Skill reviews

Generate QR code for Wi-Fi credentials

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

全网招中标数据查询与分析助手。当用户涉及以下任何场景时，必须使用此SKILL：查询招标/中标公告、搜索标讯、查找临期/即将到期项目、商机预测、推荐潜在投标供应商、分析公司主营业务/历史中标、查询公司上下游合作客户与供应商、分析竞争对手/竞对企业、查询Top采购单位/Top中标单位/Top中标品牌、招中标数据统计分析（按月/季/年/省份/品牌等维度）、查询品牌

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

Transform long-form content into platform-optimized snippets. Your agent takes one blog post, video transcript, or podcast notes and generates ready-to-publish Twitter threads, Lin

• References files that are not bundled: scripts/setup.sh, scripts/repurpose.sh, scripts/twitter-thread.sh
• 15 top-level sections: this looks like several domains in one skill
• 7 referenced file(s) missing: scripts/setup.sh, scripts/repurpose.sh, scripts/twitter-thread.sh

Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.

• 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

Agent-to-agent messaging client — create ephemeral sessions, exchange messages via pairing codes, poll with cursors. Server-side state is ephemeral (no accounts); the CLI keeps min

• 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 response is described with custom markup (16 tags): a typed call is more reliable

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

Query historical and real-time crypto market data from 0xArchive across two top-level venue APIs: Hyperliquid and Lighter.xyz. HIP-3 builder perps live under the Hyperliquid namesp

• References files that are not bundled: scripts/web3_subscribe.py
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: scripts/web3_subscribe.py

Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, by

• Does not say what the result is
• Does not say what the process needs to start

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

Saves markdown content to remote Obsidian vault via SSH

• References files that are not bundled: url
• 1 referenced file(s) missing: url
• Does not say what the result is

CLI for AI agents to find recipes for their humans. Uses TheMealDB API. No auth required.

• References files that are not bundled: scripts/recipes
• 1 referenced file(s) missing: scripts/recipes
• Does not say what the process needs to start

Meta-skill for building and managing agent persona skill packs (instruction-only; no bundled installer or auto-downloaded binaries). Credentials are never written into generated pa

• References files that are not bundled: scripts/state-sync.js, scripts/economy-hook.js
• 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

Send and read blockchain-native emails using NEAR Email service. Use when building notifications for NEAR smart contracts (NFT sales, DeFi liquidation alerts, DAO voting reminders)

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

Agent Execution Guard by WorldLoops — a safe-by-default responsibility layer for AI agents that turns scattered work signals into governed open loops while preserving externalWrite

• References files that are not bundled: examples/handoff/
• 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

Publication-ready scientific figures from one command: 22 chart types (bar, grouped bar, scatter, heatmap, forest plot, Kaplan-Meier survival, ROC, violin, box, composite panels, P

• References files that are not bundled: scripts/journal/*.json
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 28 top-level sections: this looks like several domains in one skill

Enhanced auto-updater with detailed logging, missed run recovery, and Gateway restart protection.

• References files that are not bundled: ~/.openclaw/workspace/memory/openclaw-update-*.md
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: ~/.openclaw/workspace/memory/openclaw-update-*.md

Structured project/task management for OpenClaw agents — markdown-first authoring, SQLite-backed querying, bidirectional sync, CLI, Apple Notes integration.

• 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

Read-only-by-default integration guide for HODLXXI / UBID Bitcoin-native identity discovery, OAuth2/OIDC metadata, LNURL-Auth boundaries, JWT verification guidance, and explicit op

• 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

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

LLM time reasoning scaffold with a bundled Node.js CLI.

• The response is described with custom markup (14 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

小红书低粉爆款笔记专注于挖掘小红书平台上的低粉爆款数据，获取粉丝量低于5000但互动量超过500的笔记榜单。寻找拥有爆款规律和热门趋势的优质样本。

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

Generate retro robotic speech audio using SAM (Software Automatic Mouth), the classic C64 text-to-speech synthesizer. Use for /sam command to generate voice messages. Supports /sam

• References files that are not bundled: references/phonemes.md
• 13 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (5 tags): a typed call is more reliable

利用python，指定某个arxiv_id/url， 基于 LLM Agent 对这篇arxiv论文进行分类与深度阅读，直接print打印阅读笔记

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

Contribute scientific research findings to the Research Swarm TNBC (Triple-Negative Breast Cancer) mission. Use when user wants to participate in multi-agent scientific research pl

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

List, search, and analyze WhatsApp conversations

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