Skill rating

Audit and consolidate HubSpot reporting dashboards. Identifies unused, duplicate, or outdated dashboards. Must be performed manually — no dashboard API is available.

Parse, analyze, and extract content from documents (PDF, DOCX, PPTX, audio). Supports OCR, table extraction, and semantic chunking.

Authorized web pentest: recon, proof-based exploits, report.

Use when: user wants to select architecture patterns, compile a spec, iterate on constraints/NFRs, audit why patterns were selected/rejected, or finalise an architecture for implementation. Not when:

Agent memory persistence and state backup. Save and restore your AI agent's memory, identity, and state. Persistent agent memory that survives crashes, restarts, and server failures. Agent state recov

Detect, investigate, and contain malicious or compromised bots using behavior analysis, policy enforcement, and escalation protocols.

Research purchases, compare prices, detect scams, and negotiate better deals.

Measure US equity market breadth using advance/decline lines, percentage of stocks above moving averages, and new highs/lows via the Finskills API.

Issue and verify SX# agent passports — cryptographic identity with hash-chain integrity, Merkle anchoring on Base

Enables the agent to review its own execution logs and deliver a professional, quantified daily work report. Defaults to 21:00 America/Los_Angeles and supports user-defined schedule plus on-demand rep

Reconciliation Report Analysis Expert - Parses ONLY local Settlement Detail report files (SETTLEMENT_DETAIL_*.csv / .xlsx) for settlement amount validation, fee analysis, and reconciliation knowledge

Evaluate potential suppliers and sourcing regions based on cost, quality, lead time, and risk factors.

Pre-meeting review coach for Lark/Feishu (or WeCom). Invoked when a Requester DMs their dedicated review-agent subagent with a draft, proposal, plan, or 1:1 agenda. Runs the four-pillar framework (Bac

Audit architecture, state management, boundaries, coupling, and maintainability risks that will make future AI or human iteration harder.

Score and optimize content for search engines using SERP-based analysis. Check word count, keyword usage, headings, readability, entity coverage, and get actionable recommendations.

股票全面分析 v3.0 - 港股/美股/A股 + 富途数据源 + 技术指标(RSI/MACD) + 多源新闻 + 财报分析 + 7大板块报告

Analyze Bitcoin, Ethereum, and major altcoins using real-time price, on-chain signals, and macro context from the Finskills API.

Detect requests for lawful site visits, in-person inspections, storefront or property checks, public observation, audits, or evidence that requires physical presence. Apply as soon as this intent appe

Model Context Protocol server exposing 7 tools, 3 resource types, and 3 prompts for AI agent consumption — Solana wallet operations, vanity address generation, message signing, and address validation

AI self-evolution framework based on Tsien's Engineering Cybernetics (1954/1980). Implements closed-loop feedback, adaptive control, self-organizing principles for autonomous AI agents. Core features:

Summarize audit findings into a structured multi-dimensional scorecard for UI/UX, feedback, mechanics, scope completeness, maintainability, and live risk.

审计 WorkBuddy 自定义模型注册表（models.json）中的免费模型：跨多个 OpenAI 兼容厂商新增可发现的免费模型、 剔除已转付费或失效的模型，保持注册表真实有效。当用户要求「审计自定义模型」「检查有没有新的免费模型」 「测试其余平台有无遗漏」「定期巡检模型清单」或希望对免费 API 模型做健康检查时使用。 本技能对海外平台执行 VPN 连通性门禁，按各厂商策略判定免费，活体实测

Enhanced security with OWASP Top 10, dependency scanning, SAST/DAST, secrets detection, compliance checks, and security hardening guides.

Simplify code that works — remove speculative abstraction, dead flexibility, and needless indirection while keeping behaviour identical and verified. Use after a feature lands ('now simplify it'), whe

执行 Coding ↔ Review 循环。A 写代码 → B Review → A 修改（可选）。支持 codex/claude-code 作为 A 或 B。

360-degree comprehensive security review Skill. Use before installing any Skill from ClawHub, GitHub, or other sources. Performs full security scans including all Skill Vetter checks plus extended sys

A股估值质量审阅专家。基于Anthropic financial-services开源仓库本土化改造， 对IPO定价、并购重组、股权激励、私募估值等场景的估值报告进行机构级审阅， 识别假设偏差、方法论缺陷和监管合规风险，输出结构化审阅意见书。

AI算力销售竞品对比分析器。实时对比AWS/GCP/Azure/火山引擎/阿里云GPU定价和规格。 支持按GPU型号、云厂商、区域筛选，输出对比表格或CSV。 触发词：竞品对比, GPU价格, 云厂商对比, 定价分析, competitor analysis, pricing comparison

Detect and rewrite AI-generated writing patterns, em dashes, rule-of-three lists, sycophantic openers, hollow buzzwords like "delve" and "landscape", and replace them with direct, human-sounding prose

基于东方财富数据库，支持自然语言搜索全网最新公告、研报、财经新闻、交易所动态及官方政策等，覆盖全球市场标的，可用于热点捕捉、舆情监控、研报速览、公告精读及投资决策等场景。Natural language search for financial information, covering authoritative sources including news, announcements, re

Strategic market research agent. Conducts competitive analysis, market sizing, pricing intelligence, and identifies business opportunities across EdTech, corporate, healthcare, legal, and HR verticals

Your intelligent food system. Absorbs, analyzes, and organizes everything you eat.

Comprehensive India-focused market intelligence tool that fetches real-time data on NIFTY, SENSEX, global indices, market news, geopolitical events, and provides AI-powered analysis with probability p

评价回复助手。好评回复、差评处理、回复模板、评价分析、改进建议、批量回复。Review response assistant with positive, negative, templates, analysis, improvement.

Enhanced code review with AI/ML-specific checks, multi-language support, security vulnerability patterns, and integration with automated testing. Covers security, performance, correctness, maintainabi

A knowledge-retrieval protocol allowing the agent to access a verified community knowledge base.

Secure execution and auditing of GEP-A2A skills. Use when interacting with the EvoMap ecosystem to: (1) Perform security scans on third-party skills, (2) Validate asset integrity using canonical hashe

云产品技术文档对比工具，自动抓取阿里云、华为云、AWS、腾讯云官方文档，生成结构化对比资料，辅助技术选型和学习

OpenClaw 多模式安全巡检工具：默认本地离线扫描，可选联网威胁情报上报。 功能范围：读取系统敏感信息（MAC 地址、主机名、系统日志、完整 Skill 清单）执行本地安全检测；在本机持久化保存扫描报告与安全基线；可选通过 --push 模式将摘要数据上传至 auth.ctct.cn 获取威胁情报评分（需用户显式同意）；可选通过 openclaw cron 设置定时任务（绑定 openclaw

Configurable quality evaluation for AI agent outputs. Define criteria, run evaluations, track quality over time. No LLM-as-judge, no API calls, pattern-based automated checks.

Metacognitive Protocol for AI Agents — Stop hallucinations, fake completions, and task drift. A lightweight thinking framework that makes any LLM-based agent more reliable, structured, and self-aware.

Turnitin AI Detection Checker - Check if text would be flagged by Turnitin's AI detection before submitting.

AWS SRE health check with FinOps — queries CloudWatch, SQS DLQ, and Cost Explorer, generates a Bedrock-powered incident diagnosis (Contexto, Soluções, CTAs), and sends a structured report to Telegram.

审计本地 openclaw 的安全配置与运行暴露面。用于检查、验证、解释和总结当前机器或沙箱中的 openclaw 相关安全设置，包括代理配置、sandbox 配置、docker 端口暴露、gateway 检查、文件权限、workspace symlink 风险、本地监听端口以及整体本地安全状态。

Detect and resolve backpressure issues in data pipelines, message queues, and streaming systems. Identify bottleneck stages, measure queue depths and processing rates, and recommend flow control strat

Turn a banker-memo analysis.md + data-provenance.md into an investment-banker-craft .pptx (real tables, bar/line charts, risk heatmap, scenario grid — NOT paragraph dumps). Step 2 of 2 in the banker p

Posts content and articles to X (Twitter). Custom fork with image upload fix: DOM.setFileInputFiles first, path leak cleanup, post-publish verification. Use when user asks to 'post to X', 'tweet', 'pu

> Active Directory security specialist analyzing identity configuration, privileged group design, delegation, authentication policies, legacy protocols, and attack-surface exposure across enterprise d

Prevent your AI agent from leaking classified terms to external APIs, subagents, or logs. Term registry + runtime redaction + pre-publish audit. Zero dependencies, zero network calls.

亚马逊评论趋势监控 Skill：按时间轴追踪评论量、评分与情绪的变化， 识别口碑拐点并定位拐点前后新增的抱怨主题，及早发现批次质量问题或竞品冲击。 Use when the user asks about review trends over time, rating decline, reputation tracking, 评论趋势、口碑变化、评分走势、舆情监控、差评突增、 趋势分析。Requ