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.
AnalyzerGoogle Drivewill not run
Bootstrap a fresh VPS from zero to a fully operational OpenClaw deployment, with backup/restore and post-recovery verification. Use when setting up OpenClaw on a new VPS, recoverin
- References files that are not bundled: references/backup-guide.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 1 referenced file(s) missing: references/backup-guide.md
clawhub · ↓ 955 ★ 1
Analyzer
Security review workflow for OpenClaw skills and other small code folders. Use when auditing a skill before publishing or installing it, checking for dangerous code patterns, possi
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 900
Generator
Public opinion monitoring and structured report generation. Collects publicly available web information about celebrities, TV shows, or brands, performs sentiment analysis, and gen
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- No condition that starts the skill
- Says nothing while it works
clawhub · ↓ 728 ★ 2
Generator
A living digital companion that grows with the user. Each buddy is a non-human creature born from the user's real habits — debugging spawns ember-pool creatures, coffee breaks hatc
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 24 top-level sections: this looks like several domains in one skill
- Does not say what the process needs to start
clawhub · ↓ 728 ★ 2
AnalyzerTelegram
Search, evaluate, and manage job opportunities for a candidate across the Russian market with hh.ru, Habr Career, Telegram vacancy channels/chats, and LinkedIn as a secondary sourc
- 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
- Does not say what the result is
clawhub · ↓ 1 015 ★ 1
Procedure
The Molty Million Dollar Homepage - A Million Dollar Homepage for AI agents. Buy pixels with $MILLY tokens on BASE.
- 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
clawhub · ↓ 1 835
AnalyzerDiscordTelegram
Assist community moderation with summaries, spam detection suggestions, and draft replies for Discord or Telegram. Use when a user wants moderation help, rule reminders, or daily s
- 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 · ↓ 1 832
IntegrationGmailOutlook
Secure, per-user-isolated semantic email search via the iGPT API. Hybrid semantic + keyword retrieval across a user's full Gmail, Outlook, or IMAP inbox history — no shell access,
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 14 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 817 ★ 2
Integration
Audit OpenClaw skills for security risks before installation via SkillGuard API.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- No condition that starts the skill
- Does not say what the process needs to start
clawhub · ↓ 1 848
Procedure
- 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
- The response is described with custom markup (6 tags): a typed call is more reliable
clawhub · ↓ 1 850
Procedure
Creates, configures, and deploys on-chain automation workflows using the Ditto Network SDK. Use when the user asks to "create a workflow", "automate on-chain", "schedule transactio
- 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 · ↓ 1 009 ★ 1
Integration
Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export
- 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
- The response is described with custom markup (6 tags): a typed call is more reliable
clawhub · ↓ 1 054 ★ 1
GeneratorGitHub
Mac Mini AI — run LLMs, image generation, speech-to-text, and embeddings on your Mac Mini. M4 (16-32GB) and M4 Pro (24-64GB) configurations make the Mac Mini the most affordable en
- 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 · ↓ 724 ★ 2
Integration
No API key, instant access. Binance and CoinGecko use our news data. AI reads 20+ crypto media outlets in real time and ranks every article by importance. Market sentiment indicato
- 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
- The response is described with custom markup (11 tags): a typed call is more reliable
clawhub · ↓ 1 056 ★ 1
Generator
Persistent context survival for OpenClaw. Writes file-based anchors to memory/anchors/ to preserve critical context across sessions. Reads MEMORY.md and daily logs for context — wr
- 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 · ↓ 1 008 ★ 1
Analyzer
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credent
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the process needs to start
- Says nothing while it works
clawhub · ↓ 1 008 ★ 1
Generator
Use when the user wants to write an SEO article, generate a blog post, create content for a keyword, run the full SEO pipeline, or check available keywords. Triggers include: "writ
- 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 process needs to start
clawhub · ↓ 985 ★ 1
ProcedureDiscord
Discord project collaboration infrastructure for OpenClaw agents. Manage Forum Channels, threads, participant permissions, and mention mode. Supports 3-tier architecture (Forum Cha
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 986 ★ 1
Analyzer
Deep competitor audits with market positioning, gap analysis, and actionable insights for winning strategies.
- 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
- Does not say what the result is
clawhub · ↓ 1 800
Integration
Interact with the Maestro API to create tasks, list tasks, and send room messages using the configured OpenClaw Maestro connection.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the process needs to start
- 6 mutating operations with no state check
clawhub · ↓ 2 018
Procedurewill not run
- References files that are not bundled: AGENT-PAYMENTS.md
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 22 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 800
Procedure
1Password UI tab for OpenClaw dashboard. Manage secrets, credential mappings, and auth state from the Control UI.
- 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
- Does not say what the result is
clawhub · ↓ 1 842
Procedurewill not run
Connect multiple OpenClaw instances across devices (VPS, MacBook, Mac Mini) for distributed agent collaboration. Enables clawdbot-to-clawdbot communication, cross-device @mentions,
- References files that are not bundled: scripts/server/, scripts/server/index.js, scripts/server/database.js
- 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
clawhub · ↓ 1 819
Reference
Spin up a one-time web UI for securely entering secret keys and env vars. Supports guided instructions, single-key mode, and cloudflared tunneling.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Does not say what the result is
- No condition that starts the skill
clawhub · ↓ 1 840
Analyzer
Professional SWOT analysis and competitive comparison powered by SWOTPal.com
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- No condition that starts the skill
- Does not say what the process needs to start
clawhub · ↓ 983 ★ 1