发现优质的 AI Agent 技能

聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用

80,283浏览
2下载资源
1用户
广告位 728x90

共 1082 个技能

🔗

Hugging Face API Tool Builder

Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. You can access the API directly, as well as use the `hf` command line tool. Model and Dataset cards can be accessed from repositories directly.

aiapicommandsickn33+1
21942
0
🔗

Toolbars

A toolbar provides convenient access to frequently used commands, controls, navigation, and search.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

Menus

A menu reveals its options when people interact with it, making it a space-efficient way to present commands in your app or game.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

Edit menus

An edit menu lets people make changes to selected content in the current view, in addition to offering related commands like Copy, Select, Translate, and Look Up.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

ComfyUI Gateway -- Troubleshooting Guide

Comprehensive troubleshooting reference for diagnosing and resolving issues with the ComfyUI Gateway. Every section follows the **Symptom -> Cause -> Solution** format with concrete commands you can run immediately.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

Claude Settings Audit

Analyze this repository and generate recommended Claude Code `settings.json` permissions for read-only commands.

claudecommandsickn33agentic-skills+1
21942
0
🔗

ViewModels & Commands

In a Zafiro-based application, ViewModels should be functional, reactive, and resilient.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

Android UI Verification Skill

This skill provides a systematic approach to testing React Native applications on an Android emulator using ADB commands. It allows for autonomous interaction, state verification, and visual regression checking.

commandsickn33agentic-skillsai-agents+1
21942
0
🔗

Errors

> Format: `[YYYY-MM-DD] COMMAND_OR_TOOL | what failed | fix or workaround | count:N` > Dedup: grep before adding. Increment count if exists. Promote at count:3+.

aicommandopenclawarchive+1
2329
0
🔗

Reliable Tool Context

Use this skill to build reliable tool context whenever command output will be analyzed by the model and correctness matters. Capture once, query from artifacts, and return compact answers without copying raw payloads into model context.

commandopenclawarchivebackup+1
2329
0
🔗

Browser Automation with browser-use CLI

The `browser-use` command provides fast, persistent browser automation. It maintains browser sessions across commands, enabling complex multi-step workflows.

aiautomationworkflowcommand+1
2329
0
🔗

Each entry: { command: "...", expect: "..." }

- command: "openclaw health --json" expect: "ok" resume: - "向用户汇报重启结果" rollback:

commandopenclawarchivebackup+1
2329
0
1 / 91下一页
广告位 728x90