← 返回 Skills 市场
488
总下载
1
收藏
1
当前安装
3
版本数
在 OpenClaw 中安装
/install findskill
功能描述
智能搜索和发现技能包，支持中英双语、多来源，按关键词、标签及作者快速定位所需技能。
使用说明 (SKILL.md)
name: findskill version: 1.0.4 description: 智能搜索和发现 OpenClaw 技能，支持中英双语，多来源搜索 homepage: \x3Chttps://clawhub.ai> metadata: openclaw: emoji: "🔍" requires: bins: []
FindSkill 技能包
简介
FindSkill 是一个强大的 OpenClaw 技能搜索和发现工具，帮助用户快速找到所需的技能包。
功能特点
- 智能搜索：支持关键词、标签、作者等多维度搜索
- 中英双语：完美支持中文和英文搜索
- 多来源搜索：可从 ClawHub、本地仓库等多个来源搜索技能
- 实时更新：技能数据库保持最新状态
- 详细信息：提供技能包的完整描述、使用示例和版本信息
使用场景
- 寻找特定技能：快速定位符合需求的技能包
- 技能分类浏览：按类别浏览可用技能
- 技能趋势分析：了解热门技能和最新发布
- 技能依赖查询：查看技能包之间的依赖关系
搜索语法
FindSkills 支持高级搜索语法：
- 关键词搜索：
"web scraping" - 标签搜索：
tag:automation - 作者搜索：
author:clawhub - 组合搜索：
"data analysis" tag:python
安装与使用
安装后，您可以使用以下命令：
- 搜索技能：
findskill search \x3C关键词> - 列出热门技能：
findskill trending - 查看技能详情：
findskill info \x3C技能名称>
技术栈
- Node.js
- TypeScript
- Axios（HTTP 请求）
- Fuse.js（模糊搜索）
贡献
欢迎在 GitHub 上提交 Issue 和 Pull Request！
许可证
MIT License
安全使用建议
This skill is internally consistent with being a search/discovery tool and does not request credentials. Before installing or running it: 1) note it will make outbound HTTPS requests to clawhub.ai and to an external mirror at skills.volces.com — verify you trust those hosts (network egress). 2) The repository mentions Fuse.js/TypeScript but package.json only lists axios; ensure required dependencies are installed or add missing packages before running. 3) Because there is no declared install spec, run it in a controlled environment (container or VM) and inspect the remaining truncated files not shown here for any other network endpoints or unexpected behavior. If you need zero network egress, do not install or run this skill.
功能分析
Type: OpenClaw Skill
Name: findskill
Version: 1.0.4
The FindSkill bundle is a legitimate utility designed to search and discover OpenClaw skill packages across multiple sources, including ClawHub and GitHub. The code is well-structured and modular, implementing features such as in-memory caching (cache.js), a recommendation engine based on text similarity (recommender.js), and a comprehensive translation map for bilingual search support (i18n.js). There is no evidence of malicious intent, data exfiltration, or unauthorized command execution; it interacts with public APIs (ClawHub and GitHub) solely to retrieve and display skill metadata.
能力标签
能力评估
Purpose & Capability
Name/description match the code: this is a skills search/discovery tool. It requires no credentials and only performs HTTP requests to skill indexes and mirrors. Minor inconsistencies: SKILL.md lists Fuse.js and TypeScript in the tech stack, but package.json only depends on axios and the repository is plain JS, not TypeScript. These are likely documentation mismatches rather than functional issues.
Instruction Scope
Runtime instructions are CLI-oriented and the code follows that scope. The implementation issues network calls to clawhub.ai and an external mirror at https://skills.volces.com/api/v1/search to fetch results; it caches results locally. There are no instructions or code paths that read local secrets, system config, or other unrelated files in the provided files. The use of an external mirror (not documented in SKILL.md) is worth noting.
Install Mechanism
No install spec is provided in SKILL.md/registry metadata (instruction-only), but the package contains source files and package.json (depends on axios). That mismatch means the skill will require Node.js/npm to run but the registry metadata doesn't declare an install process. Also SKILL.md mentions Fuse.js which is not present in package.json—this inconsistency may break runtime fuzzy-search features unless the missing dependency is added.
Credentials
The skill declares no required environment variables, no credentials, and no protected config paths. Its network requests are to public HTTP endpoints and it uses local in-memory caching. No secrets access is requested or evident in the code provided.
Persistence & Privilege
The skill does not request always:true, does not modify other skills or system-wide configuration in the provided code, and has no special persistence or elevated privileges. It behaves like a normal CLI/network client.
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 findskill - 安装完成后，直接呼叫该 Skill 的名称或使用
/findskill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
v1.0.4
- Added new utility modules: src/cache.js and src/utils.js
- No changes to description, features, or usage documentation
- Minor version bumped from 1.0.1 to 1.0.4
v1.0.1
- 更新描述，现在明确指出可用于发现“OpenClaw 技能”
- 版本号从 1.0.0 升级至 1.0.1
- 其余内容保持不变，无新增功能或删除项
v1.0.0
- Renamed the skill from “findskills” to “findskill”
- Updated command examples to match the new skill name
- Minor adjustments to wording and formatting for consistency
- No core functionality changes
元数据
常见问题
Find Skill 是什么？
智能搜索和发现技能包，支持中英双语、多来源，按关键词、标签及作者快速定位所需技能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 488 次。
如何安装 Find Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install findskill」即可一键安装，无需额外配置。
Find Skill 是免费的吗？
是的，Find Skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Find Skill 支持哪些平台？
Find Skill 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 Find Skill？
由 bittao（@hgta23）开发并维护，当前版本 v1.0.4。
推荐 Skills