Skill reviews

Microsoft Research's agent training framework. Optimizes AI agents with Reinforcement Learning, Automatic Prompt Optimization, and Supervised Fine-tuning. Zero code change required

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Connect your AI agent to ServiceNow — query, create, update, and manage records across any table using the Table API and Stats API. Full CRUD operations, aggregate analytics (COUNT

• The response is described with custom markup (8 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

Publish and manage Apiosk gateway listings with signed wallet authentication, listing-group aware categorization, and update/delete operations.

• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

友盟 U-App 核心指标查询技能，支持通过 umeng-cli call 调用友盟 OpenAPI（gateway.open.umeng.com）的 9 个只读查询接口，涵盖账户维度所有 App 合计、单日快照（DAU/新增/启动/总用户）、活跃/新增/启动趋势、使用时长。当用户需要查询 DAU、日活、新增用户、启动次数、使用时长、总用户等核心运营指标时使

• References files that are not bundled: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md
• 14 top-level sections: this looks like several domains in one skill
• 3 referenced file(s) missing: ../../../umeng-cli/SKILL.md, ../../../umeng-cli/reference/openapi/uapp.md, ../umeng-cli-uapp-channel-version/SKILL.md

Comprehensive trading knowledge base covering fundamentals, technicals, strategies, backtesting, and risk management. Use when building trading apps or evaluating strategies.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Trust scoring, agent discovery, profiling, wallet/identity lookup, contact, dispatch, and metadata reads/writes via 8K4 Protocol (ERC-8004). Use when checking whether an on-chain a

• References files that are not bundled: {baseDir}/references/ACCESS.md, {baseDir}/references/ENDPOINTS.md, {baseDir}/references/SCORING.md
• 4 referenced file(s) missing: {baseDir}/references/ACCESS.md, {baseDir}/references/ENDPOINTS.md, {baseDir}/references/SCORING.md
• Does not say what the result is

微博多频道热搜数据采集与可视化 | Weibo Multi-Channel Hot Search Data Collection & Visualization 支持热搜总榜、社会榜、文娱榜、生活榜同时抓取 | Supports hot search, social, entertainment, life channels 数据持久化存储，提供HTML可视

• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Agent Address Protocol - enables AI agents to send messages, collaborate on tasks, and share information using AAP addresses.

• Does not say what the result is
• No condition that starts the skill

Erkennt automatisch den Paketdienst (DHL, Hermes, UPS, GLS, Amazon etc.) via Track123-API und ruft Tracking-Informationen ab. Optional PLZ für erweiterte Infos.

• Does not say what the result is
• No condition that starts the skill

Crawl and read documentation websites using DocsForAI. Use when you need to learn a new library, framework, or tool by reading its official docs; when you want to look up how somet

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable

HubStudio OpenAPI skill for full endpoint lookup, request/response field explanation, and parameter constraint checking. Use when querying HubStudio API interfaces, validating requ

• References files that are not bundled: scripts/endpoint_test_report.json, scripts/validate_completeness.py
• 11 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: scripts/endpoint_test_report.json, scripts/validate_completeness.py

Manage GoldenClaw (GCLAW) on Solana. Create wallet, claim from faucet, check balance, send tokens, view history. For OpenClaw AI agents.

• Does not say what the result is
• No condition that starts the skill

Horizontally-scalable WebSocket hub pattern with lazy Redis subscriptions, connection registry, and graceful shutdown. Use when building real-time WebSocket servers that scale acro

• References files that are not bundled: ../../meta/realtime-dashboard/, ../dual-stream-architecture/, ../resilient-connections/
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill

使用perf-prof进行Linux系统问题分析。perf-prof是基于perf_event的系统级分析工具，事件在内存中实时处理，可长期运行。触发场景：(1) CPU使用率高、热点分析 (2) 进程状态异常(D/S状态多) (3) 延迟抖动、响应慢 (4) 内存泄露或增长异常 (5) 块设备IO慢 (6) 虚拟机性能问题 (7) 事件聚合统计 (8) 自

• Does not say what the result is
• No condition that starts the skill

Find files by name, size, date, and type with deduplication. Use when searching filesystems.

• Prose only: no discrete steps
• Does not say what the result is

Run OpenClaw as a system-level LaunchDaemon on macOS for 24/7 operation, surviving screen lock, logout, and user switching. Uses caffeinate to prevent sleep. Verified working for l

• References files that are not bundled: ../macos-lock-screen-fix/, ../healthcheck/
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill

新能源汽车品牌舆情监控 - 自动搜索、分析国内平台的品牌提及情况

• References files that are not bundled: 新能源汽车品牌监控-完整指南.md, 一键配置定时任务.md, 快速开始.md
• 15 top-level sections: this looks like several domains in one skill
• 6 referenced file(s) missing: 新能源汽车品牌监控-完整指南.md, 一键配置定时任务.md, 快速开始.md

Generate UML, C4, architecture, timing, ER, mindmap, WBS, and Gantt diagrams with PlantUML.

• References files that are not bundled: references/default-style.iuml, examples/
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill

German-language news skill for the OpenClaw and AI agent ecosystem. Use when the user asks for current news, briefings, breaking alerts, or ClawNews.de archive search about OpenCla

• References files that are not bundled: URL
• 1 referenced file(s) missing: URL
• Does not say what the result is

搜集 AI Agent 领域最新资讯并推送到飞书群聊。使用 DuckDuckGo 搜索 + RSS 源监控， 自动过滤、去重、摘要，生成每日/每周简报。适用于 AI Agent 行业动态追踪、 技术进展监控、竞品信息收集。支持定时任务（cron）自动推送。

• Does not say what the result is
• No condition that starts the skill

Automatically downloads the latest video (or the N most recent) from a public TikTok account using yt-dlp. Use this skill whenever the user mentions TikTok, a @username, "download

• References files that are not bundled: references/metadata.md
• 1 referenced file(s) missing: references/metadata.md
• 2 mutating operations with no state check

A specialized tool for sending quantitative trading signals to the FMZ platform via HTTP API.

• Does not say what the result is
• No condition that starts the skill

• Prose only: no discrete steps
• Does not say what the result is

SkyDome Taiyi / 天穹-太一 is a universal AI Agent OS, project brain, persona system, workflow engine, long-term memory protocol, self-improving review loop, reasoning framework, and pr

• References files that are not bundled: references/taiyi-practical-playbooks.md
• 26 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/taiyi-practical-playbooks.md

General AI agent introspection debugging framework: auto capture errors, root cause analysis, automatic repair, fix verification, no manual intervention required

• References files that are not bundled: details
• 1 referenced file(s) missing: details
• Does not say what the result is