implement

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Implement

实现

Hand one task to a worker: a top-level T3 thread that implements it, runs the project's checks, and commits. You brief the worker, wait, answer its questions, and report. The worker writes every line of code.
将一个任务交给一个 worker:这是一个顶层 T3 线程,负责实现任务、运行项目检查并提交代码。你需要为 worker 提供任务说明、等待它、回答它的问题并汇报结果。worker 编写每一行代码。

Pick the model

选择模型

The worker runs Opus 5.5 at
high
reasoning effort. Use the model and effort the user or calling skill names instead.
Call
orchestrator_capabilities
and resolve the worker to an exact
providerInstanceId
, model
id
, and the reasoning-effort option the catalog lists for it. Prefer the provider's native driver (
claudeAgent
for Claude models,
codex
for OpenAI models). When the model or effort is unavailable, tell the user what is missing and ask how to proceed. Never substitute a model.
worker 使用 Opus 5.5,并采用
high
推理强度。如果用户或调用 skill 指定了模型和推理强度,则改用指定的配置。
调用
orchestrator_capabilities
,为 worker 解析出精确的
providerInstanceId
、模型
id
,以及目录中列出的该模型对应的推理强度选项。优先使用提供商的原生 driver(Claude 模型使用
claudeAgent
,OpenAI 模型使用
codex
)。如果所需的模型或推理强度不可用,请告知用户缺少什么,并询问用户希望如何继续。绝不能替换模型。

Resolve the checkout

确定 checkout

Use the checkout the calling skill names. Otherwise use the current branch and worktree, and when that is the default branch, create a branch named for the task first. When the checkout has uncommitted changes, ask the user whether to commit, stash, or keep them before the worker starts.
Done when you have the checkout's absolute path and branch, and the worker's resolved model and effort.
使用调用 skill 指定的 checkout。否则,使用当前 branch 和 worktree;如果当前使用的是 default branch,则先创建一个以任务命名的 branch。如果 checkout 中存在未提交的更改,请询问用户在 worker 开始前是提交、stash 还是保留这些更改。
完成条件:获得 checkout 的绝对路径和 branch,以及为 worker 解析出的模型和推理强度。

Launch the worker

启动 worker

Call
t3_thread_launch
with the resolved model and effort, a title naming the task, and a
workspaceStrategy
that points at the checkout:
existing_worktree
with its path and branch for a worktree, or
root
for the project's main checkout. When the user asked for a separate worktree, use
worktree
with the branch as
baseRef
. The
message
carries the whole brief, since the thread starts with no history:
text
You are the worker for one task.

Repository: <absolute path>
Branch: <branch>
Task: <the prompt, or "ToVo issue <ID>: read its context with the tovo skill">

Implement the task and run the project's checks. Commit your work on this branch with atomic, descriptive commits. Do not push or open a pull request. For a ToVo issue, comment on friction as you go and leave the issue's status to whoever launched you; they also run the code review.

When done, reply with a summary of the change, the commit SHAs, and the checks you ran with their results.
Retain the
threadId
and wait with
t3_thread_wait
, reading each reply with
t3_thread_read
. When the worker asks a question, answer it from the request and the task's context, or ask the user when only they can decide.
Done when the worker has replied with its commits and its checks pass, or the user has decided how to handle a failure.
调用
t3_thread_launch
,传入解析后的模型和推理强度、一个标明任务的标题,以及指向 checkout 的
workspaceStrategy
:对于 worktree,使用
existing_worktree
并指定其路径和 branch;对于项目主 checkout,使用
root
。如果用户要求使用单独的 worktree,则使用
worktree
,并将 branch 作为
baseRef
。由于线程启动时没有历史记录,
message
必须包含完整的任务说明:
text
You are the worker for one task.

Repository: <absolute path>
Branch: <branch>
Task: <the prompt, or "ToVo issue <ID>: read its context with the tovo skill">

Implement the task and run the project's checks. Commit your work on this branch with atomic, descriptive commits. Do not push or open a pull request. For a ToVo issue, comment on friction as you go and leave the issue's status to whoever launched you; they also run the code review.

When done, reply with a summary of the change, the commit SHAs, and the checks you ran with their results.
保留
threadId
,使用
t3_thread_wait
等待,并通过
t3_thread_read
读取每条回复。当 worker 提出问题时,根据请求和任务上下文回答;如果只有用户能够决定,则向用户询问。
完成条件:worker 已回复其提交内容且所有检查均通过,或者用户已经决定如何处理失败。

Send follow-up work

发送后续工作

Review findings, disproven proof claims, and other fixes go back to the same worker. When its thread is settled, unsettle it first with
t3_thread_organize
(
action: "unsettle"
). Send the items with
t3_thread_send
, each with its location, failure scenario, and suggested fix, and ask the worker to fix and commit them. Wait for its reply as above, then confirm each fix against the code.
审查发现、未被证实的证明主张以及其他需要修复的事项,都应交回同一个 worker。当该线程处于 settled 状态时,先使用
t3_thread_organize
(
action: "unsettle"
)将其 unsettle。通过
t3_thread_send
发送这些事项,每项都应附上位置、失败场景和建议的修复方案,并要求 worker 完成修复并提交。然后按照上述方式等待回复,再对照代码确认每项修复。

Settle and report

Settle 并汇报

Settle the worker's thread with
t3_thread_organize
(
action: "settle"
) when no more work will go to it: right after your report when you run this skill on its own, or when the calling skill says so.
Report the worker's thread linked as
[title](t3-thread://v1/<threadId>)
, its model and effort, its commits, and its checks with their results.
当不会再有后续工作交给 worker 时,使用
t3_thread_organize
(
action: "settle"
)settle 其线程:如果单独运行此 skill,则在汇报后立即执行;如果调用 skill 要求这样做,则按照其要求执行。
将 worker 的线程以
[title](t3-thread://v1/<threadId>)
的形式链接,并汇报其模型和推理强度、提交内容,以及执行的检查及其结果。