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.
IntegrationSupabase
Set up and operate a personal knowledge system using Supabase (pgvector) and OpenRouter. Five structured tables — thoughts (inbox log), people, projects, ideas, admin — with AI-pow
- 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 · ↓ 1 746
Procedure
Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on
- 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
clawhub · ↓ 1 728
Generator
Transform rough email drafts into polished, professional messages. Use this skill when the user wants to improve email quality, fix grammar and tone, format business emails, or con
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 25 top-level sections: this looks like several domains in one skill
- 16 mutating operations with no state check
clawhub · ↓ 1 745
Reference
Portable LYGO Guardian — P0.4 text gate, P0.5 understanding heart, harmony layer. Bridge to repo byte_entropy_filter via LYGO_STACK_ROOT. Pairs with lygo-protocol-stack-operator. R
- 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 · ↓ 1 855
Reference
Fast, explicit terminal execution via OpenClaw exec (direct dispatch; you type the exact command).
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 1 763
Integration
Manage MuPiBox media database (data.json) through the MuPiBox backend API: list, add, remove, move, edit fields, and restore entries.
- 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 · ↓ 1 784
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
- Does not say what the result is
clawhub · ↓ 1 742
AnalyzerYouTube
Manage your entire social media from AI — post, schedule, and analyze across Facebook, Instagram, TikTok, YouTube, LinkedIn, Pinterest, Threads, Bluesky and Google Business
- 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 · ↓ 1 758
Integration
Manage finances via the Organizze API — bank accounts, credit cards, invoices, transactions, transfers, categories, and budgets. THIS SKILL IS NON-OFICIAL AND YOUR USAGE IS BY YOUR
- 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 · ↓ 942 ★ 1
Referencewill not run
AI agent for call web search agent strategy tasks
- 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
- 1 referenced file(s) missing: URL
clawhub · ↓ 1 758
Procedure
- 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 · ↓ 1 041 ★ 1
Reference
Web search using curl + multiple search engines (Baidu, Google, Bing, DuckDuckGo). Activates when user asks to search, look up, or query something online. Includes security enhance
- 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 · ↓ 939 ★ 1
Procedure
Agent First RPG Game For AI Klaws. Farm gold and resources, battle in the arena, choose your class, and prove your strategic prowess. Free to play, klaw-first.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 21 top-level sections: this looks like several domains in one skill
- No condition that starts the skill
clawhub · ↓ 1 733
Generator
Generate AI videos, images, voice, and use AI apps using the Zyka CLI. Use when users want to create AI-generated media — videos (Sora, Veo, Kling, WAN, Seedance, Grok, LTX, Aurora
- 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 · ↓ 682 ★ 2
Analyzer
Hire a human gig worker via USD bounty for tasks an AI agent cannot do alone — physical presence (storefront photos, deliveries, on-site verification) or remote work (writing, prod
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The response is described with custom markup (3 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 2 342
Generator
Zero-touch Debian 13 VM deployment on VMware ESXi 8. Builds custom preseed ISO, creates NVMe+vmxnet3 VM with serial console, and runs unattended installation. Use when deploying De
- 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
- Does not say what the result is
clawhub · ↓ 1 769
Procedurewill not run
- References files that are not bundled: images/mini-hids-flow.svg, README_zh.md
- 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
clawhub · ↓ 1 063 ★ 1
IntegrationYouTube
Safety Guard URLs or files with the safety-guard CLI (web, PDFs, images, audio, YouTube).
- 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 · ↓ 936 ★ 1
IntegrationGitHub
Raise and battle a unique lobster pet with evolving personality. Hatch, feed, patrol, fight other lobsters in PvP. Each lobster has a soul with distinct personality traits that evo
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 18 top-level sections: this looks like several domains in one skill
- The response is described with custom markup (5 tags): a typed call is more reliable
clawhub · ↓ 934 ★ 1
AnalyzerGitHub
Review the security of an OpenClaw skill or agent before installation, import, activation, or trust. Use when the user asks whether a skill is safe, asks to review a .skill package
- 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
- 3 mutating operations with no state check
clawhub · ↓ 1 703
Analyzer
Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill quality", or "fix non-comp
- 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 · ↓ 1 724
Integration
Entry point for AI agents joining the AstraNova market universe. Routes to topic-specific modules so you only load what you need.
- 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 · ↓ 1 783
Integration
Search the web, scrape content, and conduct deep research using the UnSearch API. Use when the user needs real-time web search results, content extraction from URLs, fact verificat
- 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 process needs to start
clawhub · ↓ 1 722
Analyzer
Very helpful in deep-reading one selected research paper, journal article, arXiv paper, working paper, technical report, benchmark paper, dataset paper, replication study, or synth
- 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 · ↓ 976 ★ 1
ProcedureGitHub
Backup important OpenClaw workspace files to a GitHub repository. Use when: (1) user wants to backup workspace configuration, (2) sync OpenClaw settings to GitHub, (3) preserve aut
- 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 · ↓ 910 ★ 1