cheese

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/cheese

Inputs

输入内容

Accept anything the user supplies as

$ARGUMENTS

A natural-language feature description, idea, or question.
A spec path (
```
.cheese/specs/<slug>.md
```
) or pasted spec content.
A bug report, stack trace, failing test output, or reproduction steps.
A file path, glob, or directory.
A PR or issue reference (
```
PR#142
```
,
```
#87
```
, GitHub URL).
A research question about an external library, API, or pattern.
An empty or near-empty prompt — treat as "what's next?" and clarify.

Optional flags:

```
--safe
```
— gate dispatch behind a confirmation prompt.
```
--open-pr
```
— propagate through the implementation chain to terminal
```
/plate
```
; a new PR follows
```
/plate
```
's explicit-choice and review-shape policy.
```
--continue <slug-or-note-path>
```
— resume an in-flight pipeline from a handoff slug or note.
```
--hard
```
— propagate to
```
/plate
```
, which runs the final artifact-writing gate before
```
/hard-cheese
```
and publication.

$ARGUMENTS

is missing entirely and there is no recent context to lean on, ask one clarifying question through the host routing guide in

references/handoff-gate.md

before classifying.

接受用户提供的任意内容作为

$ARGUMENTS

：

自然语言描述的功能需求、创意或问题。
规格路径（
```
.cheese/specs/<slug>.md
```
）或粘贴的规格内容。
Bug报告、堆栈跟踪、测试失败输出或复现步骤。
文件路径、通配符或目录。
PR或Issue引用（
```
PR#142
```
、
```
#87
```
、GitHub URL）。
关于外部库、API或模式的研究问题。
空或近乎空的提示——视为“下一步该做什么？”并进行澄清。

可选参数：

```
--safe
```
—— 在调度前添加确认提示作为校验。
```
--open-pr
```
—— 沿实现流程传递至终端
```
/plate
```
；新PR遵循
```
/plate
```
的明确选择和评审形态策略。
```
--continue <slug-or-note-path>
```
—— 从交接标识或笔记恢复正在进行的流程。
```
--hard
```
—— 传递至
```
/plate
```
，在
```
/hard-cheese
```
和发布前运行最终产物写入校验。

如果完全缺失

$ARGUMENTS

且没有可依赖的近期上下文，在分类前通过

references/handoff-gate.md

中的宿主路由指南提出一个澄清问题。

Flow

流程

Read the full user message, not just
$ARGUMENTS
. Any prose accompanying the invocation is a directive list; execute or answer it before — and where it conflicts, instead of — the flow's defaults and any handoff protocol. The handoff file restores state; the user's live message overrides it.
Think first (silent). Model the problem internally per
```
skills/culture/SKILL.md
```
— restate the ask, list candidate targets, name the deciding signal. Output is the classification that drives step 2.
Classify — match
```
$ARGUMENTS
```
against the intent shapes in
```
references/classification.md
```
. Pick the highest-confidence shape; below the threshold, route to
```
clarify
```
(handled by the tier-3 escalation in step 4).
Clarity check (implementation intents only). Run cook's fast-path check for
```
cook
```
and
```
mold
```
. Direct
```
plate
```
intents bypass it.
Escalate (if needed). Tier 1 dispatches the chosen target (writing a mini-spec via
```
/mold
```
's agent-invoked mode when the dispatch is
```
/cook --auto
```
and no spec path was supplied). Tier 2 autonomously invokes
```
/culture
```
and/or
```
/briesearch
```
in internal mode, then re-runs the clarity check. Tier 3 blocks on a single targeted host-routed question and re-enters classification on the answer. See
```
## Escalation
```
.
Wiki grounding (when hallouminate is present). Derive a search query from the dropped-in input, ground it against the wiki corpus — at most one
```
mcp__hallouminate__ground
```
call, corpus resolved via
```
list_corpora
```
(probe shape:
```
skills/mold/references/grounding.md
```
) — and fold the top hits into the dispatch packet as
```
handoff_context.wiki_hits
```
(
```
[{page, line, why}]
```
; see
```
references/handoff-gate.md
```
§ Context payloads). When hallouminate is absent or no wiki corpus exists, skip and degrade per
```
references/optional-plugins.md
```
.
Announce — print a short block (Intent / Reason / Target, plus wiki hits when present) per the format in
```
## Output
```
. Cite the signal that drove the routing decision.
Self-check — run the coherence questions in
```
references/coherence-check.md
```
. If any fails, downgrade to
```
clarify
```
(tier 3) or
```
research
```
.
Dispatch — without
```
--safe
```
, run the chosen skill immediately with its exact dispatch command and context packet, in the same turn as the announce. With
```
--safe
```
, issue a handoff gate per
```
references/handoff-gate.md
```
(recommended target pre-selected, at least one alternative,
```
Stop
```
) and wait for the user's selection before dispatching.

/cheese

is a router, not a worker: it never edits files, runs tests, or opens PRs. Use only the host's read, search, and dispatch capabilities. The sole exception is invoking

/mold

's agent-invoked mini-spec mode in tier 1 when

/cook --auto

needs a spec first; that write happens inside

/mold

's own capability scope, not the router's.

Portability reference:

references/harness-portability.md

. It covers helper resolution, sub-agent dispatch, GitHub operations, and handoff transitions; prefer the bundled or repo-local helper first, and treat

${CLAUDE_SKILL_DIR}

as optional host-provided fallback. The handoff blocks below are the portable contract; slash commands are host renderings, not the control model.

读取完整用户消息，而非仅
$ARGUMENTS
。调用指令附带的任何文本内容都是指令列表；在流程默认规则和任何交接协议之前执行或响应这些内容——若存在冲突，则优先遵循用户的实时消息。交接文件用于恢复状态，但用户的实时消息拥有更高优先级。
先思考（静默）。 根据
```
skills/culture/SKILL.md
```
在内部建模问题——重述需求、列出候选目标、指明决策依据。输出结果将驱动步骤2的分类操作。
分类 —— 将
```
$ARGUMENTS
```
与
```
references/classification.md
```
中的意图形态进行匹配。选择置信度最高的形态；若低于阈值，则路由至
```
clarify
```
（由步骤4中的三级升级处理）。
清晰度检查（仅针对实现类意图）。 针对
```
cook
```
和
```
mold
```
执行快速路径检查。
```
plate
```
类意图可跳过此步骤。
升级（如有需要）。 一级：直接调度选定目标（当调度指令为
```
/cook --auto
```
且未提供规格路径时，通过
```
/mold
```
的Agent调用模式生成迷你规格）。二级：自主以内部模式调用
```
/culture
```
和/或
```
/briesearch
```
，然后重新运行清晰度检查。三级：暂停流程并通过宿主路由提出一个针对性问题，获取答案后重新进入分类环节。详见
```
## 升级
```
。
Wiki关联（当hallouminate可用时）。 从输入内容生成搜索查询，在Wiki语料库中进行关联——最多调用一次
```
mcp__hallouminate__ground
```
，语料库通过
```
list_corpora
```
确定（探测形态：
```
skills/mold/references/grounding.md
```
）——并将顶部匹配结果作为
```
handoff_context.wiki_hits
```
（格式：
```
[{page, line, why}]
```
；详见
```
references/handoff-gate.md
```
§ 上下文负载）加入调度数据包。若hallouminate不可用或无Wiki语料库，则跳过此步骤并根据
```
references/optional-plugins.md
```
降级处理。
通知 —— 按照
```
## 输出
```
中的格式打印简短内容（意图/理由/目标，如有Wiki匹配结果则附加）。指明驱动路由决策的依据。
自检 —— 运行
```
references/coherence-check.md
```
中的一致性检查问题。若任何检查未通过，则降级至
```
clarify
```
（三级）或
```
research
```
。
调度 —— 若无
```
--safe
```
参数，立即使用选定Skill的精确调度命令和上下文数据包执行，与通知步骤同轮次完成。若有
```
--safe
```
参数，则根据
```
references/handoff-gate.md
```
触发交接校验（预选定推荐目标，至少提供一个替代选项和
```
Stop
```
选项），等待用户选择后再进行调度。

/cheese

是一个路由工具，而非执行工具：它从不编辑文件、运行测试或创建PR。仅使用宿主的读取、搜索和调度能力。唯一例外是在一级升级中，当

/cook --auto

需要先生成规格时，调用

/mold

的Agent调用迷你规格模式；该写入操作在

/mold

自身的能力范围内完成，而非路由工具。

可移植性参考：

references/harness-portability.md

。涵盖助手解析、子Agent调度、GitHub操作和交接转换；优先使用捆绑或仓库本地助手，将

${CLAUDE_SKILL_DIR}

视为可选的宿主提供回退。以下交接模块是可移植契约；斜杠命令是宿主渲染形式，而非控制模型。

Intent shapes

意图形态

The full classification table — including all intent shapes, signals, disambiguation rules, and edge cases — lives in

references/classification.md

完整分类表——包括所有意图形态、依据、消歧规则和边缘情况——位于

references/classification.md

中。

Escalation

升级

For

cook

and

mold

intents,

/cheese

runs cook's fast-path check (§ "Standalone fast-path" in

skills/cook/SKILL.md

) and escalates through three tiers: tier 1 (clear) dispatches immediately — reusing a matching spec via the spec-discovery check, or having

/mold

write a mini-spec, with no user interaction; tier 2 (borderline) autonomously invokes

/culture

and/or

/briesearch

to fill missing context, then re-runs the fast-path check; tier 3 (still borderline) blocks on one targeted host-routed question and re-enters classification on the answer.

--safe

does not skip the tiers, it only gates the final dispatch. Full tier mechanics and the spec-discovery check:

references/escalation.md

Non-implementation intents bypass the escalation entirely. Their target skills own their own internal escalation:

/pasteurize

has its Phase 1 feedback-loop check,

/briesearch

clarifies missing version/scope inline,

/age

and

/cure

work directly against the supplied diff or report.

针对

cook

和

mold

意图，

/cheese

执行cook的快速路径检查（

skills/cook/SKILL.md

中的“独立快速路径”章节）并通过三个层级升级：一级（明确）立即调度——通过规格发现检查复用匹配的规格，或让

/mold

生成迷你规格，无需用户交互；二级（模糊）自主调用

/culture

和/或

/briesearch

补充缺失上下文，然后重新运行快速路径检查；三级（仍模糊）暂停流程并通过宿主路由提出一个针对性问题，获取答案后重新进入分类环节。

--safe

参数不会跳过升级层级，仅会对最终调度进行校验。完整层级机制和规格发现检查：

references/escalation.md

。

非实现类意图完全跳过升级环节。其目标Skill自行处理内部升级：

/pasteurize

有第一阶段反馈循环检查，

/briesearch

会在内部澄清缺失的版本/范围，

/age

和

/cure

直接针对提供的差异或报告执行操作。

Rejected-directions check

拒绝方向检查

Before dispatching any

mold

intent, scan

.cheese/.out-of-scope/

for rejection records whose

## Direction

section's one-line description substantially matches the incoming request. If a match is found:

Surface the previously-rejected direction and its rationale in one line.
Ask the user whether to proceed with the new request or take a different angle.
Do not suppress or re-propose the rejected direction silently.

This check is lightweight — a glob + keyword scan over

.cheese/.out-of-scope/*.md

. Skip silently when the directory does not exist. Non-

mold

intents skip this check.

调度任何

mold

意图前，扫描

.cheese/.out-of-scope/

中的拒绝记录，查看其

## Direction

章节的单行描述是否与当前请求高度匹配。若找到匹配项：

用一行内容展示之前被拒绝的方向及其理由。
询问用户是继续执行新请求还是更换方向。
不得静默隐藏或重新提议被拒绝的方向。

此检查为轻量级——通过通配符+关键词扫描

.cheese/.out-of-scope/*.md

。若目录不存在则静默跳过。非

mold

意图跳过此检查。

--continue

--continue参数

/cheese --continue <slug-or-note-path>

is the manual fresh-context resumption path — use it after compacting the conversation, after

/cook

's fan pathway halts, or whenever the user wants to drive the pipeline by hand from cleared context. Before dispatching anything on a

--continue

invocation, read the full resume flow — handoff discovery,

mode:

next:

parsing, parallel-task dispatch, gated-status handling, and baseline treatment — in

references/continue-resume.md

--continue

does not propagate

--auto

— dispatch

/<next> <slug>

in its default interactive mode even with no

--safe

. The user can append

--auto

explicitly (

/cheese --continue <slug> --auto

) to opt back in.

/cheese --continue <slug-or-note-path>

是手动恢复上下文的路径——可在对话压缩后、

/cook

的分支流程停止后，或用户希望从清理后的上下文手动驱动流程时使用。在

--continue

调用调度任何内容前，请阅读完整恢复流程——交接发现、

mode:

next:

解析、并行任务调度、校验状态处理和基线处理——详见

references/continue-resume.md

。

--continue

不会传递

--auto

参数——即使没有

--safe

，也会以默认交互模式调度

/<next> <slug>

。用户可显式追加

--auto

参数（

/cheese --continue <slug> --auto

）重新启用自动模式。

Confidence and the clarify gate

置信度与澄清校验

Treat classification confidence qualitatively (

low | medium | high

). Threshold for direct routing is

medium

or better. Below that, route to tier 3 (

clarify

Ask exactly one question through the host routing guide in
```
references/handoff-gate.md
```
.
Offer the two most-likely targets as alternatives plus
```
Stop
```
.
Re-enter
```
/cheese
```
with the answer.

medium

or above, dispatch directly. For implementation intents, the cook-fast-path clarity check adds a second layer (see

## Escalation

将分类置信度定性为（

低 | 中 | 高

）。直接路由的阈值为

中

或更高。低于此阈值则路由至三级（

clarify

）：

通过
```
references/handoff-gate.md
```
中的宿主路由指南提出恰好一个问题。
提供两个最可能的目标作为替代选项，外加
```
Stop
```
选项。
获取答案后重新进入
```
/cheese
```
流程。

置信度为

中

或更高时直接调度。针对实现类意图，cook快速路径清晰度检查会添加第二层校验（详见

## 升级

）。

Preferred tools and fallbacks

首选工具与回退方案

When the input is a path or slug, call the selected source-code read or search backend directly according to

references/code-intelligence-routing.md

Beyond source-code routing there are router-specific tools:

Need	Prefer	Fallback
PR / issue context	`gh`	the URL or numbers the user provided
Confirming routing target with the user (only under `--safe` or `clarify` )	host-routed structured question per `references/handoff-gate.md`	a numbered list with explicit dispatch commands

/cheese

keeps tool use light. Beyond the single wiki-grounding probe in

## Flow

, treat anything heavier than a single-file read or one search call as a sign the work belongs in the downstream skill, not in the router.

当输入为路径或标识时，根据

references/code-intelligence-routing.md

直接调用选定的源代码读取或搜索后端。

除源代码路由外，还有路由工具专属工具：

需求	首选方案	回退方案
PR / Issue上下文	`gh`	用户提供的URL或编号
与用户确认路由目标（仅在 `--safe` 或 `clarify` 场景下）	根据 `references/handoff-gate.md` 的宿主路由结构化问题	带明确调度命令的编号列表

/cheese

尽量减少工具使用。除

## 流程

中的单次Wiki关联探测外，任何比单文件读取或单次搜索调用更复杂的操作都应视为工作应移交下游Skill处理，而非由路由工具完成。

Output

输出

Always emit, in order:

Detected intent — one line, e.g.
```
Intent: cook (clear single-file fix)
```
.
Reason — one line citing the signal (
```
reason: spec path .cheese/specs/foo.md
```
).
Target — the chosen skill, e.g.
```
Target: /cook .cheese/specs/foo.md
```
.
Wiki hits — when
```
handoff_context.wiki_hits
```
is non-empty, one line per hit:
```
wiki: <page>:<line> — <why>
```
— always rendered before dispatch so the user sees what memory informed the routing and can challenge stale hits. Omit the section when hallouminate is absent.

Then dispatch in the same turn (or, under

--safe

, via the handoff gate). If

clarify

is chosen, replace the dispatch with the single clarifying question.

始终按以下顺序输出：

检测到的意图 —— 单行内容，例如
```
Intent: cook (clear single-file fix)
```
。
理由 —— 单行内容指明依据（
```
reason: spec path .cheese/specs/foo.md
```
）。
目标 —— 选定的Skill，例如
```
Target: /cook .cheese/specs/foo.md
```
。
Wiki匹配结果 —— 当
```
handoff_context.wiki_hits
```
非空时，每个匹配结果一行：
```
wiki: <page>:<line> — <why>
```
—— 始终在调度前展示，以便用户了解路由决策参考的记忆内容，并可质疑过时的匹配结果。若hallouminate不可用则省略此部分。

然后同轮次进行调度（或在

--safe

场景下通过交接校验）。若选择

clarify

，则用单个澄清问题替代调度操作。

Handoff

交接

Without

--safe

, cheese propagates

--auto

to any target that supports it. Under

--safe

, dispatch waits for the user's selection via the handoff gate; the auto variant stays the pre-selected recommended target.

Default targets per intent:

clarify — single targeted question; no skills run until the answer arrives.
research —
```
/briesearch
```
(recommended). No auto variant.
rubber-duck —
```
/culture
```
(recommended). Only reached when the user explicitly opted out of writes. No auto variant.
mold —
```
/mold
```
(recommended). Safe-mode alternative:
```
/briesearch first
```
when external evidence is missing.
cook — default:
```
/cook --auto <slug-or-path>
```
. Safe-mode alternatives:
```
/cook <slug-or-path>
```
(no auto),
```
/mold first
```
if scope is borderline. A high-blast-radius or decomposable spec triggers cook's own fan pathway automatically — no separate dispatch needed.

ultracook (retired) —

/ultracook <slug-or-path>

resolves to

/cook <slug-or-path>

, carrying forward

--open-pr

--resume

--auto

plate —
```
/plate
```
for commit-only work, ordinary PR publication, or stack publication/maintenance. New PRs infer an obviously cohesive single, recommend and ask for reviewable ordered stacks, and ask when shape is ambiguous; explicit choices win.
debug — default:
```
/pasteurize --auto <input>
```
. Safe-mode alternatives:
```
/pasteurize <input>
```
(no auto),
```
/culture
```
only when the user explicitly wants no-write diagnosis.
age —
```
/age <ref>
```
(recommended). Safe-mode alternative:
```
/age --scope <path>
```
when the user named a path glob.
age-then-cure —
```
/age <slug>
```
(recommended). Safe-mode alternative:
```
/cure <slug>
```
when a fresh report already exists.

Pre-select only the highest-confidence target. Without

--safe

, surface the target as a decision, not a question — dispatch the recommended option directly. With

--safe

, dispatch waits for the user's selection; the captured dispatch packet runs immediately on a non-stop choice.

若无

--safe

参数，cheese会将

--auto

参数传递给任何支持该参数的目标。若有

--safe

参数，调度需等待用户通过交接校验选择；自动变体将作为预选定的推荐目标保留。

各意图的默认目标：

clarify —— 单个针对性问题；获取答案前不运行任何Skill。
research ——
```
/briesearch
```
（推荐）。无自动变体。
rubber-duck ——
```
/culture
```
（推荐）。仅当用户明确选择不写入时触发。无自动变体。
mold ——
```
/mold
```
（推荐）。安全模式替代选项：当缺少外部证据时先调用
```
/briesearch
```
。
cook —— 默认：
```
/cook --auto <slug-or-path>
```
。安全模式替代选项：
```
/cook <slug-or-path>
```
（无自动模式），若范围模糊则先调用
```
/mold
```
。高影响范围或可分解的规格会自动触发cook自身的分支流程——无需单独调度。

ultracook (已废弃) ——

/ultracook <slug-or-path>

会解析为

/cook <slug-or-path>

，并保留

--open-pr

--resume

--auto

参数。

plate ——
```
/plate
```
用于仅提交工作、普通PR发布或堆栈发布/维护。新PR会自动推断明显连贯的单个内容，推荐并请求可评审的有序堆栈，当形态模糊时进行询问；明确选择优先。
debug —— 默认：
```
/pasteurize --auto <input>
```
。安全模式替代选项：
```
/pasteurize <input>
```
（无自动模式），仅当用户明确要求无写入诊断时调用
```
/culture
```
。
age ——
```
/age <ref>
```
（推荐）。安全模式替代选项：当用户指定路径通配符时使用
```
/age --scope <path>
```
。
age-then-cure ——
```
/age <slug>
```
（推荐）。安全模式替代选项：当已有最新报告时使用
```
/cure <slug>
```
。

仅预选置信度最高的目标。若无

--safe

参数，将目标作为决策结果展示，而非问题——直接调度推荐选项。若有

--safe

参数，调度需等待用户选择；用户选择非Stop选项后，捕获的调度数据包会立即运行。

Rules

规则

Never paraphrase or summarise downstream skill output — that is the downstream skill's job.
A declined question gate is an answer. Do not re-raise it; state the open item as one line and wait for freeform input.

永远不要转述或总结下游Skill的输出——这是下游Skill的职责。
被拒绝的问题校验视为一种答案。不得重新提出；用一行内容说明未完成项并等待自由输入。

References

参考文档

```
references/classification.md
```
— intent shapes, signals, disambiguation rules.
```
references/coherence-check.md
```
— pre-dispatch self-checks that downgrade misroutes.
```
references/handoff-gate.md
```
— cross-harness post-selection dispatch contract (shared across workflow skills).
```
references/escalation.md
```
— full escalation-tier mechanics and the spec-discovery check.
```
references/continue-resume.md
```
— the
```
--continue
```
resume flow.

```
references/classification.md
```
—— 意图形态、依据、消歧规则。
```
references/coherence-check.md
```
—— 调度前的自检，用于纠正错误路由。
```
references/handoff-gate.md
```
—— 跨框架选择后的调度契约（所有工作流Skill共享）。
```
references/escalation.md
```
—— 完整升级层级机制和规格发现检查。
```
references/continue-resume.md
```
——
```
--continue
```
恢复流程。