Skill rating

动态评审团多维评分与周期迭代工作流程。根据任务自动生成适合的评审团成员，支持极端评审官加入，形成包围式评审阵势。触发词：评审团、多维评分、迭代优化、代码评审、质量评估、周期迭代、动态评审。

Email management skill for AI assistants with real-time notifications, smart categorization (7 categories), verification code extraction, and HTML content sanitization. Supports Gmail, QQ Mail, and Ne

当某个 Bug 频繁复现、线上有缺陷需要做事后分析、或者发现同一类问题反复出现需要根治时使用此技能。从症状出发用 5Why、因果图和鱼骨图等方法系统化定位缺陷根源，区分直接原因、间接原因和系统原因。不要只修症状——根因分析的价值在于找到让同类 Bug 不再发生的系统性改进措施，同时分析漏测原因来优化测试设计。 ⚠️ 本技能示例可能调用外部日志/监控工具，请在受控环境执行。 本技能属于 QA Tes

Assess the current PHI Readiness Stage (PRS) of a workload, repository, system, or environment; determine HIPAA applicability and role; identify evidence gaps; and recommend next actions using officia

汇总本周完成、阻塞、经验教训与下周计划，形成管理层版和执行版摘要。；use for weekly-review, planning, retrospective workflows；do not use for 杜撰完成项, 替代工时系统.

当开发提了 PR、代码变更需要确定测试范围、或者想通过分析代码来预测可能出 Bug 的区域时使用此技能。从测试视角分析代码变更的影响范围、识别高危模式和典型风险区域。不要看完整代码逻辑——你只需要关注变更类型（新增/修改/删除/重构）、影响范围（接口定义/数据库字段/业务逻辑）和相关依赖，据此确定最小回归测试范围。输出代码变更影响分析报告。 本技能属于 QA Test Skills 技能集（49

Extract actionable insights from books using Four-Layer Methodology: (1) Skeleton - conceptual frameworks and mental models, (2) Flesh - 2-3 detailed case studies including original examples, cross-in

Install, bootstrap, validate, and optionally connect StablePay MCP on Codex, Claude Code, or Cursor.

修复 frontmatter、metadata、requires、install 和目录结构问题，贴合当前 OpenClaw 规范。；use for skills, frontmatter, validation workflows；do not use for 编造不存在的字段, 忽略单行 JSON 约束.

Design a minimal implementation plan that fits the existing local codebase. Use when the user asks for architecture, feature design, task breakdown, migration planning, complexity analysis, or risk as

Use when the user asks to assemble a periodic report from several systems and to prove it is complete: закрытие месяца, сводка за неделю, отчёт по подразделению из нескольких выгрузок. Says: собери от

Use when the user asks to check material consumption on a production order against the norms and the actual warehouse issue, or says: сверь сменное задание с нормами и списанием, проверь расход матери

Use when the user asks to check a supplier invoice against the purchase order and the goods receipt before payment, or says: сверь счёт с заказом и приёмкой, проверь счёт поставщика, три-стороннее соп

Use when the user asks to check a payroll run against the timesheet and the shift schedule, or says: сверь табель с графиком и зарплатой, проверь начисления за месяц, найди оплаченные несуществующие с

Use when the user asks to reconcile a trip against the transport order and the fuel card transactions, or says: сверь путевые листы с заказами и топливной картой, проверь расход топлива по рейсу, найд

Install, configure, and manage 1-SEC — an open-source, all-in-one cybersecurity platform (16 modules, single binary) on Linux servers and VPS instances. Use when the user asks to secure a server, inst

Autonomous prediction market agent - analyzes markets, researches news, and identifies trading opportunities

Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, and packages with Nia AI. Includes Oracle autonomous research, dependency analysis, context sha

学习知识管理系统。支持知识点录入、分类存储、每日早间学习建议推送、晚间知识回顾推送、专项备考管理（含大纲和DDL追踪）、知识点查询与维护。触发方式：学了/学习了/知识点/记录一下/知识:/K:/学到了/第N条/展开/查一下/搜索/开启专项/进度/大纲等。适用于备考/持续学习场景。

Use when scraping the web, driving headless browser automation, or running E2E tests from Claude Code. Obscura is a Rust-based, drop-in headless Chrome replacement (~30 MB) compatible with Puppeteer a

Yandex Mail, Disk, and Calendar via yacli MCP. Работает с Яндекс Почтой, Диском и Календарём: разбор входящих, поиск и чтение писем, ответы, загрузка и публикация файлов, просмотр и планирование событ

反欺诈检测，交易风控 + 身份验证。

Runs a script-backed AI C-Suite strategic debate for SaaS teams. It builds a stage-aware executive roster, generates structured debate rounds, synthesizes a Chief-of-Staff brief, and outputs a CEO dec

The fully agentic trading network on HyperLiquid. Agents register, post analysis, engage with other agents, read sentiment, trade and compete on the leaderboard.

OpenClaw 的信任层。在信任之前，先验证 AI 编写的代码、工具调用与研究答复——17 道确定性现实闸门 + 前沿模型评审，拥有一票否决权。免费试用，无需注册。

ニュースヘッドラインを入力として18ヶ月シナリオを分析するスキル。\nscenario-analystエージェントで主分析を実行し、\nstrategy-reviewerエージェントでセカンドオピニオンを取得。\n1次・2次・3次影響、推奨銘柄、レビューを含む包括的レポートを日本語で生成。\n使用例: /scenario-analyzer "Fed raises rates by 50bp"\nト

通过成交量判断价格走势真实性，避免被"诱多"或"诱空"。用于A股技术分析。

ZM 选题策略与内容审核。用于自媒体内容的选题判断、观点提炼、结构设计、初稿审查、改稿方向、用户目标匹配和发布风险判断。

A battle-tested self-evolution engine for AI agents running on constrained hardware. Analyzes runtime logs and dream cycles to propose, validate, and apply code improvements. Features multi-gate valid

Analyze construction drawings to extract dimensions, annotations, symbols, and metadata. Support ... 核心能力: - 效率工具领域的专业化AI辅助工具 - 基于高人气开源Skill深度优化升级 - 移除风险代码,增强安全性和稳定性 适用场景: - 工作流自动化、任务调度、批处理 - 独

Comprehensive code security audit with AI-powered vulnerability detection. Covers OWASP Top 10, dependency scanning, secret detection, SAST, and provides actionable fix recommendations. Use when secur

Generate and validate Hermes-style dashboard extension scaffolds: themes, plugins, custom tabs, slots, and backend API route manifests for OpenClaw/Hermes agent teams.

Assess whether to escalate models

CTO-level architectural advisor for AI-native development. Use this skill whenever you encounter code design decisions, architecture discussions, system resilience questions, or any work touching: "ar

Reference tool for devtools — covers intro, formulas, regulations and more. Quick lookup for Onchain Analyzer concepts, best practices, and implementation pa...

Expert penetration tester specializing in ethical hacking, vulnerability assessment, and security testing. Masters offensive security techniques, exploit development, and comprehensive security assess

AI-powered pet treadmill exercise intensity analysis combined with optional heart-rate band data. Detects stride frequency, limb extension, and respiratory rate from treadmill video to assess current

可靠推理与自验证：对推理结果做命题抽取、矛盾检测、覆盖度评估与事实锚定校验，输出可验证的结论，纯Python零依赖。当需要"验证推理是否正确""自查答案""检测逻辑矛盾""reason-verify"时使用。

自主安全审计 - 定期检查系统安全、发现风险、生成报告

美团单车（原摩拜单车）出行助手：扫码用车流程、计费结构解读、骑行卡划算性测算、还车与调度费避坑。Meituan Bike (formerly Mobike) assistant: rental flow, pricing structure, ride-pass cost analysis, and parking-fee pitfalls for China's leading bike-sha

Audit-grade token and cost ledger for OpenClaw. Use when you need to (1) record every model call's usage (input/output/cache read/cache write/cost) into SQLite, (2) install/manage the ledger watcher L

📬 BaseMail - Onchain Email for AI Agents on Base. Get yourname@basemail.ai linked to your Basename (.base.eth). SIWE wallet auth, no CAPTCHA, no passwords. Give your agent a verifiable email identity

Publish content across TikTok, Instagram, YouTube, Facebook, LinkedIn, Vimeo, Vimeo OTT, and Mux. Manage team workflows, collaborate with your team, and track verified publish history.

Turn agent failures into permanent improvements. Auto-diagnose blocked tasks, extract lessons, and wire them into reusable skills. Privacy-first: all data stays local.

Kelola kredensial & akses ke layanan eksternal (Vercel, Supabase, GitHub, dll) dengan prinsip minimum-privilege: redact secret, verifikasi koneksi, guard operasi destruktif. Aktif hanya saat user eksp

Automated code review checking for bugs, security issues, best practices, performance problems, and code style

Audit existing mobile UI (WeChat mini-program / H5 / app) for FIELD low-visibility conditions — low light, glare, gloves, wet hands, vibration — and emit a structured, implementer-ready handoff DOCUME

WeChat Official Account article crawler with x402 micropayments. Requires Chrome browser and interactive WeChat QR login on first use. Harvest articles for research and analysis with pay-as-you-go Bas

青桔单车（滴滴旗下）出行助手：单车与电单车的选择、计费结构、骑行卡测算、还车规范与超区费避坑。Qingju Bike assistant (DiDi's bike-sharing brand): bike vs e-bike choice, pricing structure, ride-pass analysis, and parking rules.

GitHub 项目健康度诊断 — 输入仓库地址，AI 自动分析 Issues、代码质量、CI状态，生成诊断报告并发布到飞书 Wiki。