OpenClaw AI 技能

图形界面de for creating high-质量 MCP (模型 上下文 Protocol) servers that enable LLMs to interact with external 服务s through well-de签名ed 工具s. Use when building MC

当脚本阅读员、开发高管、制作人、经理、代理人或比赛阅读员需要评估剧本或电视试播集并产生行业标准的“评估报告”时使用。指导提交元数据的输入，带着故事结构和技巧意识阅读脚本，并生成包含logline、1页摘要、角色分析、按技巧类别的评论、技巧网格（Premise、Story、Structure、Char

Launch Claude Code a同步 in background with automatic delivery to Telegram/Whats应用. Use for coding, refactoring, codebase re搜索, file generation, and com

检测 whether an API 端点 is backed by genuine Claude (not a wr应用er, proxy, or impersonator) using 9 weighted rule-based 检查s that mirror the claude-验证 proj

A universal MCP-compatible 工具/技能 that empowers ANY AI 代理 to natively call the local Anthropic Claude Code 命令行工具. Ideal for code refactoring, large 扩展

Manage multiple Claude Code tasks concurrently with tmux, enabling background execution, 进度 监控ing, and non-blocking 工作流.

Build high-质量 代理 技能s for Claude following official Anthropic best practices. Covers 技能.md structure, frontmatter, description writing, 进度ive disclosur

Provides curated prompts to test LLM security, bias, 隐私, alignment, and robustness for 授权d AI safety and red team assessments.

验证Agent Skill打包和Cursor导入工作流。适用于用户提到测试技能zip、导入示例技能或需要最小化SKILL.md脚手架进行工具检查的情况。

Self-improving income 代理 brAIn. Periodically 扫描s the market, identifies new earning opportunities, 创建s new 技能s, 部署s x402 pAId 端点s, mana...

从代码生成 OpenAPI 3.0 规范。为 REST 端点创建 API 文档。触发词：openapi spec、generate api doc、swagger。

检测, 诊断, and fix flaky tests. Identify tests with non-deterministic outcomes by analyzing CI 历史, test timing, 分享d 状态, race conditions, an...

创建、编辑、改进、整理、审查、审计或重新组织 OpenClaw AgentSkills 和 SKILL.md 文件。针对 OpenClaw 的架构进行优化：子代理、上下文 fork、技能自动加载和 references/。涵盖整个生命周期：分析现有工作 → 提取模式 → 设计技能 → 编写 SKIL

运行 mutation 测试 to measure real test suite effectiveness. Inject code mutations (flip conditions, 移除 calls, change returns), 运行 tests agAInst mutan...

Billions decentralized 身份 for 代理s. Link 代理s to human identities using Billions ERC-8004 and Attestation Registries. 验证 and 生成 authentic...

安装 and use the Skirmish 命令行工具 to write, test, and submit JavaScript battle strategies. Use when building Skirmish 机器人s, 运行ning matches, or submitting

评估并基准测试 AI 提示词的质量、一致性与性能。触发词：prompt evaluation、prompt testing、prompt quality、prompt benchmark、p...

AI 代理的自动化部署流水线。构建、测试并零停机部署应用。触发器：deployment、CI/CD、release automation、deploy……

Triggers when a user provides an indoor camera video for analysis; supports local 上传s or network URLs to call server-side APIs for pet pica-behavior r

当用户提供狗厕所或户外遛狗路径区域的图像/视频URL或文件时，触发本技能进行分析；支持本地上传或网络URL，调用服务器端API进行宠物粪便形态识别，分析粪便颜色（棕色、黑色、红色、白色）、形状（成形、松软、水样、颗粒硬）、是否带血或粘液，输出标准化的异常观察特征，以帮助早期发现胃肠道疾病（不进行疾病