Skill rating

Reach for this when the user needs to FIND things on YouTube: videos or channels on a topic, creators covering a subject, tutorials, talks and reviews worth reading, or a channel looked up by name or

Use Chrome DevTools MCP for safe, configurable browser automation, page inspection, debugging, screenshots, network inspection, and performance analysis.

Korean crypto + news data + AI analysis for trading agents. 15 tools — dual-basis Kimchi Premium (official USD/KRW + USDT live rate) across 180+ tokens, exchange intelligence, AI sentiment analysis (w

Host-based Linux incident response and remediation skill focused on precise threat detection, forensic-safe data collection, firewall control (iptables/nftables), integrity validation, and controlled

Sync a local `wechat-report` result into Feishu Bitable after the user has reviewed the report and confirmed the sync.

Parse and deeply analyze academic papers (PDF, images) into structured research cards covering problem, methods, datasets, results, limitations, and contributions. Uses SoMark to accurately recover tw

Entry point for the Amazing PsyCoder system. Routes user requests through two mandatory three-skill chains — Experiment: Designer(5-phase design)→Coder→Reviewer, and Analysis: Designer(5-phase progres

Docker volume backup and restore for self-hosted Langfuse. Use when: backing up a self-hosted Langfuse instance, restoring Langfuse after a crash or migration, setting up daily cron backups for Langfu

对亚马逊商品评论进行深度分析，自动识别产品痛点、分析退货原因，生成改进建议和客服回复模板。Invoke when user uses /review-analysis command with a product ASIN.

Evaluates sales opportunities using BANT or MEDDICC methodology.

One-prompt Facebook Page AI setup — connect Pages, detect business type, load industry-specific skills via PageClaw

Automatically discover what your AI agent believes by analyzing its real outputs — Pattern-Based Distillation for agent behavior

AI-powered bank credit memo and credit analysis report writer - generate structured credit analysis reports, credit ratings, and facility recommendations. Updated for 2024-2026 Basel III risk weight f

LLM 应用质量评测与回归测试实操手册——从"感觉不错"到"可度量可门禁"：评测全景与指标体系（正确性/相关性/忠实度/幻觉率/鲁棒性/效率）、评测集构建（黄金数据集/对抗样本/领域评测集/规模估算）、RAG 系统评测（RAGAS 四指标：忠实度/答案相关性/上下文精度/上下文召回）、幻觉检测与度量（事实性幻觉/提示幻觉/上下文矛盾分类与检测方法）、Prompt 回归测试（用例管理/回归门禁/漂移

Build verifiable proof that a ClawHub release is live and installable. 在发布后核验 GitHub、Actions、registry、公开元数据和安装结果，避免把推送成功误当成上架成功。

Keep a drifting or half-finished project under control with one compact, conflict-checked delivery state, right-sized scope, bounded autonomy, and independent QA acceptance. Use for non-technical requ

A股基本面深度分析工具。当用户提供股票代码或要求分析股票基本面时调用。

Evaluate e-commerce pages with evidence-first SEO findings that distinguish verified issues, likely signals, editorial opportunities, unavailable checks, and appendix items.

Execute multiple token swaps in sequence. Use when user wants to rebalance, swap into multiple tokens, or execute a multi-step trading plan. Each swap goes through full safety validation independently

增强版NIO股票分析，包括实时价格、技术分析、新闻情绪、操作建议

围绕目标企业或招商项目的产业属性、投资规模、落地条件、产业带动能力、经济贡献潜力、 区域匹配度、投资可行性及风险约束等核心维度，系统评估该企业或项目是否值得招引、是否适合落地、 落地后能为区域带来什么价值，以及推进过程中需要重点关注哪些风险。本技能核心解决"这个项目值不值得招、 能不能落、落地价值有多大、对产业有没有带动、投资是否可行、政府应如何推进"等核心问题。 当用户需要评估招商项目、筛选招商

Install and authenticate OB1 (OpenBlock One), a multi-model terminal coding agent. Use when asked to install OB1, set up ob1, or when ob1 authentication/login is needed. Covers macOS/Linux install, de

Verification-first helper for proof checks and optional 0 ETH Base claim submission.

This skill should be used when evaluating the security of a ClawHub skill before installation. It performs comprehensive security risk assessment on skill directories, detecting prompt injection, mali

Reach for this when structured YouTube data is the goal: video metadata, transcripts for analysis, channel upload history, search results or playlist contents, with no Google Cloud project and no quot

研盾Skill — 五维风险评估、风险指标计算、风险等级评定

Vantage — Autonomous trading agent for Hyperliquid perpetual futures. Signal-to-execution in one loop. Runs on your machine. No cloud infra. No ongoing cost after purchase. Includes: live signal engin

AI-powered portfolio risk analysis expert for China market — covers VaR calculation, stress testing, tail risk measurement, factor exposure analysis, and risk decomposition. Built for fund managers, r

围绕一定周期内招商引资工作的整体推进情况，系统梳理招商成果、签约项目、在谈项目、 落地进展、项目转化效率、招商渠道效果、产业匹配情况、存在问题短板及后续改进方向， 形成面向领导汇报、部门复盘、招商工作优化和下一阶段行动部署的招商成效复盘报告。 本技能核心解决"这一阶段招商工作做得怎么样、取得了哪些成果、哪些项目有实质进展、 哪些环节存在问题、后续应该如何优化招商策略和推进机制"等核心问题。 当用户

Agent Threat Intelligence Exchange. Build agent-to-agent threat intelligence marketplaces: STIX/TAXII feed listing, paywall-gated IOC access, reputation-verified intel quality, autonomous SLA negotiat

金刚罩 — OpenClaw 系统守护：配置安全（pre-validate + 自动备份 + 失败回滚）、健康巡检、资源优化、故障自愈。刀枪不入，百毒不侵。

Protect agent memory: snapshot before compaction, scan memory/snapshot files for prompt-injection, secrets, and contradictions, audit what changed. Use when hardening agent memory or auditing for indi

Security vetting protocol before installing any AI agent skill. Red flag detection for credential theft, obfuscated code, exfiltration. Risk classification LOW/MEDIUM/HIGH/EXTREME. Produces structured

Drive Chromium from standard Playwright APIs with a real-device fingerprint applied inside the browser kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets

Complete web scraping methodology — legal compliance, architecture design, anti-detection, data pipelines, and production operations. Use when building scrapers, extracting web data, monitoring compet

Standardized Skill based on Alibaba Cloud CMH (Rainmeter) database evaluation tool. Full coverage: download collector, create collection account and grant privileges, run collection, export data packa

Analyze stock, crypto, and forex chart screenshots with Quant AI.

DEPRECATED — remove this legacy listing; superseded by detect-file-type-local

Enterprise-grade security framework for LobsterAI with audit logging, RBAC, input validation, output sanitization, code scanning, and dependency vulnerability detection.

会勇禾口王的AI笔记 · Agent 运行时配置体检器。检查项目的 AGENTS.md（跨 Agent 推荐） 或 CLAUDE.md（及子目录本地配置）是否符合"把它当运行时配置、不是项目说明书"的最佳实践， 给出评分卡 + 按优先级的修复建议，并可代为修复。触发：用户说「检查我的 CLAUDE.md / AGENTS.md / 运行时配置体检 / claude-md-doctor / agen

Combine transactional game analysis with Baker influence strategy for leadership conversations.

从LiDAR点云提取电力线、拟合悬链线弧垂、聚类塔架，并计算线树距离

Run Python interactively to analyze data, debug code, profile performance, validate schemas, process large files, and inspect ASTs. Use this whenever the user needs hands-on Python execution — debuggi

网络等时圈分析+多设施服务区+覆盖统计，输出服务区GeoJSON

用 OpenClaw 七大核心理念分析重大项目架构

Trustless verification protocol for autonomous agents. Discover claims, verify reality, and earn TruthScore.

Public review registry for OpenClaw skills. Agents can publish versioned reviews and read community feedback.

多期城市边界量化蔓延形态指标：紧凑度、分形维数、重心迁移与扩张面积速率

想法验证工具免费版为个人创业者提供轻量级的创业想法验证能力. 核心能力: - S.E.E.D.利基市场检查 - 基础评分(乐观/现实) - 简单PRD生成 - 技术栈推荐 适用场景: - 创业想法快速筛选 - MVP前可行性评估 - 技术栈选择参考 差异化:免费版聚焦核心验证流程,通过S.E.E.D.框架快速评估想法可行性,适合个人创业者在投入开发前判断想法是否值得追求. 适用关键词: 想法验证,

LYGO Mint Walkthrough — interactive tutorial for mint → verify → anchor snippet → optional backfill. Pure stdlib local canonicalize+SHA-256+ledger. Plain English. No subprocess, no auto-post. Pairs wi