, and only the final safety-net check (step 6) runs. If a plan has
```
medium
```
or
```
high
```
risk-tagged items inside a parallelizable group, those items lose their per-item compile-check safety. Plan authors are expected to keep high-risk items out of
```
## Parallelization
```
groups (see plan/SKILL.md step 6); if you encounter this combination during execute, proceed but note it in the final task.md notes section.
For each change list item, apply per its risk tag (plans without tags are treated as low):
- low / untagged: apply edits, update task.md after each. No per-item compile check.
- medium: apply edits → run compile check (config's
```
typecheck
```
  , if set) → update task.md. On failure, see step 6.
- high: apply edits → run compile check → update task.md immediately (so progress is durable across blockers) → only then proceed. On failure, see step 6.
After code edits done, run sync commands one by one. Update task.md per command.
Final compile check (safety net). If
```
config.md
```
has a
```
typecheck
```
command, run it. Skipped if config has no typecheck or plan explicitly opts out via
```
(none — ...)
```
in a
```
## Compile check
```
plan section.
- Pass → continue to step 7.
- Fail → make at most ONE fix attempt, restricted to files/lines listed in the current change list. Re-run.
- Still fail (or fix would require touching out-of-plan files) → blocker. STOP and report per Boundaries.

Print:

✅ task.md updated. All planned changes applied. Compile check ✅.
Next step: /verify (strongly recommended in a fresh chat)

完整读取
```
plan.md
```
。
创建
```
.handoff/task.md
```
，为每个变更列表条目和每条同步命令添加一个复选框。
检查并行化支持。若
```
plan.md
```
包含
```
## Parallelization
```
章节，且宿主Agent支持并行子Agent调度（例如Claude Code的Task工具），则为每个独立组调度一个子Agent，而非按顺序执行步骤4。调度器（本技能实例）负责更新
```
task.md
```
；子Agent仅执行文件编辑操作，并按文件报告完成情况。在执行同步命令（步骤5）前，需等待所有子Agent完成任务。若子Agent遇到阻塞，请遵循boundaries.md中的阻塞处理协议。若宿主不支持并行调度或不存在
```
## Parallelization
```
章节，则回退至以下顺序执行流程。
与风险标签的交互：在并行调度模式下，步骤4中的逐项编译检查粒度规则不适用——子Agent仅执行文件编辑，仅在最终安全检查（步骤6）时运行编译检查。若计划中某可并行组包含标记为
```
medium
```
或
```
high
```
风险的条目，这些条目将失去逐项编译检查的安全保障。计划编写者应将高风险条目排除在
```
## Parallelization
```
组之外（详见plan/SKILL.md步骤6）；若在执行过程中遇到此类组合，可继续执行，但需在最终的task.md注释部分记录该情况。
针对每个变更列表条目，根据其风险标签（无标签的计划视为低风险）执行操作：
- 低风险/无标签：应用编辑内容，完成后更新task.md。不执行逐项编译检查。
- 中风险：应用编辑内容 → 运行编译检查（若配置中设置了
```
typecheck
```
  ） → 更新task.md。若检查失败，请参见步骤6。
- 高风险：应用编辑内容 → 运行编译检查 → 立即更新task.md（确保进度在阻塞情况下仍可持久保存） → 之后再继续执行。若检查失败，请参见步骤6。
代码编辑完成后，依次运行同步命令。每完成一条命令，更新task.md。
最终编译检查（安全保障）。若
```
config.md
```
中包含
```
typecheck
```
命令，则运行该命令。若配置中无typecheck命令，或计划在
```
## Compile check
```
章节中明确通过
```
(none — ...)
```
选择跳过，则不执行该检查。
- 检查通过 → 继续执行步骤7。
- 检查失败 → 最多尝试一次修复，修复范围仅限当前变更列表中列出的文件/代码行。重新运行检查。
- 仍失败（或修复需要修改计划外文件） → 触发阻塞。停止操作并按照边界规则报告。

输出：

✅ task.md已更新。所有规划变更已应用。编译检查✅。
下一步：/verify（强烈建议在新对话中执行）

Boundaries

边界规则

See boundaries.md. Critical points:

Only run: commands listed under "Sync commands" in the plan, AND the
```
typecheck
```
command from
```
config.md
```
(read-only compile check).
Never run tests or lint — those belong to /verify. Anything that mutates files (e.g.
```
eslint --fix
```
, formatters) stays in /verify regardless.
Risk tags only adjust check granularity. They never grant authority to edit files outside the plan.
Compile-fail recovery: at most one fix attempt within the plan's listed files/lines. If that doesn't resolve it, blocker.
Never modify plan.md.
If a critical blocker is discovered (the plan can't be executed as written), STOP, print:
```
⚠️  Blocker: <description>. Plan needs revision — run `/plan` again.
```
Do NOT improvise around it.

详见boundaries.md。关键要点：

仅允许运行：计划中“Sync commands”下列出的命令，以及
```
config.md
```
中的
```
typecheck
```
命令（只读编译检查）。
切勿运行测试或代码检查（lint）——这些属于/verify的功能。任何会修改文件的操作（例如
```
eslint --fix
```
、格式化工具）均归属于/verify，无论何种情况。
风险标签仅调整检查粒度，绝不会授予编辑计划外文件的权限。
编译失败恢复：最多在计划列出的文件/代码行范围内尝试一次修复。若仍无法解决，则视为阻塞。
切勿修改plan.md。
若发现关键阻塞（无法按计划执行），请停止操作并输出：
```
⚠️  阻塞：<描述>。计划需要修订——请重新运行`/plan`。
```
切勿自行变通处理。