← 返回 Skills 市场
108
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install tsy-gzh-find-topic
功能描述
调用后端接口，获取公众号爆款选题推荐，直接输出原始 data。
安全使用建议
This skill calls an external API (default https://api.tangshiye.cn) and requires an API key (TSY_API_KEY) read from a global .env, but the skill metadata does not declare that requirement — that's the primary red flag. Before installing, verify: 1) you trust the remote domain (api.tangshiye.cn) and its privacy/security practices; 2) the API key you supply is scoped minimally and not your broader credentials; 3) you are comfortable that the key will be sent as a query parameter (may be logged by proxies); 4) the skill will output raw response data (which may include sensitive info), so avoid passing secrets you wouldn't want printed. Prefer the author update the manifest to declare required env vars (TSY_API_KEY and optional TSY_API_URL) or provide clearer provenance; if unsure, do not install or run the skill with production credentials.
功能分析
Type: OpenClaw Skill
Name: tsy-gzh-find-topic
Version: 1.0.0
The skill is a standard API wrapper for the 'tangshiye.cn' service, designed to fetch WeChat topic recommendations. It uses a local Python script (scripts/generate_request_body.py) to calculate timestamps and performs a WebFetch POST request using an API key provided in the environment variables. The logic is transparent, lacks obfuscation, and does not exhibit any signs of data exfiltration or malicious intent.
能力评估
Purpose & Capability
The name/description say: call a backend API and output the response data, which matches the SKILL.md and the small helper script. However the manifest lists no required environment variables or primary credential while SKILL.md explicitly reads TSY_API_URL and TSY_API_KEY from a global .env — this metadata/instruction mismatch is unexpected.
Instruction Scope
Instructions are narrowly scoped: run the bundled Python script to produce a JSON body, POST it to {BASE_URL}/gzh/findTopic?apikey={SATOKEN}, and output the response.data raw. That scope is coherent with the stated purpose. Concern: the skill requires reading a global .env for TSY_API_KEY/TSY_API_URL (an access to host configuration) which is not declared; the agent will send the API key as a query parameter to an external domain and then output raw response data without filtering.
Install Mechanism
No install spec; the only code is a tiny, readable Python script that generates timestamps. No downloads or extracted archives — low install risk.
Credentials
SKILL.md requires TSY_API_KEY (called SATOKEN) and optionally TSY_API_URL from a global .env, but the manifest declares no required env vars or primary credential. Requiring a secret API key is proportionate to calling a protected backend, but failing to declare that in metadata is an inconsistency that could lead to unexpected secret exposure. Also the API key is sent as a query parameter (?apikey=...), which may be logged by intermediaries — a privacy risk the user should consider.
Persistence & Privilege
always is false, no install-time changes or system-wide modifications, and the skill does not request persistent presence or elevated privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install tsy-gzh-find-topic - 安装完成后，直接呼叫该 Skill 的名称或使用
/tsy-gzh-find-topic触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
tsy-gzh-find-topic 1.0.0
- 初始版本，支持通过后端接口获取公众号爆款选题推荐。
- 调用 POST {BASE_URL}/gzh/findTopic，自动处理参数与请求体生成。
- 只输出接口响应的原始 data 字段，不进行任何加工、分析或补充。
- 严格按 HTTP 和接口状态判断输出结果，若配置或请求异常则直接报错。
元数据
常见问题
tsy-gzh-find-topic 是什么？
调用后端接口，获取公众号爆款选题推荐，直接输出原始 data。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 108 次。
如何安装 tsy-gzh-find-topic？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tsy-gzh-find-topic」即可一键安装，无需额外配置。
tsy-gzh-find-topic 是免费的吗？
是的，tsy-gzh-find-topic 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
tsy-gzh-find-topic 支持哪些平台？
tsy-gzh-find-topic 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 tsy-gzh-find-topic？
由 AI架构师汤师爷（@tangshiyegit）开发并维护，当前版本 v1.0.0。
推荐 Skills