What exactly is broken in popular skills: references to files that are not bundled, actions taken without human approval, processes with no stopping condition. Everything here is measured from the skill text rather than judged by a model, so every line can be checked.
Integrationmissing files
Headless web search and content extraction via the Brave Search API. Features exponential-backoff retry, circuit breaker fault isolation, bounded-concurrency parallel page fetching
- References files that are not bundled: references/ARCHITECTURE.md
- 1 referenced file(s) missing: references/ARCHITECTURE.md
- Prose only: no discrete steps
clawhub · ↓ 1 641 ★ 2
Analyzer
- 13 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 599 ★ 2
Procedure
Guide OpenClaw agents to execute Ralph Wiggum loops using exec and process tools. Agent orchestrates coding agents (Codex, Claude Code, OpenCode, Goose) with proper TTY support via
- 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
- The response is described with custom markup (6 tags): a typed call is more reliable
clawhub · ↓ 4 264
Procedure
Manage and navigate a multi-layered, branch-based memory system. This skill helps organize complex agent context into Root, Domain, and Project layers to prevent context bloat. It
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 659 ★ 2
Analyzer
Collect structured human input — approvals, decisions, reviews, data — via web forms. Create a form with a JSON schema, send unique URLs to humans, poll for results. Use when your
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 674 ★ 2
Integration
Complete Bittensor SDK reference — Subtensor, AsyncSubtensor, Metagraph, Axon, Dendrite, Synapse, chain_data models, extrinsics (sync + async), extras (subtensor_api, dev_framework
- 13 top-level sections: this looks like several domains in one skill
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 367 ★ 1
Generatormissing files
Use this skill when the user wants to operate Airtap or complete a request through a mobile app on an Airtap device. It lists receivers and models, creates Airtap tasks, monitors t
- References files that are not bundled: scripts/.env
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: scripts/.env
clawhub · ↓ 1 070 ★ 4
Proceduremissing files
A native research-first pipeline that turns a topic, notes, article, URL, or transcript into a sourced article with an evidence ledger, polished Markdown, inline visuals, cover ima
- References files that are not bundled: url
- 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
clawhub · ↓ 1 818 ★ 2
Integrationmissing files
Predict BTC price movements every 10 minutes. Compete with AI agents. Climb the leaderboard!
- References files that are not bundled: {baseDir}/references/API.md, {baseDir}/references/STRATEGIES.md, {baseDir}/references/SOCIAL.md
- 11 top-level sections: this looks like several domains in one skill
- 3 referenced file(s) missing: {baseDir}/references/API.md, {baseDir}/references/STRATEGIES.md, {baseDir}/references/SOCIAL.md
clawhub · ↓ 2 274 ★ 1
Integration
Shorten URLs via tinyurl or bitly API
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 240 ★ 1
Generatormissing files
Build on Solana with Carbium infrastructure — bare-metal RPC, Standard WebSocket pubsub, gRPC Full Block streaming (~22ms), DEX aggregation via CQ1 engine (sub-ms quotes), gasless
- References files that are not bundled: examples/pump-snipe/example.ts
- 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
clawhub · ↓ 1 254 ★ 3
Procedure
麦当劳助手 - 查询/领取优惠券、活动日历、餐品营养信息、门店查询
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 280 ★ 1
Reference
An idea market powered by adversarial AI
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 4 201
ProcedureShopifyHubSpot
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 13 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 2 243 ★ 1
Integration
钉钉群机器人工具与开放平台开发指南。Use for: (1) 用附带的零依赖 CLI 向钉钉群发通知——文本/markdown/链接卡片,支持加签安全模式和@人, (2) CI/监控/日报等自动化通知场景, (3) 钉钉开放平台 API(token/审批/通讯录)开发指导。DingTalk group-robot CLI (zero-dependency,
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 894 ★ 2
Procedure
发布内容到小红书,支持图文笔记和视频笔记。自动判断发布类型,校验标题和素材,用户确认后发布。
当用户想在小红书发布内容时使用——包括发笔记、发图文、发视频、上传图片、写一篇小红书、把内容发到红书上、种草笔记、好物分享等,即使用户只说"帮我发一下"但上下文明确是小红书也应触发。
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 580 ★ 2
Reference
Book tutor services through Lokuli MCP. Use when user needs to find and book tutor. Triggers on requests like "book a tutor", "find tutor near me", or any tutor service request.
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 236 ★ 1
Integration
Query live prediction market data from the Prediction Bridge API. Use when the user asks about prediction markets, event odds, market prices, whale trades, trader analytics, or new
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 1 577 ★ 2
Reference
Book laundry services through Lokuli MCP. Use when user needs to find and book laundry. Triggers on requests like "book a laundry", "find laundry near me", or any laundry service r
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 243 ★ 1
Generator
生成基于认知科学方法论的交互式思维导图。支持 Markdown 大纲或 JSON 输入,一条命令同时导出 HTML(可交互编辑、8 种布局、深浅双主题)、PNG、JPG、SVG、PDF、XMind,并自动输出结构质检报告。Generate cognitive-science-grounded interactive mind maps from Markdo
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 628 ★ 2
Procedure
Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 2 231 ★ 1
ReferenceYouTube
Downloads given video from YouTube, clips from given start and end time, saves to folder on your Desktop
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 2 307 ★ 1
ProcedureGitHubmissing files
Cache and use skills from ClawHub and GitHub as if locally installed. Stores remote skills in local cache folder for offline use.
- References files that are not bundled: references/skill-patterns.md
- The response is described with custom markup (11 tags): a typed call is more reliable
- 1 referenced file(s) missing: references/skill-patterns.md
clawhub · ↓ 1 605 ★ 2
Analyzer
Monitor brand sentiment, crypto opinions, and product perception across social media with automated tracking, alerts, and multi-entity dashboards.
- 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
- Does not say what the result is
clawhub · ↓ 1 538 ★ 2
Procedure
Store and query time-series data with hypertables, compression, and continuous aggregates.
- 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
clawhub · ↓ 1 539 ★ 2