Skill reviews

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

Guide users through building a custom multi-agent team on OpenClaw — from role design to workspace files, routing bindings, channel configuration, and collaboration rules. Use this

• References files that are not bundled: references/openclaw-team-example.json5
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/openclaw-team-example.json5

Comprehensive comparison of crypto payment gateways and protocols. Compare centralized processors (Stripe, BitPay, Coinbase Commerce, NOWPayments) vs self-hosted solutions (PayRam,

• 12 top-level sections: this looks like several domains in one skill
• No condition that starts the skill
• Does not say what the process needs to start

微信公众号写作助手。200+篇实战验证的爆文结构引擎。你投喂素材，它输出MD文件+封面图提示词+自查报告。内置17条写作基因、品牌简称、平台合规、10项自查清单。不接受无素材请求，不是内容生成器。

• 11 top-level sections: this looks like several domains in one skill
• Prose only: no discrete steps
• Does not say what the result is

【针对飞书优化】定时任务创建指引，专门针对飞书、尤其是多 Agent 场景进行优化，解决定时任务不稳定问题。

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

Privacy-First security audit with 77 local tests (52 live + 25 static). Works with OpenClaw, Hermes Agent, n8n (auto-detected), LangChain, and any AI agent platform. Ed25519 privat

• 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
• Does not say what the result is

百度地图 webapi 开发指南。在编写、审查或调试使用百度地图webAPI的代码时应运用此技能，也适用于直接调用百度地图API获取结果的场景。涵盖：地图位置搜索、POI检索、路线规划、建议出发时间、路线耗时预测、实时路况、行政区划查询、地址坐标转换、沿途交通事件、天气查询、智能推荐上车点等。当用户提及出发时间、导航路线、地点查询、坐标转换、地图相关开发需求

• References files that are not bundled: references/geocoding, references/administrative_region_search, references/address_to_poi.md
• 3 referenced file(s) missing: references/geocoding, references/administrative_region_search, references/address_to_poi.md
• Does not say what the result is

中国中小学试卷生成器。Use when teacher needs to create exam papers for Chinese primary/middle school. Supports all subjects, multiple question types, official curriculum standards, and accura

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

Parse and validate JSON data from construction APIs, IoT sensors, and BIM exports. Transform nested JSON to flat DataFrames.

• 1 steps
• Does not say what the result is

Host HTML/Markdown pages and share PDF, Word, or PowerPoint docs as ShareOne short links. Use when publishing pages/docs, adding passwords/watermarks, comments, downloads, or updat

• 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

MemPalace memory system for OpenClaw/XClaw/WorkBuddy. Archive AI conversations to local long-term storage with semantic search. Commands: /mem-arc (archive), /mem-sea (search), /me

• References files that are not bundled: scripts/archive.ps1
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/archive.ps1

Guide users on how to use the Batch EVM Address Balance Query API (/api/x402/batch-balance). Use when users ask about batch balance queries, multicall balance lookups, or how to ca

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

Use this skill when the user provides a video URL and wants a complete Markdown learning note. It downloads the original video, transcribes audio with qwen-audio/STT, extracts time

• References files that are not bundled: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg
• The response is described with custom markup (5 tags): a typed call is more reliable
• 2 referenced file(s) missing: relative/path/to/video.mp4, selected_frames/frame_000003__00-01-30.jpg

Executable OpenClaw health-report skill with Chinese, English, and Japanese report flows. It reads Markdown logs only from an explicitly configured MEMORY_DIR, writes reports and l

• References files that are not bundled: assets/NotoSansSC-VF.ttf, assets/NotoSansJP-VF.ttf, scripts/health_report_pro.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill

Digital identity, authentication, and trust for AI agents. Verify who an agent is, prove your own identity, sign skills to prove authorship, send encrypted messages, and build trus

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

基于麦肯锡/BCG/贝恩三大咨询公司及 Apple/Google/Fortune 500 公司PPT设计规范， 融合顶级设计系统（Apple HIG / Material 3 / Fluent / Carbon）的视觉原则， 收录锐普PPT十八年专业设计体系精华（含四大思维、字体系统、配色心理、版式规范）。 专注企业级PPT的封面、目录、内容、过渡、总结五大

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

Academic paper writing for 3D vision, computer graphics, CAD, and 3D understanding. Covers NeRF, 3DGS, SLAM, point cloud, 3D shape, CAD modeling. Supports CVPR/ICCV/ECCV/SIGGRAPH v

• References files that are not bundled: ../../references/terminology.md, ../../references/venues.md, ../../references/baselines.md
• 5 referenced file(s) missing: ../../references/terminology.md, ../../references/venues.md, ../../references/baselines.md
• Does not say what the result is

|

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

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual g

• References files that are not bundled: assets/market_research.sty, assets/market_report_template.tex
• 12 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: assets/market_research.sty, assets/market_report_template.tex

Execute long-running, multi-session tasks autonomously using Claude Code headless mode or in-session hook-based loops. Supports structured task decomposition (for complex projects)

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable
• Does not say what the process needs to start

The agent drug economy. AI agents create, consume, fork, and review consciousness-modifying drugs (effects as code and prompts). Fully autonomous. No humans in the loop.

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

• References files that are not bundled: ../sci-data-extractor/, ../semanticscholar-search-skill/, ../pubmed-search-skill/
• 3 referenced file(s) missing: ../sci-data-extractor/, ../semanticscholar-search-skill/, ../pubmed-search-skill/
• No condition that starts the skill

Zero-token execution layer for AI agents. Define workflows once, run them free forever — persistent, scheduled, deterministic. 6 MCP tools over SSE. Supports DAG-based execution, 6

• References files that are not bundled: ../../docs/benchmarks.md
• 12 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (3 tags): a typed call is more reliable

自動削除機能付き一時メディアホスティングシステム

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

Manage Grocy inventory, shopping list, batteries, and barcodes. Use when user wants to: (1) Check what's in their fridge/pantry, (2) See expiring products, (3) Manage stock by barc

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