ce-dogfood

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Dogfood

Dogfood（内部测试）

Act as a QA engineer who dogfoods the active branch end-to-end, autonomously, until it is genuinely ready.

Outcome: every user-visible change this branch introduced has been driven in a real browser along its whole journey, judged for correctness and for how it feels to the product's personas, with small breakages fixed, regression-tested, and committed. Done: every matrix scenario is

Pass

Fixed

Skipped

, or in a terminal

Blocked

state; the project's automated suite has been run once and its result recorded; and the report at

<root>/dogfood-reports/<YYYY-MM-DD>-<branch-slug>-dogfood.md

is finalized against its template. A green matrix over a red suite finalizes as a not-ready verdict rather than a ready one. Chasing that suite green is not this run's job.

This is diff-scoped, not whole-app exploration. You test what this branch introduced or modified versus the trunk.

Read
references/phases.md
before Phase 0 and follow it — it owns every phase in detail, and the run cannot be executed correctly from the phase list below.

担任QA工程师，对当前分支进行端到端的自主内部测试，直到分支真正就绪。

成果： 该分支引入的所有用户可见变更，均已在真实浏览器中完成全流程验证，针对正确性及产品用户角色的体验感受进行评估，小问题已修复、完成回归测试并提交。完成标志： 所有矩阵场景处于

Pass

（通过）、

Fixed

（已修复）、

Skipped

（已跳过）或最终

Blocked

（阻塞）状态；项目自动化测试套件已运行一次并记录结果；

<root>/dogfood-reports/<YYYY-MM-DD>-<branch-slug>-dogfood.md

路径下的报告已根据模板完成定稿。若测试矩阵全绿但自动化套件全红，最终判定为未就绪。本任务无需负责将自动化套件修复至全绿状态。

本测试基于代码差异范围，而非全应用探索。仅测试本分支相对于主干分支新增或修改的内容。

在进入第0阶段前，请阅读
references/phases.md
并严格遵循——该文档详细定义了每个阶段的要求，仅靠下方的阶段列表无法正确执行测试流程。

Boundaries

边界规则

Drive the browser exclusively through the
```
agent-browser
```
CLI — never Chrome MCP tools (
```
mcp__claude-in-chrome__*
```
), another browser MCP, or a built-in browser-control tool, even when the platform offers one. Use the direct binary, never
```
npx agent-browser
```
(the direct binary uses the fast Rust client).
Never dogfood the trunk on a branch-name or blank target — there is no diff. A PR target always has a base, so it is always diffable even when its head branch is named
```
main
```
.
A numeric target stays a PR identity through isolation and checkout — never collapse it to its head ref, whose name may itself be
```
main
```
.
Never switch the primary checkout out from under the user. This skill decides only whether to offer isolation — no for a blank or current-branch target (you are already on it), yes for a PR or another named ref — and
```
ce-worktree
```
owns the mechanics and the verdict. On a declined offer, check the target out in place, confirming first if uncommitted changes would be disturbed.
Screenshots and other transient artifacts go to OS temp (
```
mktemp -d "${TMPDIR:-/tmp}/ce-dogfood-XXXXXX"
```
), never the repo root; copy one in only to embed it in the report.
Auto-fix only what is small, well-understood, and low-risk. A change that needs an architectural or schema decision, alters product behavior or UX intent, spans many files, or has plausible competing solutions is escalated to the report's Decisions for a human section, never implemented to clear a matrix item.

仅通过
```
agent-browser
```
CLI操控浏览器——绝不使用Chrome MCP工具（
```
mcp__claude-in-chrome__*
```
）、其他浏览器MCP或内置浏览器控制工具，即便平台提供这些工具也不例外。使用直接二进制文件，绝不使用
```
npx agent-browser
```
（直接二进制文件采用快速的Rust客户端）。
绝不对主干分支进行内部测试——无代码差异可对比。PR目标始终有基准分支，因此即使其头部分支名为
```
main
```
，也始终可进行差异对比。
数字标识的PR目标在隔离和检出过程中保持PR身份——绝不将其简化为头部引用，因为头部引用本身可能名为
```
main
```
。
绝不擅自切换用户的主检出分支。本技能仅决定是否提供隔离方案——针对空白或当前分支目标不提供（已处于该分支），针对PR或其他命名分支提供——
```
ce-worktree
```
负责具体机制和判定。若用户拒绝隔离方案，需先确认未提交的变更是否会受影响，再原地检出目标分支。
截图及其他临时产物需存储至系统临时目录（
```
mktemp -d "${TMPDIR:-/tmp}/ce-dogfood-XXXXXX"
```
），绝不能存储至仓库根目录；仅在嵌入报告时才复制相关文件。
仅自动修复小问题、易理解且低风险的问题。若变更需要架构或 schema 决策、改变产品行为或UX意图、涉及多个文件，或存在多种可行解决方案，则需升级至报告的需人工决策部分，绝不能通过实现修复来清除矩阵项。

Prerequisites

前置条件

User-runnable invocation rendering. In prerequisite failures, default to

/ce-setup

and

/ce-dogfood <original arguments>

; use

$ce-setup

and

$ce-dogfood <original arguments>

only when the active host is Codex or explicitly documents dollar-prefixed skill invocation. On oh-my-pi (

omp

), use

/skill:ce-setup

and

/skill:ce-dogfood <original arguments>

. Render only each invocation as inline code and output one form only.

A local dev server you can start (
```
bin/dev
```
,
```
rails server
```
,
```
npm run dev
```
, etc.).
```
agent-browser
```
installed. Check:
bash
```
command -v agent-browser >/dev/null 2>&1 && echo "Ready" || echo "NOT INSTALLED"
```
If not installed, stop and tell the user to install
```
agent-browser
```
: print the rendered
```
ce-setup
```
invocation for the current install command, followed by the rendered
```
ce-dogfood <original arguments>
```
invocation to retry. This workflow cannot function without it.

用户可执行的调用命令格式。若前置条件不满足，默认使用

/ce-setup

和

/ce-dogfood <原始参数>

；仅当当前主机为Codex或明确文档说明使用美元前缀的技能调用时，才使用

$ce-setup

和

$ce-dogfood <原始参数>

。在oh-my-pi（

omp

）环境下，使用

/skill:ce-setup

和

/skill:ce-dogfood <原始参数>

。仅需渲染一种格式的调用命令，以内联代码形式呈现。

可启动的本地开发服务器（
```
bin/dev
```
、
```
rails server
```
、
```
npm run dev
```
等）。
已安装
```
agent-browser
```
。检查命令：
bash
```
command -v agent-browser >/dev/null 2>&1 && echo "Ready" || echo "NOT INSTALLED"
```
若未安装，请停止操作并告知用户安装
```
agent-browser
```
：打印当前环境下渲染后的
```
ce-setup
```
调用命令，随后打印渲染后的
```
ce-dogfood <原始参数>
```
调用命令以重试。本工作流无法在缺少该工具的情况下运行。

Artifact Root

产物根目录

Reports live under

<root>/dogfood-reports/

and personas under

<root>/personas/

. Resolve

<root>

the first time you compose any

<root>/

path, whether you are reading or writing, and never before. A run that composes none skips it.

Resolve the CE artifact root
<root>
before composing any artifact path.

Read

docs_root

from

<repo-root>/.compound-engineering/config.yaml

only (

<repo-root>

git rev-parse --show-toplevel

). Do not read it from

config.local.yaml

. Unset ->

<root>

docs

, exactly as before.

Validate a set value: a repo-relative directory whose real, symlink-resolved path stays inside the repo and is neither the repo root nor under
```
.git/
```
. Otherwise stop with an error naming
```
docs_root
```
and the value -- never fall back to
```
docs
```
.
Use
```
<root>
```
as the sole artifact location: create it if absent, compose each path as
```
<root>/<subdir>
```
with this skill's own subdirectory, and never also read
```
docs
```
.

报告存储于

<root>/dogfood-reports/

，用户角色文件存储于

<root>/personas/

。仅在首次构建任何

<root>/

路径（无论读写）时解析

<root>

，此前绝不解析。若本次运行无需构建此类路径，则跳过解析步骤。

在构建任何产物路径前，请先解析CE产物根目录
<root>
。

读取：仅从

<repo-root>/.compound-engineering/config.yaml

中读取

docs_root

（

<repo-root>

git rev-parse --show-toplevel

）。禁止从

config.local.yaml

读取。若未设置，则

<root>

为

docs

，与此前保持一致。

验证：已设置的值必须是仓库相对目录，其真实、解析符号链接后的路径需位于仓库内部，且既不是仓库根目录也不在
```
.git/
```
目录下。否则停止操作并报错，指明
```
docs_root
```
及其值——绝不回退至
```
docs
```
。
使用：
```
<root>
```
为唯一产物存储位置：若不存在则创建，将每个路径构建为
```
<root>/<子目录>
```
（使用本技能专属子目录），绝不读取
```
docs
```
目录。

Delegation

任务委托

ce-dogfood

is an orchestrator: prefer an existing CE skill over re-deriving its behavior. Isolate a PR or named-branch target with

ce-worktree

; take a non-obvious root cause to

ce-debug

; commit each fix with

ce-commit

; capture a reusable lesson with

ce-compound

ce-dogfood

是编排器：优先使用现有CE技能，而非重新实现其功能。使用

ce-worktree

隔离PR或命名分支目标；使用

ce-debug

排查非明显根因；使用

ce-commit

提交每个修复；使用

ce-compound

记录可复用的经验。

Phase order

阶段顺序

Scope -> analyze the diff -> map the flows -> derive the matrix -> serve -> execute -> fix loop -> report. The order is the invariant: the flow model precedes the matrix, and the matrix precedes any browser work. Each phase's conditions are in

references/phases.md

— read it before Phase 0 rather than reconstructing a phase from this line. Work one scenario at a time, judged for correctness and for how it feels to each persona. A fix is not done until a regression test fails before it and passes after, or the report says why no automated test was meaningful.

Checkpoint, not a final write. Create the report from

references/dogfood-report-template.md

as soon as the matrix exists, with every scenario at

Pending

, and update it after each scenario is judged and each fix is committed.

<branch-slug>

is the branch name lowercased, with every run of non-alphanumeric characters — slashes included — collapsed to one

. Find a prior run by globbing

<root>/dogfood-reports/*-<branch-slug>-dogfood.md

. The task list is session-scoped, but the report on disk is what a later run or a teammate resumes from, so an interrupted run must leave a template-shaped checkpoint rather than a bare matrix.

Terminal states.

Blocked (needs human verify)

(an external-interaction leg — OAuth, real email, payments, SMS — that cannot be driven headlessly) and

Blocked (human decision)

(a fix too big to make autonomously) both wait on a person, and each ends that scenario, not the run: continue the rest of the matrix, and never silently re-queue a blocked scenario, on this run or on resume. How a person is reached differs per state, and the phase that sets the state says which.

确定范围 -> 分析代码差异 -> 梳理用户流程 -> 生成测试矩阵 -> 启动服务 -> 执行测试 -> 修复循环 -> 生成报告。顺序不可更改：流程模型需先于测试矩阵，测试矩阵需先于任何浏览器操作。每个阶段的条件定义于

references/phases.md

——请在进入第0阶段前阅读该文档，而非仅通过下方的阶段列表重构流程。逐个处理场景，同时评估正确性及每个用户角色的体验感受。修复完成的标志是：修复前回归测试失败，修复后回归测试通过；或报告中说明为何无需自动化测试。

检查点，而非最终写入。测试矩阵生成后，立即基于

references/dogfood-report-template.md

创建报告，所有场景标记为

Pending

（待处理），并在每个场景评估完成、每个修复提交后更新报告。

<branch-slug>

为分支名称小写形式，所有连续非字母数字字符（包括斜杠）替换为单个

。可通过通配符

<root>/dogfood-reports/*-<branch-slug>-dogfood.md

查找历史运行记录。任务列表为会话范围，但磁盘上的报告是后续运行或团队成员恢复任务的依据，因此中断的运行需留下符合模板的检查点，而非仅留下测试矩阵。

最终状态。

Blocked (needs human verify)

（阻塞：需人工验证）（无法无头操控的外部交互环节——OAuth、真实邮件、支付、短信）和

Blocked (human decision)

（阻塞：需人工决策）（无法自主修复的大型变更）均需等待人工处理，且仅终止当前场景，而非整个运行：继续处理测试矩阵中的其余场景，且在本次运行或恢复运行时绝不重新排队阻塞的场景。联系人工的方式因状态而异，设置该状态的阶段会说明具体方式。