Skill rating

门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。

Discover and verify specialist Airnode Hub APIs before general-purpose web search.

Automated appointment management for beauty salons, clinics, studios, and photo booths. Handles booking requests, calendar sync, conflict detection, reminders, no-show tracking, and waitlist managemen

面向团队与企业的高级结构化分析工具,在免费版基础上扩展批量分析、协作评审、自定义框架等能力。核心能力: - 多领域深度分析(代码、数据、文本、决策、可视化、架构) - 批量文件分析与聚合报告生成 - 团队协作评审与多视角交叉验证 - 自定义分析框架与模板管理 - 历史分析存档与趋势追踪 适用场景: - 企业代码库批量安全审查 - 架构决策多视角评审 - 团队复盘与改进追踪 差异化: - 兼容免

时空智能分析法（v2.0 完整版）。纵向时间线 × 横向对照 × 交汇判断，必须先检索后下判断。含双交付模式（摘要→完整版）、当代实证研究不用学术库、引用覆盖率门槛、PDF 输出配方、松哥写作约定、5 子 agent 工程化流水线、数据采集脚本与模板等。触发：「时空智能分析」「时空分析」「spatiotemporal」「深度研究报告」「竞争格局分析」，或用户要求「研究一下 X 与 Y 的关系」这类

Review application code in the current workspace for concrete security issues and provide proportionate fixes. Use when the user asks for a code security audit, secure rewrite, permission review, or r

Detects morbid behavioral cues in poultry and pigs from continuous barn videos — such as difficulty standing, ruffled feathers/piloerection, isolation, drowsiness and appetite loss — and outputs behav

Join the MoltLab research community — propose claims, run computations, vote on ideas, debate research, write papers, and review your colleagues' work.

AI-powered bioinformatics analysis platform with intelligent auto-organization and comprehensive Chinese report generation. Auto-detects sequencing data, generates R scripts, saves all outputs to stru

概念验证中心平台建设运营全流程技能。当用户需要规划、建设或运营概念验证中心平台时使用，涵盖规划定位、政策资金、创新人才、管理团队、产业领域、知识产权、运营模式、合规管控、项目管理、生态建设、合作伙伴、年度目标、阶段考评等平台层面全流程。适用于高校院所、孵化器、产业园区、央企大院等机构的概念验证中心平台建设运营。本技能聚焦TRL1-4阶段的可行性验证平台，与中试基地技能（TRL4-7工艺放大验证）形

面向团队与企业的高级 Git 历史分析工具,在免费版基础上扩展团队复盘、同意管理、趋势追踪等能力。核心能力: - 团队复盘分析(需全员同意) - 同意管理与审计追踪 - 多仓库批量扫描与聚合报告 - 历史趋势追踪与基线对比 - 匿名化输出与隐私保护 适用场景: - 团队迭代复盘与改进 - 多仓库代码质量审计 - 代码质量趋势追踪 差异化: - 兼容免费版全部能力,无缝升级 - 支持团队复盘与同

Encrypted backups, integrity verification, and data retention enforcement for Greek legal requirements (5-20 year retention). AES-256.

Draft or review writing to avoid structural AI tells and preserve a rough human voice.

Verify any Bitcoin (BSV) Merkle proof — free, no account, trusting no one including bsv.cx — against a block-headers node bsv.cx syncs itself over the BSV P2P network. Send a raw TSC proof, a BEEF env

Use this skill when auditing or operating the Trinity/OpenClaw self-evolution loop: checking version status, preflight health, capability validation gates, direction radar output, failure-repair fallb

Validated CAG decision memory for OpenClaw tools, agents, and long-running project sessions.

Track BTC self-custody metrics — COLDCARD Q vault health, mempool fee estimation, UTXO management, and on-chain verification. Designed for sovereign holders who verify, don't trust.

MCP security audit for AI-agent configs — run it before connecting any MCP server. 14 automated static rules catch hardcoded credentials, arbitrary command execution, writable mounts, SSRF attack surf

Automated code review with fix suggestions and in-place code repairs.

Analyze failed GitHub Action jobs for a pull request.

使用Qwen模型分析视频内容,支持本地文件与远程URL,可自定义提示词,适合个人创作者。

Monitor Persian-language X (Twitter) activity related to Iran, detect high-signal geopolitical events, translate posts, score escalation risk, and generate actionable intelligence reports with optiona

Role-based access control for Greek accounting firms. Login, role hierarchy, per-client permissions, session management, audit logging.

Protects against malicious or compromised OpenClaw skills by auditing newly installed skills before first use, detecting red-flag patterns, and enforcing hard-floor safety rules that no skill can over

Validates Agent Skill packaging and Cursor import workflows. Use when the user mentions test skill zip, imports a sample skill, or needs a minimal SKILL.md scaffold for tooling checks.

Multi-model ensemble weather forecasts comparing GFS, ECMWF, JMA, GEM, ICON, ARPEGE, GraphCast and more. Get high temperature predictions from up to 9 independent weather models with agreement analysi

Security scanner for ClawHub skills. Detects malicious code, obfuscated payloads, and social engineering before installation. Three-layer analysis: pattern matching, deobfuscation, and LLM intent anal

ClawGuard v3 Auditor - 企业级 Skill 安全审计器，支持意图偏离检测、SAST、供应链安全、ML 异常检测。当用户要求审计、检测、安装前检查一个 Skill 的安全性时触发。

Analyze the weekly attendance records of employees at Zhuihui Branch and generate an attendance report in docx format. At the same time, output an xlsx file as a detailed supplement.

太极架构多 Agent 协作框架，支持集中式、分布式，元混合三种执行模式。基于 Redis 消息总线，实现 Planner/Drafter/Validator/Dispatcher 四个阶段的工作流。

玩手机检测告警技能。通过摄像头抓图→AI 分析→TTS 语音→设备播放的完整流程。Use when: 需要监控玩手机行为并自动告警、课堂/考场/会议室纪律监控、通过萤石摄像头进行 AI 行为检测。

AI-powered code review for Q/kdb+ — catch bugs in the most terse language in finance

墨言安全审计 — Agent 生态首个可验证信任验证服务。PMI 四维向量评分 + DecayProof 可验证衰减 + κ_Axiom 自治审计。43 防线 / 7 层纵深防御。支持支付宝/微信/ClawTip AI 支付闭环。64/64 TSC 合规，W3C agent-identity 三方收敛。

For novel, fiddly, or infrastructure-sensitive work, search prior notes and solved cases for a structurally similar problem. Reuse the method as a hypothesis, verify it against current state, test the

万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl read_only 流式读取（iter_rows 支持 10 万行以上）、Parquet 转换加速、内存优化、分块处理和大文件写入模式。**遇到以下任一情况就主动使用本 skill**：①数据行数 ≥ 10k（由 sn-da-excel-workflow 的行数评估步骤触发）；②用户出现触发词：大文件 / 大数据量 / 性能优化

Use when analyzing SonarQube issues and turning them into SPEC SDDs for TDD implementation.

Analyze mutual fund performance, holdings, risk metrics, and investment suitability

Automated daily health check for OpenClaw instances. Verifies memory file presence, detects stale/overdue cron jobs, and surfaces system status. Intended for scheduled execution via cron.

Detect physical conflicts (fighting, shoving, scuffling) between 2+ people from one or many RTSP camera streams concurrently. Continuous mode: a single Python process monitors every configured camera

(已验证) 根据客户和场次，自动生成详细的《直播复盘与成长规划报告》。

跨Agentaudit日志standard。7类日志（决策/操作/错误/security/性能/访问/data）+ compliance检查点 + audittrackstandard，适配fully AI companygovernframework。

在代码提交前或任务完成后使用，进行代码审查

Use when the user runs /wdp-ctx to save, load, verify, export, or clear the project's context so it survives session reset and can be resumed by any coding agent. Subcommands: sum, init, profile, veri

Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, traini

Chat with Immanuel Kant (1724–1804), Prussian philosopher who unified rationalism and empiricism. Author of the Categorical Imperative and the Critique of Pure Reason. Invoke with /kant to converse in

Peer-review AI-authored research papers on AgentPub. Sets up a recurring loop that claims review assignments, writes structured reviews, and submits them. Also supports submitting your own papers.

Clawpilot is your skill installation advisor. It analyzes task intent, recommends suitable skills, compares tradeoffs, explains risk, and suggests an installation order. Version 1 provides advice only

Use this skill when the user asks for 品牌一致性、品牌审核、视觉规范、Brand Check、AI内容质检，或要为电商、广告、营销、短剧、漫剧、带货与种草内容完成品牌视觉一致性审核。它服务品牌市场、设计管理、广告代理商和内容中台：接收品牌规范、标准素材、待检图片或视频、渠道和例外规则，交付Logo、颜色、字体、构图、影调、人物和语气偏差清单与修复优先级。特色是

Multi-agent coordination. Role registry, task routing, workload balancing, trust-verified handoffs. Free version — core functionality included. Pro version ($19) — priority queues, team performance tr

Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts,