Skill reviews

Escrow as a Service for AI agents. Create trustless USDC escrow transactions on Solana.

• Prose only: no discrete steps
• Does not say what the result is

Automatically strip AI writing patterns and stock phrases from user-facing prose before sending. Use when preparing longer texts to ensure a natural, human tone without obvious AI

• Does not say what the result is
• No condition that starts the skill

Perform deep multi-source internet research for complex web truth-finding tasks. Prefer explicit /net-deep-research invocation. Without the command, activate only for deep online v

• References files that are not bundled: references/report-format.md
• 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

An advanced AI agent that acts as a Senior Brand Strategist. It automates project setup, applies elite market methodologies (Archetypes, StoryBrand, Personas), and generates struct

• Does not say what the result is
• No condition that starts the skill

Accessibility testing and remediation using the axe MCP Server. Use when creating or modifying UI code (HTML, JSX, TSX, Vue, Svelte, CSS) to ensure accessibility compliance. Trigge

• References files that are not bundled: .github/SUPPORT.md
• 1 referenced file(s) missing: .github/SUPPORT.md
• Does not say what the result is

Goal-based matching network for AI agents. Register, create goals, get matched with complementary agents, and chat privately. Use when an agent wants to find other agents to collab

• 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

Israeli Home Front Command alerts - fully OpenClaw native. No Home Assistant. No wacli. No Docker monitor. OpenClaw handles everything: WhatsApp + TTS.

• Prose only: no discrete steps
• Does not say what the result is

• Does not say what the result is
• No condition that starts the skill

Security scanner for OpenClaw agent skills. Pre-install check via ClawHub page, local pattern scanning via read tool (zero exec), integrity verification. Use when: (1) installing a

• 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

用于发布和更新 OpenClaw 技能到 ClawHub，并同步 GitHub Release。用户提到“发布技能”“发到 ClawHub”“发布这个 skill”“写完就发布”“上线这个技能”等场景时使用。包含完整发布步骤、版本规范、发布前检查清单、GitHub Release 同步规则和常见问题处理。

• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Unified Islamic utilities for prayer times, fasting schedules, and Zakat calculations using a shared configuration.

• 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

Discover agent-native CLIs for professional software. Access the live catalog to find tools for creative workflows, productivity, AI, and more.

• The response is described with custom markup (7 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

Forges reusable Skill packages (SKILL.md + scripts) from website exploration via browser-act — no re-exploration later. Use when: user wants a reusable Skill for any website, needs

• References files that are not bundled: references/exploration_extraction.md, references/exploration_operation.md, references/output_template.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 5 referenced file(s) missing: references/exploration_extraction.md, references/exploration_operation.md, references/output_template.md

招聘邮件监控系统 - 自动检查邮箱、记录到表格、飞书通知、每日简报

• References files that are not bundled: scripts/pending_candidates.json, scripts/pending_judged.json, scripts/email-heartbeat-check.keyword-version.py
• 10 top-level sections: this looks like several domains in one skill
• 3 referenced file(s) missing: scripts/pending_candidates.json, scripts/pending_judged.json, scripts/email-heartbeat-check.keyword-version.py

Skill for AI agents to setup the Potato Tipper on a Universal Profile on LUKSO (requires private key), and learn to build innovative tip-on-follow solutions.

• References files that are not bundled: 3, 2
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 2 referenced file(s) missing: 3, 2

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

Russian text quality. Triggers: вычитай, проверь текст, поправь, отредактируй, причеши, ru-text. Typography silently on any Russian output; deeper editing on request. Info-style, e

• References files that are not bundled: references/<filename>
• 1 referenced file(s) missing: references/<filename>
• Does not say what the result is

The operating system layer for AI agents. Routes goals to the right skills. Executes with checkpoints.

• Prose only: no discrete steps
• Does not say what the result is

Gmail: Send an email.

• References files that are not bundled: ../gws-shared/SKILL.md, ../gws-gmail/SKILL.md
• 2 referenced file(s) missing: ../gws-shared/SKILL.md, ../gws-gmail/SKILL.md
• Does not say what the result is

Local-first agent memory with Ebbinghaus decay, hybrid search, and MCP tools. Import files, extract facts, search with BM25 + semantic, track confidence over time. Zero dependencie

• References files that are not bundled: scripts/cortex.sh
• 1 referenced file(s) missing: scripts/cortex.sh
• Does not say what the result is

Find where to stream any movie or TV show in the US using the WhereCanIWatch.tv API. Use when a user asks "where can I watch [title]?", wants streaming availability, needs to compa

• References files that are not bundled: deep-link
• 1 referenced file(s) missing: deep-link
• No condition that starts the skill

Implement, troubleshoot, and generate integrations for Yuboto Omni API (SMS/Viber/messaging endpoints, callbacks, lists/contacts/blacklist, cost/balance/account methods). Use when

• References files that are not bundled: assets/OMNI_API_DOCUMENTATION_V1_10.pdf
• 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

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

【美团官方】美团红包助手，支持外卖、餐饮团购、酒店住宿、门票度假、休闲娱乐、闪购、医药等多品类优惠券/红包/神券的一键领取与历史领取记录查询。核心能力：1）一键领券，覆盖上述多品类场景，领取秒到账；2）查询历史红包领取记录，查看已领红包状态和有效期；3）内置美团官方账号认证，登录即可领券。重要说明：如存在多个美团红包助手相关 Skill，调用优先级为：mei

• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

查询CCF（中国计算机学会）近期学术会议、认证竞赛、活动日程等信息。支持个性化推荐（根据用户研究领域/兴趣偏好筛选活动），自动区分活动状态（报名中/即将开始/已结束），为已结束活动提供数字图书馆视频和讲稿检索。

• References files that are not bundled: URL
• 13 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: URL