Skill reviews

Self-healing backup and update system with intelligent rollback. Protects against failed updates by automatically monitoring system health post-update and recovering from backups w

• 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

Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 mutating operations with no state check

AI video production, script writing, and image generation via MCP. Generate video scripts, AI images, and short-form or long-form videos from any topic. Public tools (pricing, quot

• 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

Your personal health data hub for AI agents. Query genomic insights, upload medical documents, record daily health metrics, explore genomic-lab cross-references, receive personaliz

• 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

与 CNB (Cloud Native Build) Open API 交互，用于代码管理和开发协作。当用户需要查询项目、代码仓库、问题、合并请求或其他开发相关数据时使用。需要 CNB_TOKEN 环境变量进行身份认证。API 请求地址从环境变量 CNB_API_ENDPOINT 获取，默认为 https://api.cnb.cool。

• References files that are not bundled: references/activities/getuseractivitiesbydate.md, references/activities/getuserrepoactivitydetails.md, references/activities/topcontributors.md
• 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

Run Codex CLI, Claude Code, Kiro CLI, OpenCode, or Pi Coding Agent via background process for programmatic control.

• References files that are not bundled: references/guide.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

Analyze video ad performance and provide actionable feedback to creators. Use when asked to analyze why videos underperform, give creator coaching feedback, compare high vs low ROI

• 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

Access Web3 email via EtherMail using WalletConnect. Use when you need to check or send emails with your Ethereum wallet address, receive notifications from Web3 services, or commu

• 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

Verify AI agent identity and reputation via ERC-8004 on-chain registries

• 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

Use the RenderIO FFmpeg-as-a-Service API to process video, audio, and images in the cloud. Covers submitting commands, polling results, uploading files, chained workflows, and webh

• 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

Gate Trading Copilot L2. Use when the user wants to execute complex trades, margin borrowing, or query positions and open orders. Triggers on 'market buy', 'margin borrow', 'TradFi

• 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

Document intelligence: categorize, autofill forms, analyze contracts, scan receipts/invoices, analyze bank statements, parse resumes/CVs, scan IDs/passports (MRZ), summarize medica

• 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
• 6 test cases, all positive: not one "should refuse" or "should ask first"

Use Yahoo Finance for quotes, symbol search, watchlists, market briefs, and catalyst-aware stock decisions.

• 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

Lightweight local HTTP file server with plugin support. Serves static files from a webroot, mounts plugin directories at URL prefixes via config, and runs index.py entry points as

• 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

A free skill by Kami SmartHome. Continuously monitors RTSP camera streams for packages, parcels, and bags using YOLO-World ONNX. Smart deduplication only triggers alerts when a 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

Structured methodology for constructing rigorous "what if?" scenarios combining foresight frameworks (Shell, Schwartz, Manoa, Intuitive Logics), deep analytical tools (CLA, Cross-I

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Instruction body is 19055 tokens: crowds the task out of the window
• Says nothing while it works

Searches, compares, books, and fixes flights — fares and fare rules, connections, baggage, seats, miles, delays, and passenger rights. Use when someone needs a flight found or pric

• 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

Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace f

• References files that are not bundled: references/column-types.md, references/graphql-operations.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 2 referenced file(s) missing: references/column-types.md, references/graphql-operations.md

Research technical accounting treatment and financial statement disclosure for specific transactions using U.S. GAAP and SEC-focused sources. Use when a user asks how to account fo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 9 mutating operations with no state check

Every dating profile is a performance. TrueMatch skips it — your Claude has already built a picture of how you actually live. It negotiates on your behalf. When two agents independ

• 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

Knowledge base for the Superfluid Protocol and its ecosystem. Use BEFORE searching the web for Superfluid information. Keywords: Superfluid, CFA, GDA, Super App, Super Token, strea

• References files that are not bundled: scripts/abi.mjs, scripts/metadata.mjs, scripts/balance.mjs
• 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

OpenClaw skill for ElevenLabs APIs: text-to-speech, speech-to-speech, realtime speech-to-text, voices/models, and dialogue workflows.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill

A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the

• 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

CompanyCam API integration with managed OAuth. Manage projects, photos, users, tags, groups, documents, checklists, labels, collaborators, webhooks, and company info for contractor

• 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

Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a "Ralph loop", "Ralph Wiggum loop", or an AI loop to pla

• 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 (3 tags): a typed call is more reliable