skills-vote

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Discovery And Feedback

技能发现与反馈

Read only this file first. Do not read

scripts/

or any other files in this skill unless this file or a script output explicitly tells you to do so.

Use this skill in two moments:

Before you fetch or invoke external skills for the current task.
After the task is effectively done, to report what skills were actually useful.

Skip this skill if you are not considering any external skills at all.

All paths mentioned in this file are relative to this skill root.

cd

to this root directory before running any command here.

请首先仅阅读此文件。除非此文件或脚本输出明确要求，否则不要读取该技能中的

scripts/

目录或其他任何文件。

该技能适用于两个场景：

为当前任务获取或调用外部技能之前。
任务实际完成后，报告哪些技能确实起到了作用。

如果你完全不考虑使用任何外部技能，则跳过此技能。

此文件中提到的所有路径均相对于该技能的根目录。运行此处的任何命令前，请先

cd

到该根目录。

Preconditions

前置条件

Before using this skill, ensure that:

```
SKILLS_VOTE_API_KEY
```
is set in the environment
```
uv
```
is installed and available on
```
PATH
```
the runtime can execute local scripts with
```
uv run
```
```
GITHUB_TOKEN
```
or
```
GH_TOKEN
```
may be needed later if GitHub blocks skill downloads because the repo is private or rate-limited

Confirm

SKILLS_VOTE_API_KEY

is set:

macOS or Linux:
```
bash scripts/check_api_key.sh
```

Windows PowerShell:

powershell -ExecutionPolicy Bypass -File scripts/check_api_key.ps1

Verify that
```
uv
```
is installed:
```
uv -V
```

uv

is missing, install it from the official docs.

macOS or Linux:

If curl is available,

curl -LsSf https://astral.sh/uv/install.sh | sh

Otherwise

wget -qOhttps://astral.sh/uv/install.sh | sh

Windows PowerShell:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Verify again:
```
uv -V
```

使用此技能前，请确保：

环境中已设置
```
SKILLS_VOTE_API_KEY
```
已安装
```
uv
```
且可在
```
PATH
```
中找到
运行时可通过
```
uv run
```
执行本地脚本
如果GitHub因为仓库为私有或触发速率限制而阻止技能下载，后续可能需要
```
GITHUB_TOKEN
```
或
```
GH_TOKEN
```

确认已设置

SKILLS_VOTE_API_KEY

：

macOS或Linux：
```
bash scripts/check_api_key.sh
```

Windows PowerShell：

powershell -ExecutionPolicy Bypass -File scripts/check_api_key.ps1

验证
```
uv
```
已安装：
```
uv -V
```

如果缺少

uv

，请从官方文档安装：

macOS或Linux：

如果有curl，执行

curl -LsSf https://astral.sh/uv/install.sh | sh

否则执行

wget -qOhttps://astral.sh/uv/install.sh | sh

Windows PowerShell：

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

再次验证：
```
uv -V
```

Recommend

推荐

Request schema

请求结构

recommend.py

accepts one JSON object with these fields:

```
query
```
(
```
str
```
): A standalone and explicit description of the task, suitable for use as an independent skill-recommendation prompt. You may rewrite the user's original request to improve clarity, specificity, and retrieval performance, and may add reasonable implied details or likely substeps when helpful.

client_name

(

Literal["codex", "codex-app", "claude-code", "cursor", "gemini-cli", "openclaw-cli", "opencode"] | None = None

): Name of this agent. If unknown/unverified or not listed, omit the field or return

null

```
client_version
```
(
```
str | None = None
```
): Version of this agent. Prefer the exact version string reported by the client itself. If unknown/unverified, omit the field or return
```
null
```
.
```
download_dir
```
(
```
str = ".skills_vote/"
```
): Directory to download recommended skills into. Relative paths are resolved from the current working directory. The path must be writable from the current runtime.

recommend.py

接收包含以下字段的JSON对象：

```
query
```
(
```
str
```
)：对任务的独立、明确描述，适合作为独立的技能推荐提示词。你可以重写用户的原始请求以提升清晰度、特异性和检索效果，必要时可以添加合理的隐含细节或可能的子步骤。

client_name

(

Literal["codex", "codex-app", "claude-code", "cursor", "gemini-cli", "openclaw-cli", "opencode"] | None = None

)：该Agent的名称。如果未知/未验证或不在列表中，省略该字段或返回

null

。

```
client_version
```
(
```
str | None = None
```
)：该Agent的版本。优先使用客户端自身上报的准确版本字符串。如果未知/未验证，省略该字段或返回
```
null
```
。
```
download_dir
```
(
```
str = ".skills_vote/"
```
)：下载推荐技能的目录。相对路径从当前工作目录解析。该路径必须对当前运行时可写。

Example

示例

Before sending the request, try to identify the

client_name

and

client_version

from the executable or CLI when possible. If no command exists to extract the version and it cannot be retrieved from the environment (e.g., some desktop apps), omit these fields.

`client_name`	`client_version`	`command`	`output`
`openclaw-cli`	`2026.3.24`	`openclaw -v`	`OpenClaw 2026.3.24 (cff6dc9)`
`codex`	`0.117.0`	`codex -V`	`codex-cli 0.117.0`
`codex-app`	`26.325.21221`	`N/A`	`N/A`
`claude-code`	`2.1.85`	`claude -v`	`2.1.85 (Claude Code)`
`cursor`	`2.6.13`	`cursor -v`	`2.6.13`
`gemini-cli`	`0.35.1`	`gemini -v`	`0.35.1`
`opencode`	`1.3.0`	`opencode -v`	`1.3.0`

Next, run

recommend.py

exactly once with one JSON object on stdin via EOF. Do not pass prose around the JSON, multiple JSON objects, or extra shell flags.

recommend.py

may take around 5 minutes end to end. You must wait for it to finish completely and must not do other work before it exits. If you need progress, keep watching stdout until the command finishes.

bash

uv run -qq scripts/recommend.py <<'EOF'
{
  "query": "Add integration tests for a FastAPI skill recommendation flow, mock the gateway, and verify the returned skills and feedback flow.",
  "client_name": "codex",
  "client_version": "0.117.0",
  "download_dir": ".skills_vote/"
}
EOF

发送请求前，尽可能从可执行文件或CLI中识别

client_name

和

client_version

。如果没有命令可以提取版本，也无法从环境中获取（例如部分桌面应用），则省略这些字段。

`client_name`	`client_version`	`command`	`output`
`openclaw-cli`	`2026.3.24`	`openclaw -v`	`OpenClaw 2026.3.24 (cff6dc9)`
`codex`	`0.117.0`	`codex -V`	`codex-cli 0.117.0`
`codex-app`	`26.325.21221`	`N/A`	`N/A`
`claude-code`	`2.1.85`	`claude -v`	`2.1.85 (Claude Code)`
`cursor`	`2.6.13`	`cursor -v`	`2.6.13`
`gemini-cli`	`0.35.1`	`gemini -v`	`0.35.1`
`opencode`	`1.3.0`	`opencode -v`	`1.3.0`

接下来，通过EOF将一个JSON对象传入stdin，仅执行一次

recommend.py

。不要在JSON周围添加文本、传入多个JSON对象或额外的shell标志。

recommend.py

全程可能需要约5分钟。你必须等待它完全结束，在它退出前不要进行其他工作。如果需要查看进度，请持续观察stdout直到命令完成。

bash

uv run -qq scripts/recommend.py <<'EOF'
{
  "query": "Add integration tests for a FastAPI skill recommendation flow, mock the gateway, and verify the returned skills and feedback flow.",
  "client_name": "codex",
  "client_version": "0.117.0",
  "download_dir": ".skills_vote/"
}
EOF