converter

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

/converter -- Cross-Platform Skill Converter

/converter -- 跨平台Skill转换器

Parse AgentOps skills into a universal SkillBundle format, then convert to target agent platforms.

将AgentOps skills解析为通用的SkillBundle格式，然后转换为目标Agent平台格式。

Quick Start

快速开始

bash

/converter skills/council codex     # Convert council skill to Codex format
/converter skills/vibe cursor       # Convert vibe skill to Cursor format
/converter --all codex              # Convert all skills to Codex

bash

/converter skills/council codex     # 将council skill转换为Codex格式
/converter skills/vibe cursor       # 将vibe skill转换为Cursor格式
/converter --all codex              # 将所有skills转换为Codex格式

Pipeline

处理流程

The converter runs a three-stage pipeline:

parse --> convert --> write

转换器运行一个三阶段流程：

解析 --> 转换 --> 写入

Stage 1: Parse

阶段1：解析

Read the source skill directory and produce a SkillBundle:

Extract YAML frontmatter from SKILL.md (between
```
---
```
markers)
Collect the markdown body (everything after the closing
```
---
```
)
Enumerate all files in
```
references/
```
and
```
scripts/
```
Assemble into a SkillBundle (see
```
references/skill-bundle-schema.md
```
)

读取源skill目录并生成SkillBundle：

从SKILL.md中提取YAML前置内容（位于
```
---
```
标记之间）
收集Markdown正文（所有在闭合
```
---
```
之后的内容）
枚举
```
references/
```
和
```
scripts/
```
中的所有文件
组装为SkillBundle（详见
```
references/skill-bundle-schema.md
```
）

Stage 2: Convert

阶段2：转换

Transform the SkillBundle into the target platform's format:

Target	Output Format	Status
`codex`	Codex SKILL.md + prompt.md	Implemented
`cursor`	Cursor .mdc rule + optional mcp.json	Implemented

The Codex adapter produces a

SKILL.md

(body + inlined references + scripts as code blocks) and a

prompt.md

(Codex prompt referencing the skill). Descriptions are truncated to 1024 chars at a word boundary if needed.

The Cursor adapter produces a

<name>.mdc

rule file with YAML frontmatter (

description

globs

alwaysApply: false

) and body content. References are inlined into the body, scripts are included as code blocks. Output is budget-fitted to 100KB max -- references are omitted largest-first if the total exceeds the limit. If the skill references MCP servers, a

mcp.json

stub is also generated.

将SkillBundle转换为目标平台的格式：

目标平台	输出格式	状态
`codex`	Codex SKILL.md + prompt.md	已实现
`cursor`	Cursor .mdc规则 + 可选mcp.json	已实现

Codex适配器会生成一个

SKILL.md

（正文+内联引用+作为代码块的脚本）和一个

prompt.md

（引用该skill的Codex提示词）。如果需要，描述会在单词边界处截断至1024字符。

Cursor适配器会生成一个带YAML前置内容（

description

、

globs

、

alwaysApply: false

）的

<name>.mdc

规则文件以及正文内容。引用会内联到正文中，脚本作为代码块包含在内。输出会适配100KB的上限——如果总大小超过限制，会从最大的引用开始省略。如果skill引用了MCP服务器，还会生成一个

mcp.json

存根文件。

Stage 3: Write

阶段3：写入

Write the converted output to disk.

Default output directory:

.agents/converter/<target>/<skill-name>/

Write semantics: Clean-write. The target directory is deleted before writing. No merge with existing content.

将转换后的输出写入磁盘。

默认输出目录：

.agents/converter/<target>/<skill-name>/

写入规则： 清理写入。写入前会删除目标目录，不会与现有内容合并。

CLI Usage

CLI使用方法

bash

undefined

bash

undefined

Convert a single skill

转换单个skill

bash skills/converter/scripts/convert.sh <skill-dir> <target> [output-dir]

Convert all skills

转换所有skills

bash skills/converter/scripts/convert.sh --all <target> [output-dir]

undefined

bash skills/converter/scripts/convert.sh --all <target> [output-dir]

undefined

Arguments

参数

Argument	Required	Description
`skill-dir`	Yes (or `--all` )	Path to skill directory (e.g. `skills/council` )
`target`	Yes	Target platform: `codex` , `cursor` , or `test`
`output-dir`	No	Override output location. Default: `.agents/converter/<target>/<skill-name>/`
`--all`	No	Convert all skills in `skills/` directory

参数	是否必填	描述
`skill-dir`	是（或使用 `--all` ）	skill目录的路径（例如 `skills/council` ）
`target`	是	目标平台： `codex` 、 `cursor` 或 `test`
`output-dir`	否	覆盖输出位置。默认值： `.agents/converter/<target>/<skill-name>/`
`--all`	否	转换 `skills/` 目录下的所有skills

Supported Targets

支持的目标平台

codex -- Convert to OpenAI Codex format (SKILL.md + prompt.md). Output:
```
<dir>/SKILL.md
```
and
```
<dir>/prompt.md
```
.
cursor -- Convert to Cursor rules format (
```
.mdc
```
rule file + optional
```
mcp.json
```
). Output:
```
<dir>/<name>.mdc
```
and optionally
```
<dir>/mcp.json
```
.
test -- Emit the raw SkillBundle as structured markdown. Useful for debugging the parse stage.

codex -- 转换为OpenAI Codex格式（SKILL.md + prompt.md）。输出：
```
<dir>/SKILL.md
```
和
```
<dir>/prompt.md
```
。
cursor -- 转换为Cursor规则格式（
```
.mdc
```
规则文件 + 可选
```
mcp.json
```
）。输出：
```
<dir>/<name>.mdc
```
和可选的
```
<dir>/mcp.json
```
。
test -- 以结构化Markdown形式输出原始SkillBundle。对调试解析阶段很有用。

Extending

扩展方法

To add a new target platform:

Add a conversion function to
```
scripts/convert.sh
```
(pattern:
```
convert_<target>
```
)
Update the target table above
Add reference docs to
```
references/
```
if the target format needs documentation

要添加新的目标平台：

在
```
scripts/convert.sh
```
中添加转换函数（模式：
```
convert_<target>
```
）
更新上方的目标平台表格
如果目标格式需要文档，在
```
references/
```
中添加参考文档

References

参考资料

```
references/skill-bundle-schema.md
```
-- SkillBundle interchange format specification

```
references/skill-bundle-schema.md
```
-- SkillBundle交换格式规范