'Analyze competitor SEO/GEO: keywords, content, backlinks, AI citations, traffic share gaps. 竞品分析/竞争对手'

当需要构建 Web 组件体系（React/Vue/Svelte 组件模式与 API 设计）时使用。

每次回复末尾自动提供上下文相关的快捷选项，形成持续对话循环。

當使用者要求「分析資料、報表摘要、數據趨勢、建儀表板、處理 CSV/Excel、做資料視覺化」時使用。引導以結構化方式做資料分析、摘要與圖表，並可與本專案 data_analyst_agent、echarts、RAG 整合。

>-

生成或修订 prototype.md，并在文档依据足够时生成本地可运行的 prototype-demo。用于演示和评审，不要求真实后端或生产数据。

>

Unreal Engine single-entry skill with Hardness (H/M/L) and subagent orchestration for discovery, implementation, and verification.

Codex-compatible entry point for the former /instinct-status command. 查看所有已学习的本能及其置信度状态

Simulator validation and test runs for Linux boot, CoreMark, and Dhrystone in this project; use when verifying simulator correctness or running quick regression commands.

Use when writing or updating mobile-first Playwright coverage for the badminton H5 flow, including home CTA, upload readiness, candidate clip selection, processing progress, report rendering, history, compare, and error recovery.

Scene understanding and analysis. Use when users want to get a summary, overview, dependency report, or export of the current scene state. Triggers: scene summary, analyze, overview, statistics, count, export report, 场景摘要, Unity分析, Unity概览, Unity统计, 导出报告, 依赖分析.

claims-extractor

读取当前项目的 PR 审查结果，自动修复中等和严重问题，轻微问题需确认后再决定是否修复

>

legal-due-diligence

1. imageloader 的话自己怎么设计这个功能

academic-search

> 實戰驗證於 2026-03-08 | OpenClaw 2026.3.2 | macOS (Apple Silicon)

>

配置和管理终端多彩主题轮换系统 — 添加/修改/删除主题、调整颜色和背景混合比例、排查显示问题。当用户提到终端主题、终端颜色、终端配色、prompt颜色、tab颜色时触发。

自动化处理 Word 和 Excel 文件。使用 Python 脚本读取、写入、格式化文档和表格。支持批量处理、模板填充、数据提取和格式转换。

>

CTF 逆向工程技术。当挑战提供未知二进制文件需要分析算法逻辑、游戏客户端需要破解验证、混淆代码需要还原、自定义 VM 需要解释执行时使用。覆盖 Ghidra/IDA 静态分析、GDB/Frida 动态调试、反调试绕过、WASM/.NET/APK/Python 字节码/Go/Rust 多平台逆向

name: openclaw-clean

> 个人自动化任务集合，通过 macOS launchd 定时调度，自动执行日常任务并同步到多个平台。

Use when building a thread-safe data persistence layer in Swift using actors with in-memory cache and file storage.

Go 测试模式，包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。遵循具有惯用 Go 实践的 TDD 方法论。

Generate comprehensive R tutorials for specialized applications (health economics, qualitative research, signal processing, environmental epidemiology) with theory + practice workflow. Use when: (1) User requests domain-specific tutorials, (2) File names match [number]-[topic].rmd pattern, (3) Keywords: TreeAge, CEA, text mining, wavelet, VMD, DLNM, WQS, BKMR.

Create content records in Notion "内容中心" database after publishing articles to various platforms.

本 Skill 提供支付宝智能体钱包和AI支付相关产品介绍，该服务是基于 A2M 智能收协议（HTTP 402）的付费资源。买家（消费者 Agent）通过本 Skill 向卖家服务端发起资源请求，服务端将返回 402 Payment-Needed 响应报文，买家需将该报文传递给支付宝的 alipay-pay-for-402-service 技能以完成付款。

>

**持续学习与自我改进引擎** - 基于 RLHF + 经验驱动学习

Archive Behance projects to Eagle DAM (Digital Asset Management) library. Use when user wants to archive or save a Behance project URL to their Eagle collection with proper metadata. Triggers include requests like '归档 https://www.behance.net/gallery/...', '保存 Behance 项目', 'archive behance project', or any request to download or save Behance gallery content to local Eagle library.

AI辅助需求分析与设计规范生成，强调多代理编排、结构化产物和质量门禁。

>

Credit risk data cleaning and variable screening pipeline for pre-loan modeling. Use when working with raw credit data that needs quality assessment, missing value analysis, or variable selection before modeling. it covers data loading and formatting, abnormal period filtering, missing rate calculation, high-missing variable removal,low-IV variable filtering, high-PSI variable removal, Null Importance denoising, high-correlation variable removal, and cleaning report generation. Applicable scenarios arecredit risk data cleaning, variable screening, pre-loan modeling preprocessing.

Evidence-based competitor tracking and analysis. **All analysis must be based on actual code, never assumptions.**

deep-research

>

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.