openclaw-skills/find-skills/SKILL.md
Use when users do not know which skill fits a task, need to search available skill catalogs, compare candidates, install a matching skill, or route work to the best existing capability.
npx skillsauth add seaworld008/commonly-used-high-value-skills find-skillsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
当用户只描述目标、但未指定具体工具或技能时,优先使用本技能做自动匹配。Find Skills 是 Agent 的“大脑插件中心”,它能理解用户意图,并从浩如烟海的 ClawHub 仓库中精准定位、安装并配置合适的技能。
npx clawhub@latest install find-skills
clawhub install。image-edit 时)。parse-xlsx 而非仅仅是 xlsx。list_agent 或搜索接口。description 和 metadata。verified 标签或在大厂生产环境验证过的技能。clawhub install <skill-name>。README.md,识别是否需要环境变量(ENV)或 OAuth 授权。composio_connect_app 完成连接。hello world 级别的测试指令,确保技能真实可用。puppeteer, ffmpeg 等底层二进制工具)。### 用户目标
[描述:实现一个能够自动分析 XHS 数据并生成周报的机器人]
### 识别出的关键词 (Generated Keywords)
- `xiaohongshu-crawler`
- `data-analysis-pandas`
- `markdown-report-generator`
- `chart-visualizer`
### 推荐技能组合 (Recommended Stack)
1. **xhs-analyzer** (评分 4.8): 包含成熟的爬虫逻辑和反爬策略。
2. **super-report** (评分 4.5): 支持将 JSON 直接转化为美观的 Markdown。
3. **quick-chart** (评分 4.9): 能够生成静态图片图表并插入报告。
### 是否立即安装前两项? (Confirm Installation?)
> [Yes] / [No] / [Tell me more]
// 示例:查询具备“代码审查”能力的技能
const candidateSkills = await mcp_call({
name: 'search_available_skills',
arguments: {
keyword: 'code-review',
limit: 5,
sort_by: 'downloads'
}
});
python-scripts,现在想迁移到云端。Find Skills 会主动寻找 vercel-deploy 和 supabase-connector 等技能来适配。dependency vulnerability 时,Find Skills 会搜索具备“安全扫描与自动补救”能力的技能(如 security-vetter)。description 解析会消耗较多 Token。find-skills 进行横向对比。SKILL.md 获取该技能的 Common Patterns。development
Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.
testing
Orchestrating specialist AI agent teams as a meta-coordinator. Decomposes requests into minimum viable chains, spawns each as an independent session in AUTORUN modes, and drives to final output. Use when a task spans multiple specialist domains, requires parallel agent execution, or needs hub-and-spoke routing across the skill ecosystem.
development
Converting document formats (Markdown/Word/Excel/PDF/HTML). Converts specs from Scribe and reports from Harvest into distributable formats; generates reusable conversion scripts. Use when converting documents, building accessibility-compliant PDFs, or creating Pandoc/LibreOffice pipelines.
testing
Curating cross-agent knowledge and guarding institutional memory. Extracts patterns from agent journals into METAPATTERNS.md, detects knowledge decay, propagates best practices, prevents organizational forgetting. Use when consolidating cross-agent insights, curating memory, or auditing knowledge decay.