krillinai-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

KrillinAI CLI

Use this as the top-level routing skill for KrillinAI command-line work.

将此 skill 作为 KrillinAI 命令行工作的顶层路由 skill。

Build And Locate The Binary

构建并定位二进制文件

Build both KrillinAI binaries through the repository script:

bash

pnpm krillinai:build

For the current machine, locate the CLI without assuming a platform or architecture:

bash

TARGET="$(node -p "process.platform + '-' + process.arch")"
SUFFIX="$(node -p "process.platform === 'win32' ? '.exe' : ''")"
KRILLINAI_CLI="$PWD/.runtime/build/krillinai/$TARGET/bin/krillinai-cli$SUFFIX"
test -f "$KRILLINAI_CLI"

The CLI loads

config/config.toml

relative to its process working directory. For real runs from a source checkout, use

runtime/krillinai

as the process working directory and create its ignored

config/config.toml

from

config/config-example.toml

without overwriting an existing file. A release archive should be run from its unpacked package root.

For build layout, configuration, JSON, manifest, output, and error details, read:

text

skills/krillinai-cli/references/cli-contract.md

通过仓库脚本构建两个 KrillinAI 二进制文件：

bash

pnpm krillinai:build

对于当前机器，在不预设平台或架构的情况下定位 CLI：

bash

TARGET="$(node -p "process.platform + '-' + process.arch")"
SUFFIX="$(node -p "process.platform === 'win32' ? '.exe' : ''")"
KRILLINAI_CLI="$PWD/.runtime/build/krillinai/$TARGET/bin/krillinai-cli$SUFFIX"
test -f "$KRILLINAI_CLI"

CLI 会相对于其进程工作目录加载

config/config.toml

。对于从源代码检出执行的真实运行，应使用

runtime/krillinai

作为进程工作目录，并根据

config/config-example.toml

创建被忽略的

config/config.toml

，但不要覆盖现有文件。发布归档包应从解压后的包根目录运行。

有关构建布局、配置、JSON、manifest、输出和错误详情，请阅读：

text

skills/krillinai-cli/references/cli-contract.md

Choose The Command

选择命令

User intent	Command / skill
Generate source, target, bilingual, and short vertical subtitles	`subtitle` ; use `krillinai-subtitle`
Generate target-language dubbing from subtitles	`tts` ; use `krillinai-tts`
Create landscape videos	`render-horizontal` ; use `krillinai-render-horizontal`
Create portrait/short-form videos	`render-vertical` ; use `krillinai-render-vertical`
Generate a cover from a complete image prompt	`cover` ; use `krillinai-cover`
Generate speech from plain text	`speech`
List provider voice codes for Aliyun, OpenAI, or MiniMax	`voices`
Validate a requested multi-stage output plan	`pipeline --dry-run` ; use `krillinai-pipeline`

pipeline

only validates plans in dry-run mode; non-dry-run execution returns

unsupported_command

status

is reserved and unsupported.

用户意图	命令 / skill
生成源语言、目标语言、双语和竖版短视频字幕	`subtitle` ; 使用 `krillinai-subtitle`
根据字幕生成目标语言配音	`tts` ; 使用 `krillinai-tts`
创建横屏视频	`render-horizontal` ; 使用 `krillinai-render-horizontal`
创建竖屏/短视频	`render-vertical` ; 使用 `krillinai-render-vertical`
根据完整的图像提示词生成封面	`cover` ; 使用 `krillinai-cover`
根据纯文本生成语音	`speech`
列出 Aliyun、OpenAI 或 MiniMax 的提供商声音代码	`voices`
验证请求的多阶段输出计划	`pipeline --dry-run` ; 使用 `krillinai-pipeline`

pipeline

仅在 dry-run 模式下验证计划；非 dry-run 执行会返回

unsupported_command

。

status

为保留命令，目前不支持。

Operating Rules For Agents

Agent 操作规则

Use a dedicated
```
--workdir
```
; do not scatter outputs in the repo root.
Use
```
--dry-run
```
for command-shape validation before external calls.
Parse stdout as JSON lines. The terminal response is the object containing
```
ok
```
; OpenCreator mode may emit progress frames first.
Treat
```
krillinai_manifest.json
```
and actual output files as the source of truth after a real stage.
Reuse manifest outputs for later stages instead of guessing filenames.

If a command fails, classify by

error.kind

usage

retryable

dependency

, or

internal

Avoid rerunning expensive stages if the manifest already has valid upstream outputs.
Do not claim that
```
cover
```
consumed a reference image: the current CLI accepts a complete text prompt and size only.
Do not request an Edge TTS voice catalog:
```
voices
```
currently supports
```
aliyun
```
,
```
openai
```
, and
```
minimax
```
.

使用专用的
```
--workdir
```
；不要将输出散落在仓库根目录。
在进行外部调用之前，使用
```
--dry-run
```
验证命令结构。
将 stdout 解析为 JSON Lines。终端响应是包含
```
ok
```
的对象；OpenCreator 模式可能会先输出进度帧。
真实阶段完成后，以
```
krillinai_manifest.json
```
和实际输出文件为准。
后续阶段应复用 manifest 输出，不要猜测文件名。
如果命令失败，按
```
error.kind
```
分类：
```
usage
```
、
```
retryable
```
、
```
dependency
```
或
```
internal
```
。
如果 manifest 中已有有效的上游输出，避免重新运行耗时的阶段。
不要声称
```
cover
```
使用了参考图像：当前 CLI 仅接受完整的文本提示词和尺寸。
不要请求 Edge TTS 声音目录：
```
voices
```
目前支持
```
aliyun
```
、
```
openai
```
和
```
minimax
```
。

Minimal Workflow

最小工作流

bash

REPO_ROOT="$PWD"
WORKDIR="$REPO_ROOT/tasks/demo"
mkdir -p "$WORKDIR"

(cd "$REPO_ROOT/runtime/krillinai" && "$KRILLINAI_CLI" subtitle \
  "https://www.youtube.com/watch?v=VIDEO_ID" \
  --origin-lang en \
  --target-lang zh_cn \
  --workdir "$WORKDIR" \
  --caption-source any \
  --prepare-video)

(cd "$REPO_ROOT/runtime/krillinai" && "$KRILLINAI_CLI" render-vertical \
  --workdir "$WORKDIR")

bash

REPO_ROOT="$PWD"
WORKDIR="$REPO_ROOT/tasks/demo"
mkdir -p "$WORKDIR"

(cd "$REPO_ROOT/runtime/krillinai" && "$KRILLINAI_CLI" subtitle \
  "https://www.youtube.com/watch?v=VIDEO_ID" \
  --origin-lang en \
  --target-lang zh_cn \
  --workdir "$WORKDIR" \
  --caption-source any \
  --prepare-video)

(cd "$REPO_ROOT/runtime/krillinai" && "$KRILLINAI_CLI" render-vertical \
  --workdir "$WORKDIR")