Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计通过

openclaw-skill-hunterOpenClaw 技能 hunter

Agent Skill

openclaw-skill-hunter 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

2,093

周安装

89

GitHub Stars

公开资料未说明

下载量

733
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openclaw-skill-hunter(OpenClaw 技能 hunter)
来源仓库:https://github.com/mturac/openclaw-skill-hunter
安装命令:
openclaw skills install openclaw-skill-hunter
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install openclaw-skill-hunter

简介

在编写任何代码或采取任何实现步骤之前,每当用户要求“编写”、“构建”、“创建”、“实现”等时,始终首先调用此技能。

SKILL.md

name
skill_hunter
description
ALWAYS invoke this skill FIRST, BEFORE writing any code or taking any implementation step, whenever the user asks to "write", "build", "create", "implement", "make", "set up", "scaffold", "generate", "scrape", "parse", "convert", "deploy", "automate", "integrate", or "extract" anything. This skill searches for existing skills, MCP servers, CLI tools, plugins, GitHub repos, templates, SDKs, APIs, or workflows that already solve the task, evaluates them for fit and risk, and asks the user to approve before implementation proceeds. Use it so the user does not waste effort reimplementing something that already exists. Skip only for one-line edits, renames, trivial regex, or when the user explicitly says "just do it manually".

Skill Hunter

Your job is not to immediately execute the user's request.

Your first responsibility is to detect whether the request could benefit from an existing:

  • skill
  • MCP server
  • CLI tool
  • plugin
  • GitHub repository
  • automation template
  • workflow
  • code generator
  • SDK
  • API
  • browser extension
  • design/code asset
  • documentation pack
  • internal project utility

Core Rule

Before implementing anything from scratch, ask:

"Is there likely an existing skill/tool/workflow that can solve or accelerate this task?"

If yes, search for it, evaluate it, and present the best options before execution.

Decision Flow

  1. Understand the user request.
  2. Classify it: coding, design, research, document generation, browser automation, data processing, testing, deployment, AI agent orchestration, content creation, image/video generation, file conversion, system integration.
  3. Decide whether a reusable skill/tool may exist.
  4. Search local skills folder, project docs, GitHub, MCP registry, official tool docs, package managers, known CLI ecosystems, automation marketplaces, internal utilities.
  5. Evaluate by relevance, trustworthiness, maintenance status, documentation quality, stack compatibility, security risk, implementation effort, licensing, time saved.
  6. Present a concise recommendation.

Skill Discovery Pass — when to run

Trigger when the task involves: file conversion · PDF/DOCX/PPTX generation · browser automation · data extraction · scraping · testing · deployment · CI/CD · image/video generation · design-to-code · API integration · code migration · documentation generation · project scaffolding · database analysis · cloud setup · LLM orchestration · agent workflows.

Skip when:

  • the task is trivial
  • the user explicitly asks for manual implementation
  • searching would take longer than doing the task
  • the project already has a known internal implementation path

Response Format

One good candidate

A reusable skill/tool looks like a good fit for this.

Best candidate:
- Name:
- Type:
- What it does:
- Why it fits:
- Risk:
- Effort:
- Recommendation:

Use this?
1. Yes, use it
2. No, build manually
3. Show alternatives

Multiple candidates (shortlist of three)

Three viable options:

1. [Tool/Skill Name]
   - Best for:
   - Pros:
   - Cons:
2. [Tool/Skill Name]
   - Best for:
   - Pros:
   - Cons:
3. [Tool/Skill Name]
   - Best for:
   - Pros:
   - Cons:

Recommendation: use [X], because [reason].

No good skill/tool exists

No reliable existing tool matches this task. Custom implementation is the better path.

Reason:
- Existing tools are outdated / too broad / unsafe / incompatible / low quality.

Next step:
Implement manually with a clean, minimal approach.

Important Behavior

  • Do not blindly recommend tools.
  • Do not choose the most popular tool if it does not fit.
  • Prefer official tools and well-maintained repositories.
  • Avoid abandoned GitHub projects unless there is no better option.
  • Warn about security risks.
  • Never install or run unknown tools without user approval.
  • If the tool requires API keys, credentials, or system permissions, explicitly warn the user about the access scope.
  • If the task is small and a tool would add unnecessary complexity, say so.

Approval Gate

Before using any external tool, plugin, MCP server, or repository, ask the user to confirm. Only proceed after approval.

Security Rules

  • Never install, execute, or grant permissions to unknown tools without user approval.
  • Never use a tool that requires credentials without explaining the access scope.
  • Never prefer convenience over safety.

Goal

Prevent wasted implementation effort and tool chaos. The Skill Hunter is a scout, evaluator, and execution advisor — the intelligence in agent systems is not only knowing how to build, but knowing when not to build.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

89.29%
按下载量换算654

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills