← 返回
未分类 中文

Skill Downloader

Discover, compare, review, install, or update OpenClaw skills from trusted sources with a review-first workflow. Use when the user wants to search for a skil...
从可信来源发现、比较、审查、安装或更新 OpenClaw 技能,采用先审查的工作流程。适用于用户想要搜索某项技能时。
yyang100 yyang100 来源
未分类 clawhub v0.1.20 1 版本 99853.2 Key: 无需
★ 1
Stars
📥 660
下载
💾 2
安装
1
版本
#latest

概述

Skill Downloader

Provide a review-first workflow for discovering and installing skills from trusted sources.

Scope

Use this skill for:

  • searching for skills
  • comparing candidates from one or more trusted sources
  • inspecting ClawHub-hosted skills before installation
  • installing or updating a skill after explicit user approval

Keep recommendations proportional to the information available. If important fields are missing, say so before making a recommendation.

Core workflow

  1. Identify whether the user wants discovery only, inspection, or discovery plus installation.
  2. Search trusted sources and collect source-labeled results.
  3. Inspect the most relevant candidates when detailed metadata is available.
  4. Present the result set with clear completeness labeling:
    • Full: enough information to compare and recommend
    • Partial: some fields are unavailable
    • Minimal: only basic identification is available
  5. Ask for explicit approval before any install or update step.
  6. Review source material before writing files.
  7. Prefer official registry workflows when available.
  8. Preserve user data when updating an existing skill.

Source policy

Use trusted sources first. Prefer ClawHub when the requested skill is hosted there. Use supplementary sources when needed to confirm availability, compare options, or recover from partial metadata.

If rate limits or source failures prevent a full inspection:

  • report the limitation clearly
  • mark missing fields as unknown
  • let the user choose whether to wait, proceed with partial data, or stop

Inspect workflow

When the user asks to inspect a specific result (for example "inspect 第一个" or "inspect 这个"):

  1. Resolve the target skill name or slug from the previous result list.
  2. Run the official inspection workflow first.
  3. If more detail is needed, prefer reading the inspected skill's listed files or primary text files.
  4. Do not invent or guess unsupported CLI subcommands.
  5. If a field is unavailable, mark it as unknown instead of inferring it.
  6. Do not claim that a candidate is newer, better, equivalent to a built-in skill, or safer than another option unless the evidence explicitly supports that statement.

Inspect output template

For inspected skills, prefer this structure:

  • Name
  • Slug
  • Owner
  • Version
  • License
  • Security status
  • Summary
  • Key capabilities
  • Requirements / dependencies
  • Notable files reviewed
  • Unknown fields
  • Recommendation status: yes, conditional, or no
  • Recommendation basis: Full, Partial, or Minimal

Only give a firm recommendation when the information level is Full.

Installation policy

Do not install or update anything without explicit user approval.

When installing or updating:

  • use the requested destination (~/.openclaw/skills/ for global or {workspace}/skills/ for local by default)
  • prefer official registry workflows when available
  • use a review-first fallback workflow only when needed
  • avoid symlink-based installs
  • preserve unrelated user data during updates

Safety policy

Treat this skill as review-first, not execution-first.

  • inspect source material before writing files
  • prefer trusted registries and repository sources
  • avoid silent assumptions when metadata is incomplete
  • explain risks if a candidate appears suspicious
  • avoid unsupported claims about parity, freshness, or superiority without direct evidence

References

For low-level source handling details, fallback mechanics, and implementation notes, read:

  • references/advanced-workflows.md

版本历史

共 1 个版本

  • v0.1.20 当前
    2026-05-03 04:24 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,398 📥 323,226
ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,110 📥 833,549
ai-agent

Agent Browser

rez0
用于 AI 代理的浏览器自动化 CLI。当用户需要与网站交互(包括浏览页面、填写表单、点击按钮、截图等)时使用。
★ 838 📥 315,855