Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计提醒

openclaw-refOpenClaw REF 搜索

Agent Skill

openclaw-ref 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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

499

周安装

20

GitHub Stars

24

下载量

162
CodexClaudeCursorGemini CLI

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

unknown

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-ref(OpenClaw REF 搜索)
来源仓库:https://github.com/tenequm/skills
仓库路径:skills/openclaw-ref
安装命令:
npx skills add https://github.com/tenequm/skills --skill openclaw-ref
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/tenequm/skills --skill openclaw-ref

简介

openclaw-ref 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。

  • 适用于需要根据关键词或任务场景进行信息检索的场景,支持来源仓库和 README 核验。
  • 通过 npx skills add 命令从 GitHub 安装,需结合原始 README 确认具体用法。
  • 安装前建议确认权限范围、维护状态及是否触发联网或文件操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

OpenClaw Platform Reference

Structured reference for the OpenClaw assistant platform. Source repo: ~/Projects/openclaw/. Tracking version: 2026.4.7 (refresh: 2026-04-07).

Quick Navigation

Load the relevant reference file based on the task:

Plugin & Extension System

  • references/plugin-system.md - Plugin discovery, loading, manifest format, registration API, installation CLI, SDK exports. Read when building/debugging plugins or understanding how extensions are loaded.

Configuration

  • references/configuration.md - Full config structure (OpenClawConfig), config paths, file format (JSON5), env var substitution, $include directives, validation (Zod), per-plugin config, programmatic read/write. Read when modifying or generating openclaw config.

Boot & Provisioning

  • references/boot-provisioning.md - Gateway startup sequence, BOOT.md mechanism, onboarding flows (interactive/non-interactive), plugin loading during boot, sidecar startup order, health checks. Read when designing automated provisioning or debugging startup.

Channels & Extensions

  • references/channels-extensions.md - All built-in channels (Telegram, Discord, Slack, Signal, iMessage, WhatsApp, Web) + extension channels (MS Teams, Matrix, Zalo, Voice Call, Feishu). Channel plugin registration, per-channel config, Telegram specifics. Read when adding/configuring channels.

Models & Providers

  • references/models-providers.md - Provider configuration, models.mode (merge/replace), x402 providers, model catalog structure, provider registration via plugins. Read when configuring model access or building provider plugins.

CLI Commands

  • references/cli-commands.md - Key CLI commands for config, plugins, channels, agents, onboarding, gateway, skills. Read when scripting openclaw setup or building automation.

GitHub Context (live issues, PRs, gotchas)

  • references/github-context.md - Open bugs, breaking changes, recent impactful PRs, plugin/config known issues, dev gotchas synthesized from GitHub. Refreshed via /refresh-openclaw. Read before starting any non-trivial openclaw work to avoid known pitfalls.

Key File Paths (repo-root relative)

src/plugins/           - Plugin loader, discovery, registry, install, types
src/plugin-sdk/        - 100+ scoped exports for plugin consumption
src/config/            - Config loading, types, validation, defaults, paths
src/gateway/           - Gateway server, boot, startup, server methods
src/commands/          - CLI commands (onboard, config, etc.)
src/cli/               - CLI wiring (plugins-cli, skills-cli, etc.)
extensions/            - Extension implementations (channels, memory, etc.)
skills/                - Built-in skill definitions
docs/                  - Documentation (Mintlify)

Config File Locations

  • Main config: ~/.openclaw/openclaw.json (parsed as JSON5)
  • Extensions: ~/.openclaw/extensions/
  • Skills: ~/.openclaw/skills/ (managed) + workspace skills
  • Agents: ~/.openclaw/agents/<agent-id>/
  • Sessions: ~/.openclaw/agents/<agent-id>/sessions/
  • Credentials: ~/.openclaw/credentials/
  • Override: OPENCLAW_CONFIG_PATH env var

Plugin Manifest Quick Ref

{
  "id": "plugin-id",
  "name": "Display Name",
  "kind": "memory",
  "channels": ["channel-id"],
  "providers": ["provider-id"],
  "configSchema": { "type": "object" },
  "uiHints": { "field": { "label": "...", "sensitive": true } }
}

Config Structure Quick Ref

Top-level keys in OpenClawConfig: meta, auth, acp, env, secrets, plugins, skills, models, agents, tools, channels, session, hooks, gateway, logging, browser, memory, messages, approvals, cron

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

34.4%
按下载量换算56

Claude

28.57%
按下载量换算46

Cursor

19.33%
按下载量换算31

Gemini CLI

9.26%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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