plan-orchestrate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Plan Orchestrate

计划编排

Bridge a plan document to

/orchestrate custom

by emitting one ready-to-paste invocation per step. The skill is generative only — it never executes

/orchestrate

. The user pastes each line when ready.

通过为每个步骤生成一个可直接粘贴的调用命令，将计划文档与

/orchestrate custom

打通。本技能仅负责生成内容——绝不执行

/orchestrate

。用户可在准备就绪时粘贴每一行命令。

When to Activate

激活场景

User has a multi-step plan document (PRD, RFC, implementation plan) and wants to drive it through
```
/orchestrate
```
.
User says "orchestrate this plan", "give me orchestrate prompts for each step", "compose chains for this plan".
A step-by-step plan exists but the user does not want to manually pick agents per step.

Skip when:

The work is one ad-hoc step → call
```
/orchestrate custom
```
directly.
The plan is unreadable or empty. Lack of explicit numbering alone is not a skip condition — see the "No clear steps" edge case below.

用户拥有多步骤计划文档（PRD、RFC、实施计划），并希望通过
```
/orchestrate
```
执行该计划。
用户提出类似“编排这个计划”、“给我每个步骤的orchestrate提示词”、“为这个计划组合链”的需求。
存在分步计划，但用户不想为每个步骤手动选择Agent。

跳过场景：

工作仅为单个临时步骤→直接调用
```
/orchestrate custom
```
。
计划不可读或为空。仅缺少明确编号不构成跳过条件——请参阅下文“步骤不清晰”边缘情况。

Inputs

输入参数

<plan-doc-path> [--lang=python|typescript|go|rust|cpp|java|kotlin|flutter|auto] [--scope=all|step:<n>|range:<a>-<b>] [--dry-run]

```
<plan-doc-path>
```
— required; relative or absolute path (
```
@docs/...
```
accepted).
```
--lang
```
— reviewer language variant; defaults to
```
auto
```
(detected from project).
```
--scope
```
— limits emitted steps; defaults to
```
all
```
.
```
--dry-run
```
— print decomposition + chain rationale only; do not emit final prompts.

<plan-doc-path> [--lang=python|typescript|go|rust|cpp|java|kotlin|flutter|auto] [--scope=all|step:<n>|range:<a>-<b>] [--dry-run]

```
<plan-doc-path>
```
— 必填；相对或绝对路径（支持
```
@docs/...
```
格式）。
```
--lang
```
— 评审器语言变体；默认值为
```
auto
```
（从项目中自动检测）。
```
--scope
```
— 限制生成的步骤范围；默认值为
```
all
```
。
```
--dry-run
```
— 仅输出步骤分解结果和链设计依据；不生成最终提示词。

Authoritative

/orchestrate

shape (do not deviate)

标准

/orchestrate

命令格式（请勿偏离）

{ORCH_CMD} custom "<agent1>,<agent2>,...,<agentN>" "<task description>"

Where

{ORCH_CMD}

is determined in Phase 0 (see below). The command string in the emitted output always uses one concrete form — never both, never a placeholder.

```
custom
```
is a sequential chain; each agent's HANDOFF feeds the next.
Comma-separated agent list. No spaces preferred; one space tolerated.
No
```
--mode
```
/
```
--gate
```
/
```
--agents=...
```
flags exist — never invent them.
Agent names come from the catalogue in this skill. Embedded double quotes in the task description are escaped as
```
\"
```
.

{ORCH_CMD} custom "<agent1>,<agent2>,...,<agentN>" "<task description>"

其中

{ORCH_CMD}

由阶段0确定（见下文）。生成输出中的命令字符串始终采用一种具体格式——绝不混用两种格式，也不使用占位符。

```
custom
```
表示顺序链；每个Agent的HANDOFF结果会传递给下一个Agent。
Agent列表用逗号分隔。优先无空格格式；允许单个空格。
不存在
```
--mode
```
/
```
--gate
```
/
```
--agents=...
```
等参数——请勿自行添加。
Agent名称来自本技能中的目录。任务描述中的嵌入式双引号需转义为
```
\"
```
。

ECC install form and namespacing

ECC安装形式与命名空间

Two install forms determine the prefix on both the slash command and every agent name. The two MUST stay in sync — one form per output, never mixed:

Let

<claude-home>

denote the Claude Code home directory:

~/.claude

on macOS/Linux,

%USERPROFILE%\.claude

on Windows. Resolve it the way the host platform resolves the user home directory (do not hardcode

Form	Detection	`{ORCH_CMD}`	Agent name format
Plugin install (1.9.0+)	`<claude-home>/plugins/marketplaces/everything-claude-code/` exists	`/everything-claude-code:orchestrate`	`everything-claude-code:<name>`
Legacy bare install	Above absent; agent files under `<claude-home>/agents/`	`/orchestrate`	`<name>`

Why this matters: under the plugin install, agents register as

everything-claude-code:tdd-guide

. Bare names force fuzzy matching, which fails intermittently under parallel calls. Under legacy, the prefixed forms are not registered and fail outright.

两种安装形式决定了斜杠命令和每个Agent名称的前缀。两者必须保持一致——每个输出仅使用一种形式，绝不混用：

用

<claude-home>

表示Claude Code的主目录：macOS/Linux系统为

~/.claude

，Windows系统为

%USERPROFILE%\.claude

。需按照宿主平台解析用户主目录的方式解析该路径（请勿硬编码

）。

形式	检测方式	`{ORCH_CMD}`	Agent名称格式
插件安装（1.9.0+）	`<claude-home>/plugins/marketplaces/everything-claude-code/` 目录存在	`/everything-claude-code:orchestrate`	`everything-claude-code:<name>`
传统裸安装	上述目录不存在；Agent文件位于 `<claude-home>/agents/` 下	`/orchestrate`	`<name>`

为何这一点很重要：在插件安装模式下，Agent注册为

everything-claude-code:tdd-guide

形式。裸名称会触发模糊匹配，在并行调用时可能间歇性失败。在传统模式下，带前缀的形式未注册，会直接执行失败。

Available agent catalogue (must pick from these)

可用Agent目录（必须从中选择）

General:

```
planner
```
— requirement restatement, risk decomposition, step planning
```
architect
```
— architecture, system design, refactor proposals
```
tdd-guide
```
— write tests → implement → 80%+ coverage
```
code-reviewer
```
— generic code review
```
security-reviewer
```
— security audit, OWASP, secret leakage
```
refactor-cleaner
```
— dead code, duplicates, knip-class cleanup
```
doc-updater
```
— documentation, codemap, README
```
docs-lookup
```
— third-party library API lookups (Context7)
```
e2e-runner
```
— end-to-end test orchestration
```
database-reviewer
```
— PostgreSQL schema, migration, performance
```
harness-optimizer
```
— local agent harness configuration
```
loop-operator
```
— long-running autonomous loops
```
chief-of-staff
```
— multi-channel triage (rarely a fit for plan steps)

Build error resolvers:

build-error-resolver

(generic) /

cpp-build-resolver

go-build-resolver

java-build-resolver

kotlin-build-resolver

rust-build-resolver

pytorch-build-resolver

Code reviewers:

python-reviewer

typescript-reviewer

go-reviewer

rust-reviewer

cpp-reviewer

java-reviewer

kotlin-reviewer

flutter-reviewer

A misspelled agent name fails

/orchestrate

. Cross-check against this list before emitting.

通用类：

```
planner
```
— 需求重述、风险分解、步骤规划
```
architect
```
— 架构设计、系统设计、重构提案
```
tdd-guide
```
— 编写测试→实现→覆盖率达80%以上
```
code-reviewer
```
— 通用代码评审
```
security-reviewer
```
— 安全审计、OWASP合规、密钥泄露检查
```
refactor-cleaner
```
— 死代码清理、重复代码移除、knip类清理
```
doc-updater
```
— 文档更新、代码映射、README维护
```
docs-lookup
```
— 第三方库API查询（基于Context7）
```
e2e-runner
```
— 端到端测试编排
```
database-reviewer
```
— PostgreSQL schema、迁移、性能优化
```
harness-optimizer
```
— 本地Agent harness配置优化
```
loop-operator
```
— 长期运行的自主循环
```
chief-of-staff
```
— 多渠道分类处理（很少适用于计划步骤）

构建错误解决器：

build-error-resolver

（通用）/

cpp-build-resolver

go-build-resolver

java-build-resolver

kotlin-build-resolver

rust-build-resolver

pytorch-build-resolver

代码评审器：

python-reviewer

typescript-reviewer

go-reviewer

rust-reviewer

cpp-reviewer

java-reviewer

kotlin-reviewer

flutter-reviewer

拼写错误的Agent名称会导致

/orchestrate

执行失败。生成输出前请对照此列表进行交叉检查。

How It Works

工作流程

Phase 0 — Detect ECC mode + language

阶段0 — 检测ECC模式与语言

Read
```
<plan-doc-path>
```
. If missing or empty, report and stop.
Detect ECC install form once and freeze it into
```
ECC_MODE
```
. Algorithm (run in order, stop at the first match):
1. If
```
<claude-home>/plugins/marketplaces/everything-claude-code/
```
  exists →
```
ECC_MODE=plugin
```
  .
2. Else if
```
<claude-home>/agents/
```
  exists and contains at least one ECC agent file (e.g.
```
tdd-guide.md
```
  ,
```
code-reviewer.md
```
  ) →
```
ECC_MODE=legacy
```
  .
3. Else → default to
```
ECC_MODE=legacy
```
  and emit a one-line warning at the top of the output:
```
> Warning: could not detect ECC install; defaulting to legacy form. If you use the plugin install, edit the prefixes manually.
```
4. If both markers exist (mixed install),
```
plugin
```
  wins — the plugin namespace is the only one that resolves agent names without fuzzy matching.
From this point on, every emitted line uses the matching prefix on both the slash command and every agent name. Never emit both forms in the same output.
Resolve
```
--lang
```
. When
```
auto
```
, run a polyglot-aware detection:
- Probe markers:
```
pyproject.toml
```
  /
```
uv.lock
```
  /
```
requirements.txt
```
  → python;
```
package.json
```
  → typescript;
```
go.mod
```
  → go;
```
Cargo.toml
```
  → rust;
```
CMakeLists.txt
```
  or top-level
```
*.cpp
```
  → cpp;
```
pom.xml
```
  /
```
build.gradle
```
  (Java) → java;
```
build.gradle.kts
```
  or top-level Kotlin → kotlin;
```
pubspec.yaml
```
  → flutter.
- Polyglot tie-break: if more than one marker matches, pick the language whose source files outnumber the others (count via
```
git ls-files
```
  , excluding
```
vendor/
```
  ,
```
node_modules/
```
  ,
```
dist/
```
  ,
```
build/
```
  ,
```
.venv/
```
  , generated files, and obvious test fixtures). On a tie or when no language exceeds 60% of source files, set
```
lang=unknown
```
  .
- No marker matched → set
```
lang=unknown
```
  .
- ```
lang=unknown
```
  is a sentinel — it is not an agent name. Phase 2 rules 4 and 5 turn it into
```
code-reviewer
```
  /
```
build-error-resolver
```
  at chain composition time.
Detect a PyTorch sub-profile: when
```
lang=python
```
and any of
```
pyproject.toml
```
/
```
requirements.txt
```
/
```
uv.lock
```
declares a dependency on
```
torch
```
, set
```
pytorch=true
```
. This only affects
```
build
```
chain selection (Phase 2 rule below); the reviewer remains
```
python-reviewer
```
.
Normalize any agent names declared in the plan: if the plan text references agents by their plugin-prefixed form (e.g.
```
everything-claude-code:tdd-guide
```
), strip the prefix to get the bare catalogue name before validating or composing chains. Re-prefixing happens only at output time per
```
ECC_MODE
```
(Phase 4). Never let a pre-prefixed name flow into chain composition — it would double-prefix in plugin mode.

读取
```
<plan-doc-path>
```
。若文件缺失或为空，报告并终止操作。
检测ECC安装形式并将其固定为
```
ECC_MODE
```
。检测算法（按顺序执行，匹配到第一个即停止）：
1. 若
```
<claude-home>/plugins/marketplaces/everything-claude-code/
```
  目录存在→
```
ECC_MODE=plugin
```
  。
2. 否则，若
```
<claude-home>/agents/
```
  目录存在且包含至少一个ECC Agent文件（如
```
tdd-guide.md
```
  、
```
code-reviewer.md
```
  ）→
```
ECC_MODE=legacy
```
  。
3. 否则→默认设置为
```
ECC_MODE=legacy
```
  ，并在输出顶部生成一行警告：
```
> Warning: could not detect ECC install; defaulting to legacy form. If you use the plugin install, edit the prefixes manually.
```
4. 若两种标记都存在（混合安装），
```
plugin
```
  模式优先——插件命名空间是唯一能准确解析Agent名称而无需模糊匹配的模式。
从此时起，所有生成的行都将使用与
```
ECC_MODE
```
匹配的前缀，斜杠命令和每个Agent名称均需遵循。绝不允许在同一输出中混用两种形式。
解析
```
--lang
```
参数。当设置为
```
auto
```
时，执行多语言感知检测：
- 探测标记文件：
```
pyproject.toml
```
  /
```
uv.lock
```
  /
```
requirements.txt
```
  →python；
```
package.json
```
  →typescript；
```
go.mod
```
  →go；
```
Cargo.toml
```
  →rust；
```
CMakeLists.txt
```
  或顶级
```
*.cpp
```
  文件→cpp；
```
pom.xml
```
  /
```
build.gradle
```
  （Java）→java；
```
build.gradle.kts
```
  或顶级Kotlin文件→kotlin；
```
pubspec.yaml
```
  →flutter。
- 多语言平局处理：若多个标记文件匹配，选择源文件数量最多的语言（通过
```
git ls-files
```
  统计，排除
```
vendor/
```
  、
```
node_modules/
```
  、
```
dist/
```
  、
```
build/
```
  、
```
.venv/
```
  、生成文件和明显的测试夹具）。若出现平局或没有语言的源文件占比超过60%，则设置
```
lang=unknown
```
  。
- 无匹配标记文件→设置
```
lang=unknown
```
  。
- ```
lang=unknown
```
  是一个标记值——并非Agent名称。阶段2的规则4和5会在链组合时将其转换为
```
code-reviewer
```
  /
```
build-error-resolver
```
  。
检测PyTorch子配置：当
```
lang=python
```
且
```
pyproject.toml
```
/
```
requirements.txt
```
/
```
uv.lock
```
中声明了
```
torch
```
依赖时，设置
```
pytorch=true
```
。这仅影响构建链的选择（见下文阶段2规则）；评审器仍为
```
python-reviewer
```
。
标准化计划中声明的Agent名称：若计划文本引用了带插件前缀的Agent（如
```
everything-claude-code:tdd-guide
```
），在验证或组合链之前需剥离前缀以获取目录中的裸名称。仅在输出阶段根据
```
ECC_MODE
```
重新添加前缀（阶段4）。绝不允许带前缀的名称进入链组合流程——否则在插件模式下会出现双重前缀。

Phase 1 — Decompose steps

阶段1 — 步骤分解

Identify "step units" in priority order:

Explicit numbering:
```
## Step N
```
/
```
### Phase N
```
/
```
## N. ...
```
/ top-level ordered list.
A "Step" column in a table.
```
---
```
-separated blocks with verb-led headings.
Otherwise treat each H2 as one step.

Per step extract

id

(1-based),

title

(≤ 80 chars),

intent

(1–3 sentences),

tags

按优先级识别“步骤单元”：

明确编号：
```
## Step N
```
/
```
### Phase N
```
/
```
## N. ...
```
/顶级有序列表。
表格中的“Step”列。
由
```
---
```
分隔的、以动词开头的标题块。
否则将每个H2标题视为一个步骤。

为每个步骤提取

id

（从1开始）、

title

（≤80字符）、

intent

（1-3句话）、

tags

。

Phase 2 — Tag and pick chain

阶段2 — 标记与链选择

Tag by intent (multi-tag allowed; chain built from primary + stacked secondaries):

Trigger words below are matched case-insensitively. Multilingual plans are supported by matching the word stems in any language as long as the meaning aligns with the listed English trigger words.

Tag	Trigger words	Default chain
`design`	architecture, design, choose, evaluate, RFC	`planner,architect`
`plan`	plan, breakdown, milestone	`planner`
`impl`	implement, build, add, create, port	`tdd-guide,<lang>-reviewer`
`test`	test, coverage, e2e, integration	`tdd-guide,e2e-runner`
`refactor`	refactor, cleanup, dedupe, split	`architect,refactor-cleaner,<lang>-reviewer`
`migration`	migrate, upgrade, rewrite, port	`architect,tdd-guide,<lang>-reviewer`
`db`	schema, migration, index, SQL, Postgres, alembic, sqlmodel	`database-reviewer,<lang>-reviewer`
`security`	encrypt, auth, secret, OWASP, PII	`security-reviewer,<lang>-reviewer`
`build`	build, compile, lint failure, CI	`<lang>-build-resolver` (falls back to `build-error-resolver` )
`docs`	docs, readme, codemap, changelog	`doc-updater`
`lookup`	lookup, reference, API usage	`docs-lookup`
`review`	review, audit, verify	`<lang>-reviewer,code-reviewer`
`loop`	loop, autonomous, watchdog	`loop-operator`

Chain composition rules:

Primary tag selection: when a step matches multiple tags, the first one in table order (top of the table = highest priority) is the primary; the rest are secondaries. Composition rules 2 and 3 below handle specific multi-tag combinations explicitly; otherwise, append secondary chains in tag table order.

impl

security

→

tdd-guide,<lang>-reviewer,security-reviewer

impl

db

→

tdd-guide,database-reviewer,<lang>-reviewer

Deduplicate the resulting chain (preserve first occurrence). E.g.
```
review
```
+
```
lang=unknown
```
would yield
```
code-reviewer,code-reviewer
```
after rule 5; deduplication collapses it to
```
code-reviewer
```
.

<lang>-reviewer

resolves to

code-reviewer

when

lang=unknown

<lang>-build-resolver

resolves to

build-error-resolver

when

lang=unknown

. Special case: if Phase 0 set

pytorch=true

, use

pytorch-build-resolver

for

build

chains regardless of

<lang>

. There is no

python-build-resolver

;

--lang=python

without

pytorch=true

resolves to

build-error-resolver

Zero-tag steps: if no trigger word matches, set chain to
```
code-reviewer
```
and write
```
no tag matched; default review-only chain
```
under "Chain rationale".
Chain length ≤ 4 after deduplication. If exceeded, drop weakest tag (
```
lookup
```
and
```
docs
```
first).
Do not pair
```
planner
```
and
```
architect
```
in an
```
impl
```
chain (token waste). Pair them only on
```
design
```
steps.
Steps tagged
```
impl
```
,
```
refactor
```
, or
```
migration
```
end with a reviewer-class agent — any of
```
<lang>-reviewer
```
,
```
code-reviewer
```
,
```
security-reviewer
```
, or
```
database-reviewer
```
. The most domain-specific reviewer wins the tail position (e.g. rule 2's
```
impl+security
```
ends with
```
security-reviewer
```
; rule 3's
```
impl+db
```
ends with
```
<lang>-reviewer
```
because
```
database-reviewer
```
already gates the migration earlier in the chain).
```
test
```
and
```
build
```
steps are gated by their own validators (
```
e2e-runner
```
and the build resolver respectively) and do not require an additional reviewer.

根据意图标记（允许多标记；链由主标记+次要标记堆叠构建）：

以下触发词不区分大小写。支持多语言计划，只要含义与列出的英文触发词一致，匹配任何语言的词干即可。

标记	触发词	默认链
`design`	architecture, design, choose, evaluate, RFC	`planner,architect`
`plan`	plan, breakdown, milestone	`planner`
`impl`	implement, build, add, create, port	`tdd-guide,<lang>-reviewer`
`test`	test, coverage, e2e, integration	`tdd-guide,e2e-runner`
`refactor`	refactor, cleanup, dedupe, split	`architect,refactor-cleaner,<lang>-reviewer`
`migration`	migrate, upgrade, rewrite, port	`architect,tdd-guide,<lang>-reviewer`
`db`	schema, migration, index, SQL, Postgres, alembic, sqlmodel	`database-reviewer,<lang>-reviewer`
`security`	encrypt, auth, secret, OWASP, PII	`security-reviewer,<lang>-reviewer`
`build`	build, compile, lint failure, CI	`<lang>-build-resolver` （回退到 `build-error-resolver` ）
`docs`	docs, readme, codemap, changelog	`doc-updater`
`lookup`	lookup, reference, API usage	`docs-lookup`
`review`	review, audit, verify	`<lang>-reviewer,code-reviewer`
`loop`	loop, autonomous, watchdog	`loop-operator`

链组合规则：

主标记选择：当一个步骤匹配多个标记时，表格中顺序靠前的标记（表格顶部优先级最高）为主标记；其余为次要标记。以下规则2和3明确处理特定多标记组合；否则，按标记表格顺序追加次要链。

impl

security

→

tdd-guide,<lang>-reviewer,security-reviewer

。

impl

db

→

tdd-guide,database-reviewer,<lang>-reviewer

。

去重生成的链（保留首次出现的Agent）。例如，
```
review
```
+
```
lang=unknown
```
在规则5处理后会得到
```
code-reviewer,code-reviewer
```
；去重后简化为
```
code-reviewer
```
。

当

lang=unknown

时，

<lang>-reviewer

解析为

code-reviewer

。

当

lang=unknown

时，

<lang>-build-resolver

解析为

build-error-resolver

。特殊情况：若阶段0设置

pytorch=true

，则无论

<lang>

是什么，构建链都使用

pytorch-build-resolver

。不存在

python-build-resolver

；

--lang=python

且

pytorch=false

时解析为

build-error-resolver

。

无标记步骤：若未匹配到任何触发词，将链设置为
```
code-reviewer
```
，并在“链设计依据”下标注
```
no tag matched; default review-only chain
```
。
去重后链长度≤4。若超过，移除最弱标记（优先移除
```
lookup
```
和
```
docs
```
）。
在
```
impl
```
链中不要同时搭配
```
planner
```
和
```
architect
```
（浪费token）。仅在
```
design
```
步骤中搭配两者。
标记为
```
impl
```
、
```
refactor
```
或
```
migration
```
的步骤必须以评审类Agent结尾——包括
```
<lang>-reviewer
```
、
```
code-reviewer
```
、
```
security-reviewer
```
或
```
database-reviewer
```
。最具领域专业性的评审器位于链的末尾（例如规则2中的
```
impl+security
```
以
```
security-reviewer
```
结尾；规则3中的
```
impl+db
```
以
```
<lang>-reviewer
```
结尾，因为
```
database-reviewer
```
已在链的早期处理迁移验证）。
```
test
```
和
```
build
```
步骤由各自的验证器（
```
e2e-runner
```
和构建解决器）把关，无需额外评审器。

Phase 3 — Compress task description

阶段3 — 压缩任务描述

Each emitted

<task description>

must:

Be self-contained (the first agent does not need the plan document open).
Start with
```
[Plan: <path>#step-<id>]
```
.
Include 1–3 verifiable Acceptance criteria.
Include a Scope guard (
```
Out of scope: ...
```
) only if the plan declares one for this step. Inherit verbatim. If the plan has no out-of-scope statement, omit the clause entirely — do not invent one.
Be 200–600 characters; one line; embedded
```
"
```
escaped as
```
\"
```
; no literal newlines.

每个生成的

<task description>

必须：

自包含（第一个Agent无需打开计划文档即可执行）。
以
```
[Plan: <path>#step-<id>]
```
开头。
包含1-3条可验证的验收标准。
仅当计划中为此步骤声明了范围限制时，才包含范围防护语句（
```
Out of scope: ...
```
）。直接沿用原文表述。若计划中无范围限制声明，完全省略该语句——请勿自行编造。
长度为200-600字符；单行；嵌入式
```
"
```
转义为
```
\"
```
；无字面换行符。

Phase 4 — Output

阶段4 — 输出

Emit Markdown using the form determined by
ECC_MODE
. The output uses one form throughout — every

{ORCH_CMD}

and every agent name is rendered with the matching prefix from Phase 0. Do not emit both forms; do not include "this is plugin form" / "strip the prefix" instructions in the rendered output.

Concrete rendering rules:

{ORCH_CMD}

/everything-claude-code:orchestrate

under

plugin

/orchestrate

under

legacy

{AGENT(name)}

everything-claude-code:<name>

under

plugin

<name>

under

legacy

The overview-table "Chain" column uses the same
```
{AGENT(name)}
```
rendering.
Per-step bash blocks contain only the runnable command. No
# plugin form
or
# legacy form
comments — the form is implicit and uniform across the whole output.

Output structure:

markdown

undefined

根据

ECC_MODE

确定的格式生成Markdown输出。整个输出统一使用一种格式——所有

{ORCH_CMD}

和Agent名称均使用阶段0确定的前缀。绝不输出两种格式；渲染后的输出中请勿包含“这是插件格式”/“移除前缀”等说明。

具体渲染规则：

{ORCH_CMD}

：

plugin

模式下为

/everything-claude-code:orchestrate

，

legacy

模式下为

/orchestrate

。

{AGENT(name)}

：

plugin

模式下为

everything-claude-code:<name>

，

legacy

模式下为

<name>

。

概览表格的“Chain”列使用相同的
```
{AGENT(name)}
```
渲染方式。
每个步骤的bash块仅包含可运行的命令。请勿添加
# plugin form
或
# legacy form
注释——格式是隐含的，且在整个输出中保持一致。

输出结构：

markdown

undefined

Plan-Orchestrate Result

Plan:

<path>

Lang:

<detected-or-given>

ECC mode:

<plugin | legacy>

Steps: <N> Scope: <all | step:n | range:a-b>

Plan:

<path>

Lang:

<detected-or-given>

ECC mode:

<plugin | legacy>

Steps: <N> Scope: <all | step:n | range:a-b>

Steps overview

#	Title	Tags	Chain
1	...	impl, db	`{AGENT(tdd-guide)},{AGENT(database-reviewer)},{AGENT(python-reviewer)}`
...

#	Title	Tags	Chain
1	...	impl, db	`{AGENT(tdd-guide)},{AGENT(database-reviewer)},{AGENT(python-reviewer)}`
...

Step 1 — <title>

Intent: <1–3 sentences> Tags: <a, b> Chain rationale: <why this chain; which agent closes the loop>

bash

{ORCH_CMD} custom "{AGENT(tdd-guide)},{AGENT(database-reviewer)},{AGENT(python-reviewer)}" "[Plan: docs/foo.md#step-1] <compressed task description>; Acceptance: <1–3 items>; Out of scope: <…>"


> The `{ORCH_CMD}` and `{AGENT(...)}` notation above describes the substitution this skill performs at runtime. The actual emitted Markdown contains the resolved strings, never the placeholders.

Append a final "Batch execution" block aggregating every step's command in order so the user can paste them all at once. **Skip the Batch block in overview-only mode** (see "Large plan" edge case): when only the overview table is being emitted, there are no per-step commands to aggregate.

Intent: <1–3 sentences> Tags: <a, b> Chain rationale: <why this chain; which agent closes the loop>

bash

{ORCH_CMD} custom "{AGENT(tdd-guide)},{AGENT(database-reviewer)},{AGENT(python-reviewer)}" "[Plan: docs/foo.md#step-1] <compressed task description>; Acceptance: <1–3 items>; Out of scope: <…>"


> 上述`{ORCH_CMD}`和`{AGENT(...)}`表示法描述了本技能在运行时执行的替换操作。实际生成的Markdown包含解析后的字符串，绝不包含占位符。

最后添加一个“批量执行”块，按顺序汇总每个步骤的命令，方便用户一次性粘贴所有命令。**在仅概览模式下跳过批量块**（见“大型计划”边缘情况）：当仅生成概览表格时，无需生成每个步骤的命令，因此无需汇总。

Phase 5 — Self-check (run before emitting)

阶段5 — 自检（生成输出前执行）

Every agent in every chain comes from the catalogue (after stripping any
```
everything-claude-code:
```
prefix that appeared in the plan; see Phase 0 step 5).
Resolved
```
{ORCH_CMD}
```
and every resolved
```
{AGENT(...)}
```
use the same form (
```
plugin
```
or
```
legacy
```
) — never mixed in one output.
No
```
# plugin form
```
/
```
# legacy form
```
annotations and no "strip the prefix" instructions remain in the rendered output.
No invented
```
--mode
```
/
```
--gate
```
/
```
--agents=...
```
fields.
Each task description is single-line, double-quoted, with embedded
```
"
```
escaped.
Each task description begins with
```
[Plan: <path>#step-<id>]
```
and includes Acceptance (1–3 items). The
```
Out of scope:
```
clause is present only when inherited from the plan.
No duplicate agent in any chain after Phase 2 dedup.
Chain length ≤ 4.
Steps tagged
```
impl
```
/
```
refactor
```
/
```
migration
```
end with a reviewer-class agent (
```
<lang>-reviewer
```
,
```
code-reviewer
```
,
```
security-reviewer
```
, or
```
database-reviewer
```
).
```
test
```
and
```
build
```
are exempt — see Phase 2 rule 10.

Zero-tag steps emit

code-reviewer

with the rationale

no tag matched; default review-only chain

Overview table lists every step in the plan, regardless of
```
--scope
```
.
Per-step detail block count matches the resolved
```
--scope
```
(full plan when
```
--scope=all
```
; one block for
```
step:n
```
; range size for
```
range:a-b
```
). In overview-only mode, no per-step blocks and no Batch block are emitted.

每个链中的所有Agent均来自目录（已剥离计划中出现的任何
```
everything-claude-code:
```
前缀；见阶段0步骤5）。
解析后的
```
{ORCH_CMD}
```
和所有解析后的
```
{AGENT(...)}
```
使用相同格式（
```
plugin
```
或
```
legacy
```
）——同一输出中绝不混用。
渲染后的输出中无
```
# plugin form
```
/
```
# legacy form
```
注释，也无“移除前缀”等说明。
无自行添加的
```
--mode
```
/
```
--gate
```
/
```
--agents=...
```
参数。
每个任务描述均为单行、双引号包裹，嵌入式
```
"
```
已转义。
每个任务描述以
```
[Plan: <path>#step-<id>]
```
开头，并包含验收标准（1-3项）。
```
Out of scope:
```
语句仅在从计划中继承时才存在。
阶段2去重后，任何链中无重复Agent。
链长度≤4。
标记为
```
impl
```
/
```
refactor
```
/
```
migration
```
的步骤以评审类Agent结尾（
```
<lang>-reviewer
```
、
```
code-reviewer
```
、
```
security-reviewer
```
或
```
database-reviewer
```
）。
```
test
```
和
```
build
```
步骤除外——见阶段2规则10。

无标记步骤生成

code-reviewer

链，并标注依据

no tag matched; default review-only chain

。

概览表格列出计划中的所有步骤，无论
```
--scope
```
设置如何。
每个步骤的详细块数量与解析后的
```
--scope
```
匹配（
```
--scope=all
```
时为完整计划；
```
step:n
```
时为1个块；
```
range:a-b
```
时为对应范围的数量）。在仅概览模式下，不生成每个步骤的详细块和批量执行块。

Edge cases

边缘情况

No clear steps: prefer H2/H3 splitting; if still ambiguous, report "no structured steps detected" with the document outline and ask the user to confirm running by outline.
Large plan (>1500 lines): enter overview-only mode — emit only the overview table and ask the user to narrow with
```
--scope
```
before re-running for details. In this mode, skip per-step detail blocks and skip the Batch execution block.
Step too broad (e.g. "complete all backend work"): do not force a single chain. Suggest splitting into N.a and N.b and propose a split.
Plan declares agents (rare): first strip any
everything-claude-code:
prefix to get the bare catalogue name (Phase 0 step 5), then validate against the catalogue. Replace invalid agents and explain under "Chain rationale". The bare name is re-prefixed at output time per
```
ECC_MODE
```
.
Polyglot project where
--lang=auto
cannot pick a winner: set
```
lang=unknown
```
; reviewer resolves to
```
code-reviewer
```
and build resolver to
```
build-error-resolver
```
. Mention the fallback under "Chain rationale".

步骤不清晰：优先按H2/H3拆分；若仍不明确，报告“未检测到结构化步骤”并提供文档大纲，请求用户确认按大纲执行。
大型计划（>1500行）：进入仅概览模式——仅生成概览表格，并请求用户使用
```
--scope
```
缩小范围后重新运行以获取详细内容。在此模式下，跳过每个步骤的详细块和批量执行块。
步骤过于宽泛（例如“完成所有后端工作”）：不要强制使用单个链。建议拆分为N.a和N.b步骤，并提出拆分方案。
计划中声明了Agent（罕见）：首先剥离任何
everything-claude-code:
前缀以获取目录中的裸名称（阶段0步骤5），然后对照目录验证。替换无效Agent并在“链设计依据”下说明原因。裸名称会在输出阶段根据
```
ECC_MODE
```
重新添加前缀。
多语言项目中
--lang=auto
无法确定主导语言：设置
```
lang=unknown
```
；评审器解析为
```
code-reviewer
```
，构建解决器解析为
```
build-error-resolver
```
。在“链设计依据”下提及回退方案。

Examples

示例

Example 1 — Plugin mode, Python plan

示例1 — 插件模式，Python计划

Input:

plan-orchestrate @docs/plan/example-feature.md --lang=python

Excerpt of expected output:

markdown

undefined

输入：

plan-orchestrate @docs/plan/example-feature.md --lang=python

预期输出节选：

markdown

undefined

Step 2 — Encrypt sensitive UserProfile fields

Intent: Introduce an

EncryptedString

SQLAlchemy type and AES-GCM encrypt

birth_datetime

location

before persistence; load the key from an environment variable. Tags: impl, security, db Chain rationale: Security-sensitive write path, so

security-reviewer

closes the chain;

database-reviewer

validates the alembic migration;

python-reviewer

covers typing and PEP 8.

bash

/everything-claude-code:orchestrate custom "everything-claude-code:tdd-guide,everything-claude-code:database-reviewer,everything-claude-code:python-reviewer,everything-claude-code:security-reviewer" "[Plan: docs/plan/example-feature.md#step-2] Implement EncryptedString SQLAlchemy type and migrate UserProfile.birth_datetime/location columns; key from ENV APP_DB_KEY; Acceptance: encrypt/decrypt roundtrip tests pass; alembic upgrade/downgrade clean on empty DB; no plaintext in DB after migrate; Out of scope: cross-tenant profile sharing logic"

undefined

Intent: Introduce an

EncryptedString

SQLAlchemy type and AES-GCM encrypt

birth_datetime

location

before persistence; load the key from an environment variable. Tags: impl, security, db Chain rationale: Security-sensitive write path, so

security-reviewer

closes the chain;

database-reviewer

validates the alembic migration;

python-reviewer

covers typing and PEP 8.

bash

/everything-claude-code:orchestrate custom "everything-claude-code:tdd-guide,everything-claude-code:database-reviewer,everything-claude-code:python-reviewer,everything-claude-code:security-reviewer" "[Plan: docs/plan/example-feature.md#step-2] Implement EncryptedString SQLAlchemy type and migrate UserProfile.birth_datetime/location columns; key from ENV APP_DB_KEY; Acceptance: encrypt/decrypt roundtrip tests pass; alembic upgrade/downgrade clean on empty DB; no plaintext in DB after migrate; Out of scope: cross-tenant profile sharing logic"

undefined

Example 2 — Legacy mode, same step

示例2 — 传统模式，同一步骤

ECC_MODE=legacy

were detected, the same step would be emitted as a single uniform command (no plugin-prefixed forms anywhere in the output):

bash

/orchestrate custom "tdd-guide,database-reviewer,python-reviewer,security-reviewer" "[Plan: docs/plan/example-feature.md#step-2] ..."

The two examples above illustrate the two possible outputs for two different environments. A single skill invocation produces only one of them, end to end.

若检测到

ECC_MODE=legacy

，同一步骤会生成为统一的命令（输出中无任何带插件前缀的形式）：

bash

/orchestrate custom "tdd-guide,database-reviewer,python-reviewer,security-reviewer" "[Plan: docs/plan/example-feature.md#step-2] ..."

上述两个示例展示了两种不同环境下的可能输出。单次技能调用只会生成其中一种输出，全程保持一致。

Notes

注意事项

Generative only. Never invoke
```
/orchestrate
```
from inside this skill.
Match the language of the plan document for task descriptions (agent names always remain English).
Do not insert "Co-Authored-By" lines or emoji in the output unless the user explicitly asks.

仅生成内容。绝不从本技能内部调用
```
/orchestrate
```
。
任务描述需与计划文档的语言匹配（Agent名称始终保持英文）。
除非用户明确要求，否则请勿在输出中插入“Co-Authored-By”行或表情符号。

plan-orchestrate

Original

Translation

Plan Orchestrate

计划编排

When to Activate

激活场景

Inputs

输入参数

Authoritative /orchestrate shape (do not deviate)

标准/orchestrate命令格式（请勿偏离）

ECC install form and namespacing

ECC安装形式与命名空间

Available agent catalogue (must pick from these)

可用Agent目录（必须从中选择）

How It Works

工作流程

Phase 0 — Detect ECC mode + language

阶段0 — 检测ECC模式与语言

Phase 1 — Decompose steps

阶段1 — 步骤分解

Phase 2 — Tag and pick chain

阶段2 — 标记与链选择

Phase 3 — Compress task description

阶段3 — 压缩任务描述

Phase 4 — Output

阶段4 — 输出

Plan-Orchestrate Result

Plan-Orchestrate Result

Steps overview

Steps overview

Step 1 — <title>

Step 1 — <title>

Phase 5 — Self-check (run before emitting)

阶段5 — 自检（生成输出前执行）

Edge cases

边缘情况

Examples

示例

Example 1 — Plugin mode, Python plan

示例1 — 插件模式，Python计划

Step 2 — Encrypt sensitive UserProfile fields

Step 2 — Encrypt sensitive UserProfile fields

Example 2 — Legacy mode, same step

示例2 — 传统模式，同一步骤

Notes

注意事项

Authoritative
`/orchestrate`
shape (do not deviate)

标准
`/orchestrate`
命令格式（请勿偏离）