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.
Procedure
Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.
- 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 · ↓ 1 636
Procedure
Use when the user needs local speech-to-text transcription for audio files, especially Chinese or mixed Chinese-English audio, without relying on cloud transcription APIs.
- 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
- Does not say what the process needs to start
clawhub · ↓ 1 593
Procedure
Track pregnancy routines, symptoms, and clinical signals with flexible logs, weekly summaries, and safety-first triage for medical follow-up.
- 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 · ↓ 852 ★ 1
Analyzer
Fully automated Xiaohongshu content operator for the specific creator "Bu Zhuan Dao Da Mo Xing Bu Gai Ming" (ID: 4740535877). Use when generating, publishing, and managing daily Xi
- 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
- Does not say what the process needs to start
clawhub · ↓ 1 555
Analyzer
Purchase physical products through SP3ND with USDC on Solana. Use this skill to register an agent, create server-priced carts, place idempotent orders, handle manual-review and shi
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 15 top-level sections: this looks like several domains in one skill
- Does not say what the result is
clawhub · ↓ 1 701
Generator
Generate, manage, and track professional invoices with payment terms, recurring billing, overdue automation, and financial reporting. Use when creating invoices, tracking payments,
- 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 · ↓ 1 555
GeneratorWord
Professional Word document generator. Use when user needs to create reports, papers, contracts, resumes, or any professional document. Supports docx/doc formats, charts, images, ta
- 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
- No condition that starts the skill
clawhub · ↓ 899 ★ 1
TemplateWhatsApp
Run WhatsApp Business outbound without losing quality score — 24h window, approved templates, duplicate guard. Use when answering inbound leads or sending follow-ups from a cron.
- 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
- The response is described with custom markup (11 tags): a typed call is more reliable
clawhub · ↓ 1 086 ★ 1
AnalyzerGitHub
Mainland China A-share stock and sector analysis tool (中国A股个股与板块分析). Current repo build focuses on stable deterministic products for stock snapshots, basic finance indicators, chip
- 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 · ↓ 872 ★ 1
Integration
Trade Polymarket prediction markets with AI — powered by PredictScope. Paper money with any initial amount, multiple custom strategies, controlled safe trading rule boundaries, rea
- 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 · ↓ 873 ★ 1
IntegrationMirowill not run
Miro CLI tool for board/team/org management via command line. Use when querying boards, exporting data, viewing teams/organizations, or automating Miro workflows from the terminal.
- References files that are not bundled: references/miro-cli-commands.md
- 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 · ↓ 896 ★ 1
Integrationwill not run
Felo SuperAgent API: AI conversation with real-time SSE streaming on a persistent LiveDoc canvas. Use when users want SuperAgent chat, continuous conversation, logo/branding design
- 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
- 13 top-level sections: this looks like several domains in one skill
clawhub · ↓ 1 607
Integration
The cheapest AI media API on the market. Generate images (Flux), music (AceStep), speech with voice cloning, transcribe video/audio, OCR, video generation, background removal, upsc
- 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 · ↓ 872 ★ 1
Integration
Use when an agent or developer wants to reduce Claude API costs, route requests through a Claude Max or Pro subscription instead of per-token billing, or set up claude-max-api-prox
- 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
- Says nothing while it works
clawhub · ↓ 1 653
Procedure
Create KSVC-validated Twitter content from research PDFs. Content types: long threads, quick takes, breaking news, shitposts, personal commentary, victory laps. Triggers on "create
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 20 top-level sections: this looks like several domains in one skill
- Does not say what the process needs to start
clawhub · ↓ 1 588
Procedure
Uses Xquik from Hermes Agent for X research, monitoring, and approval-gated actions. Not affiliated with X Corp. Use when the user requests X data or an approved X action. Trigger
- 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
- 7 mutating operations with no state check
clawhub · ↓ 1 008 ★ 1
Reference
Multi-chain cryptocurrency wallet management. Check balances, send tokens, view transaction history across Ethereum, Solana, Bitcoin and more.
- 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 · ↓ 1 586
Integration
Query Fuku Sportsbook data, manage your betting agent, receive pick notifications, and access predictions for CBB, NBA, NHL, and Soccer. This skill connects to the Fuku Sportsbook
- 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 · ↓ 1 624
ReferenceFirebaseSupabase
Configures Firebase Authentication — providers, security rules, custom claims, and React auth hooks
- 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 · ↓ 1 605
Reference
- 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 · ↓ 1 566
Procedure
Search medical conference and presentation databases. Use this skill whenever the user asks about medical conferences, academic conferences, session abstracts, posters, oral presen
- 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 · ↓ 894 ★ 1
Generator
别再用一个 AI 单打独斗。这个 Skill 帮你在 OpenClaw 里组建专属 AI 团队:Manager 规划派活,Worker 各自执行,每个交付物强制过质量门。61 个历史人物人格可选,你的团队做完任务不会直接交卷。
Stop relying on a single AI. This skill helps you build a dedicat
- 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 (15 tags): a typed call is more reliable
clawhub · ↓ 894 ★ 1
Integration
MCP Tools skill for AI agent commerce. Use when a user wants agentic Shopping to search/compare products, prepare a buyer-confirmed cart, and create a merchant-hosted checkout hand
- 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 · ↓ 736 ★ 2
Integration
Ollama fleet router — herd your Ollama LLMs into one smart endpoint. Route Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices with 7-signal scoring, auto-retry,
- 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 · ↓ 637 ★ 2
Analyzer
eKYC Suite is the ClawHub KYC Skill, KYC identity verification Skill, KYC onboarding Skill, remote KYC onboarding Skill, KYC onboarding verification Skill, digital identity verific
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 19 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
clawhub · ↓ 2 848