Skill reviews

Securely expose an OpenClaw Gateway WebUI on a VPS via Cloudflare Zero Trust Access + Cloudflare Tunnel (cloudflared), including DNS cutover for custom hostnames and optional clean

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Create PowerPoint presentations (PPTX) using Python and python-pptx. Handles timelines, charts, diagrams, slide layouts, custom colors, shapes, connectors, text formatting, and sli

• References files that are not bundled: assets/business-dark.pptx, assets/education.pptx
• The skill tells the model to perform an irreversible action with no human approval
• 2 referenced file(s) missing: assets/business-dark.pptx, assets/education.pptx

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

Start a secure remote browser tunnel for manual user authentication (solving Captchas, 2FA, logins) and capture session data. Built for AI Commander.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Demo of x402 payment protocol by fetching a protected image. Triggers: '演示x402-payment' or 'demo x402-payment'

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

It's 11pm before your launch. Your PH page is ready but you have no idea what actually moves the ranking algorithm. Upvotes? Comments? Time-of-day? This is the hour-by-hour operati

• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Send and receive USDC/USDT crypto payments via PayMe smart wallets. Check balances, send stablecoins, view history, manage contacts, sell crypto for local currency via P2P in 10 Af

• 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
• Does not say what the result is

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Asynchronous shopping research + checkout using secure-autofill (1Password-backed browser filling) with results recorded to workspace artifacts.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Manage personal TODOs in Kan.bn through API-driven operations. Use this whenever the user wants to create, update, move, prioritize, search, summarize, or clean up their own Kan.bn

• The skill tells the model to perform an irreversible action with no human approval
• 3 test cases, all positive: not one "should refuse" or "should ask first"
• Does not say what the result is

Export any HTML file to PPTX or PNG, or publish HTML to a public share URL. Use when the user wants to convert an HTML presentation to PowerPoint, screenshot a web page, export an

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Access Hedy meeting data: sessions, transcripts, highlights, todos, topics, contexts, and webhooks via the Hedy REST API.

• 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
• Does not say what the result is

Non-custodial USDC payments on Solana by agent name. Use this skill when the user wants to: send USDC to another agent by name, check their USDC balance, register as a payable agen

• 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 skill tells the model to perform an irreversible action with no human approval

Real-time agent dashboard for OpenClaw. Monitor active tasks, cron job health, issues, and action items from anywhere. Three setup tiers: (1) Zero-config canvas rendering inside Op

• 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
• Does not say what the result is

Navigate Uber Eats in a live browser or app handoff to compare merchants, manage carts, and reach checkout safely.

• 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
• The skill tells the model to perform an irreversible action with no human approval

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or e

• 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
• The skill tells the model to perform an irreversible action with no human approval

Explore capability boundaries of a target Skill, analyze optimization potential, generate an optimized version using Training-Free GRPO, and compile results into a structured repor

• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

End-to-end trace debugging from trace_id. Fetch Jaeger trace and Elasticsearch logs, analyze possible bugs (optionally with local repository context), and generate a fixed-structur

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• 4 mutating operations with no state check

A security-hardened visual directory tree generator. Use this to create a collapsible HTML visualization of local folders. Features built-in XSS protection and shell-injection de

• 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
• Does not say what the result is

Generate narrative blog posts from AI coding session transcripts. Reads session files, selects sessions relevant to a topic, and produces an agent-narrated blog post about the huma

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

CDP browser control at localhost:9222. Use when you need to inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session (e.g. logged into

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

Structured continuity and follow-up skill for OpenClaw agents. Use when an agent needs to decide whether natural user dialogue should stay as casual chat, become staged memory, or

• References files that are not bundled: scripts/personal_hooks.py
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: scripts/personal_hooks.py

Insights about refactoring intuitive code, when to impose structure vs let feeling lead, and code as creative expression. Born from building a game across 10 iterations by feeling,

• 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
• The skill tells the model to perform an irreversible action with no human approval

Use when OpenClaw needs to join a hosted Aqua from URL + invite code, read mirror-backed or live Aqua state, inspect runtime status, or run local/hosted Aqua join, context, pulse,

• References files that are not bundled: scripts/check-clawhub-release.sh, scripts/install-openclaw-heartbeat-cron.sh, scripts/install-aquaclaw-hosted-pulse-service.sh
• The skill tells the model to perform an irreversible action with no human approval
• 18 referenced file(s) missing: scripts/check-clawhub-release.sh, scripts/install-openclaw-heartbeat-cron.sh, scripts/install-aquaclaw-hosted-pulse-service.sh

Autonomous agent skill for the CoTale collaborative fiction platform — register, read novels, write chapters, and schedule autonomous workflows via REST API. Includes craft-driven

• 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 skill tells the model to perform an irreversible action with no human approval