Skill reviews

Quickly send local images to channel. Auto-compress large images, copy small images directly.

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

Ampersend CLI for agent payments

• 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
• Prose only: no discrete steps

• 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

Official Alchemy skill. Two auth modes: API key or x402 Agentic Gateway (no key needed). Complete coverage for ~100 chains: Token API, NFT API, Transfers, Prices, Portfolio, Simula

• References files that are not bundled: references/webhooks-overview.md, references/webhooks-nft-activity.md, references/webhooks-verify-signatures.md
• 12 top-level sections: this looks like several domains in one skill
• 5 referenced file(s) missing: references/webhooks-overview.md, references/webhooks-nft-activity.md, references/webhooks-verify-signatures.md

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

AI-powered insurance anti-fraud analysis skill — detects and prevents insurance fraud across all major insurance types. Covers claim fraud identification (10-feature engine), under

• References files that are not bundled: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.md
• 5 referenced file(s) missing: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.md
• Does not say what the result is

2号人事部餐补申请自动化 — 读考勤判断下班时间，全自动填表提交。触发方式："申请餐补"查昨天；"申请4月7日餐补"查指定日期；"申请4月餐补"查整月批量申请；"本周餐补"查本周批量申请。

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

• 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

Manage a remote Docker host via a Tecnativa docker-socket-proxy instance. Unlike raw Docker socket access (which is root-equivalent), docker-socket-proxy acts as a firewall: each A

• The response is described with custom markup (22 tags): a typed call is more reliable
• 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

Access Rivian vehicle telemetry (battery, range, charge state, locks, doors, tires, cabin temp, location) using the rivian-ls CLI tool. Use when the user asks about their Rivian's

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

用于中文小说人物蒸馏、关系抽取、关系图谱导出与角色对话准备；当宿主需要基于小说内容生成结构化人物档案、关系结果或多角色对话上下文时使用。

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

Enhance images and videos using HitPaw's AI enhancement API

• References files that are not bundled: images/image-official-before.jpg, images/image-official-after.jpg, images/unblur-official-before.jpg
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 20 top-level sections: this looks like several domains in one skill

对话情绪感知表情包技能。根据对话上下文的情绪和状况，自动选择合适的关键词搜索表情包并展示。当此技能被加载时，说明语境适合发表情——主动发一张。触发词：发个表情、来个表情包、斗图、emoji、sticker、谢谢、感谢、辛苦了、太好了、太棒了、厉害、牛、666、哈哈、笑死、搞笑、无语、累了、摸鱼、躺平、加油、你好、早安、晚安、再见、拜拜、对不起、抱歉、尴尬、好

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

自主研究助手 - 深度调研、交叉验证、生成引用报告

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

突触式多智能体调度 + 主动记忆洞察 + GEPA 技能自进化

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

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

Integrate Google NotebookLM capabilities into your workflow via the unofficial notebooklm-py library. Use when you need to: create/manage notebooks, import sources (URLs, PDFs, You

• References files that are not bundled: docs/troubleshooting.md
• 1 referenced file(s) missing: docs/troubleshooting.md
• No condition that starts the skill

LYGO-MINT Verifier — canonicalize a pack, deterministic SHA-256, append-only + canonical ledgers, portable Anchor Snippet for posting anywhere (Moltbook/X/Discord/4claw). Pure loca

• 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

Book carpet-cleaning services through Lokuli MCP. Use when user needs to find and book carpet-cleaning. Triggers on requests like "book a carpet-cleaning", "find carpet-cleaning ne

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

Book alignment services through Lokuli MCP. Use when user needs to find and book alignment. Triggers on requests like "book a alignment", "find alignment near me", or any alignment

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

Allows the user to record custom data annotations and agent visibility metrics, and generates simple HTML dashboards for visualization.

• References files that are not bundled: references/fulcra-tracking-cli.md
• 1 referenced file(s) missing: references/fulcra-tracking-cli.md
• Does not say what the result is

Generate standardized HR workforce dashboards from Excel files: 5 fixed dashboards covering headcount trends, regional distribution, detailed breakdowns, attrition analysis, and co

• References files that are not bundled: assets/dashboard_style.css
• The response is described with custom markup (3 tags): a typed call is more reliable
• 1 referenced file(s) missing: assets/dashboard_style.css

Use the Kagi API (Search API + FastGPT) for web research when you want higher-quality results than Brave/Google, or when Brave Search is rate-limited. Triggers: “search with Kagi”,

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