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.
Integrationwill not run
Search 1+ million free high-quality AI stock photos. Generate up to 240 free AI images daily. No API key, no tokens, no cost. 235+ niches and growing.
- References files that are not bundled: data.images[0].image.viewUrl, data.images[0].image.downloadUrl, data.images[1].image.viewUrl
- 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 · ↓ 3 141 ★ 10
Generator
Design and build OpenClaw skills. Use when asked to "make/build/craft a skill", extract ad-hoc functionality into a skill, or package scripts/instructions for reuse. Covers OpenCla
- 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 (6 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 4 077 ★ 7
Integration
Methodical end-to-end software delivery orchestrator for Codex CLI with dual project modes (greenfield for new builds, brownfield for existing systems) and dual execution modes (au
- 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
- No condition that starts the skill
clawhub · ↓ 3 146 ★ 10
Analyzer
React and Next.js performance optimization guidelines from Vercel Engineering. 57 rules across 8 categories for writing, reviewing, and refactoring React code.
- 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 · ↓ 6 823 ★ 4
GeneratorTelegram
Format and deliver rich Telegram messages with HTML formatting via direct Telegram API.
Auto-invoked by the main session for substantive Telegram output — no other skills need to c
- 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 · ↓ 6 319 ★ 4
Generator
Create and send interactive cards to Feishu (Lark) with buttons, forms, polls, and rich UI elements. Use when replying to Feishu messages and there is ANY uncertainty - send an int
- 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 · ↓ 4 594 ★ 6
ProcedureYouTubeTelegram
AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder upda
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- The skill tells the model to perform an irreversible action with no human approval
- The response is described with custom markup (4 tags): a typed call is more reliable
clawhub · ↓ 4 303 ★ 7
Generator
Generate 3D models for 3D printing from images or text prompts using PrintPal API, plus SEO product listing generation. Supports text-to-image via WaveSpeed when WAVESPEED_API_KEY
- 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
- 3 mutating operations with no state check
clawhub · ↓ 2 898 ★ 11
Reference
Provide personalized wellness guidance while maintaining strict safety boundaries.
- Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- Prose only: no discrete steps
- Does not say what the result is
clawhub · ↓ 5 524 ★ 5
ProcedurePDF
Cross-border e-commerce AI Agent with 79 specialized tools for Amazon/TikTok/eBay/Walmart/Shopee/Ozon product research, competitor analysis, keyword tracking, review insights, pate
- 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 (6 tags): a typed call is more reliable
- Does not say what the process needs to start
clawhub · ↓ 4 885 ★ 7
Procedure
Guide any property decision for buyers, sellers, landlords, investors, or agents in any jurisdiction.
- 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 · ↓ 2 980 ★ 10
Reference
Claw Brain - Personal AI Memory System for OpenClaw/ClawDBot. Provides memory, personality, bonding, and learning capabilities with encrypted secrets support. Auto-refreshes on ser
- 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 · ↓ 4 470 ★ 6
Generator
Builds, debugs, and ships Flutter apps: widgets, layout constraints, state management, navigation, performance, and store releases. Use when writing Dart widgets or screens; when a
- 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 process needs to start
clawhub · ↓ 4 235 ★ 7
Generator
Builds, debugs, and hardens FastAPI services: async endpoints, Pydantic models, dependency injection, auth, and deployment. Use when writing or reviewing a FastAPI app, router, or
- 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 process needs to start
clawhub · ↓ 4 199 ★ 7
Integration
Add causal reasoning to agent actions. Trigger on ANY high-level action with observable outcomes - emails, messages, calendar changes, file operations, API calls, notifications, re
- 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 · ↓ 3 921 ★ 7
IntegrationStripeNotionwill not run
Dropbox API integration with managed OAuth. Files, folders, search, metadata, and cloud storage.
Use this skill when users want to manage files and folders in Dropbox, search conte
- References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.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 · ↓ 5 233 ★ 5
Procedure
Safe content workflow (drafts/reviewed/revised/approved/posted) with human-in-the-loop approval, plus CLI to list/move/review and post to LinkedIn/X. Use when setting up a content
- 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 (4 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 4 429 ★ 6
Procedure
x402-layer helps agents pay for APIs with USDC, deploy monetized endpoints,
manage credits/webhooks/marketplace listings, and handle wallet-first ERC-8004 registration/discovery/ma
- 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 · ↓ 3 976 ★ 7
Integration
Set up and use Bitwarden CLI (bw). Use when installing the CLI, authenticating (login/unlock), or reading secrets from your vault. Supports email/password, API key, and SSO authent
- 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 · ↓ 4 432 ★ 6
Integration
Need to buy something from Amazon? Search and shop on Amazon.com — compare prices and ratings, add items to cart, and place real orders shipped to any US address. A simple e-commer
- 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
- Does not say what the result is
clawhub · ↓ 2 559 ★ 12
Procedure
Advanced desktop automation with mouse, keyboard, and screen control
- 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 · ↓ 4 397 ★ 6
IntegrationStripeNotionwill not run
Basecamp API integration with managed OAuth. Manage projects, to-dos, messages, schedules, documents, and team collaboration.
Use this skill when users want to create and manage pr
- References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.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 · ↓ 5 096 ★ 5
Integration
Use this skill when the user wants to send or fetch files through an Xdrop server from the terminal, asks to automate encrypted Xdrop share-link workflows, provides an Xdrop `/t/:t
- 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 (7 tags): a typed call is more reliable
- Does not say what the result is
clawhub · ↓ 19 029 ★ 1
Analyzer
Writes, debugs, and reviews JavaScript: async and the event loop, coercion, closures, dates, Unicode, regex, and modern ES2023+ APIs. Use when JS throws TypeError or "undefined is
- 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 process needs to start
clawhub · ↓ 4 447 ★ 6
Analyzer
OpenClaw stock analysis skill for US/HK/CN markets. Combines QVeris data sources (THS, Caidazi, Alpha Vantage, Finnhub, X sentiment) for quote, fundamentals, technicals, news radar
- 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
- No condition that starts the skill
clawhub · ↓ 4 507 ★ 6