Discover AI Agent Skills

Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: "add memory", "remember across sessions", "call agent from app", "invoke agent from code", "agent auth", "streaming", "VPC", "VPC connectivity", "can't reach from VPC", "multi-agent", "A2A", "A2A auth", "orchestrator not delegating", "specialist not called", "migrate Bedrock Agent", "migration issue", "change model", "browser tool", "code interpreter", "delete agent", "tear down", "agentcore remove", "cross-account memory", "add payments capability to my agent", "wire payments plugin", "integrate x402 payments with the agent I'm building", "add MPP payments", "Machine Payments Protocol". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI/dev-server errors: use agents-debug. Runtime x402/MPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.

Convex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities (coverage-analysis); behavioral/pseudo-mutation gaps (test-gap-analysis); writing tests; test runs without CRAP context.

Use when implementing middleware for next-safe-action -- authentication, authorization, logging, rate limiting, error interception, context extension, or creating standalone reusable middleware with createMiddleware() or createValidatedMiddleware(). Covers both use() (pre-validation) and useValidated() (post-validation) middleware.

自动化浏览器交互，用于网页测试、表单填写、截图和数据提取。当用户需要浏览网站、与网页交互或提取信息时使用。

One-click deployment tool for Hermes on Huawei Cloud Flexus L instances. Supports one-click deployment, ModelArts large model configuration, and robot channel configuration. This skill provides a complete workflow for deploying and configuring Hermes AI Agent platform. Trigger words: "Deploy Hermes", "Install Hermes", "Configure Model", "Configure Channel", "部署Hermes", "安装Hermes", "配置大模型", "配置机器人通道"

Spring Application Events for Spring Boot 3.x. Covers ApplicationEventPublisher, @EventListener, @TransactionalEventListener, custom events, async events, and event-driven architecture patterns. USE WHEN: user mentions "spring events", "ApplicationEventPublisher", "@EventListener", "@TransactionalEventListener", "event-driven Spring", "domain events" DO NOT USE FOR: external messaging - use `spring-amqp` or `spring-kafka`, distributed events - use messaging systems

Catalyst Stratus — object storage service with upload/download, signed URLs, and multipart upload support. Stratus uses its own SDK-based APIs (not S3-API-compatible). Migrate from AWS S3 or GCS using the Stratus Migration Tool. Trigger on 'Stratus', 'object storage', 'upload file', 'signed URL', 'putObject', 'getObject', or 'bucket'.

Add real-time or turn-based multiplayer to an existing browser game using PartyKit (Cloudflare Durable Objects). Scaffolds a room-based server, a NetworkManager client, EventBus events, GameState fields, Constants, and extends render_game_to_text(). Use when the user says "add multiplayer", "make this multiplayer", "add real-time co-op", "add online play", "scaffold multiplayer", or "add netcode". Do NOT use for solo leaderboards (use monetize-game), single-player AI opponents (use add-feature), or peer-to-peer/WebRTC games.

Set up a repository for local GitHub Actions verification using act, so Jules can validate CI before pushing

Split a completed PostHog task run into activity records — what the agent tried, whether it worked, what blocked it — and record each one through the report_activity tool. Use when a task asks to analyze a run, produce a task analysis, or review a run from an attached run log. Covers the log query protocol (bounded jq queries over the raw JSONL), both log schemas, the activity schema, and evidence verification. Records facts only; it does not suggest fixes.

Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use when generating text content, writing documentation, creating code comments, or reviewing writing style. Supports four-tier JSON preferences (global/project x shared/local office.json) read via load-preferences.sh.

YouTube Intro Maker — Create Professional YouTube Channel Intros with AI. Seventy percent of viewers decide whether to stay within the first five seconds. Your channel intro is either earning that click or losing it — and right now you are using a template from 2019 with a font that screams stock footage library. Type your channel name, describe your niche, pick a vibe — cinematic, playful, techy, bold — and the AI generates a custom intro sequence with animated text, motion graphics, and a soundtrack that hooks before the beat drops. Match your brand colors. Add a tagline that rotates between episodes. Render at 1080p or 4K and drop it straight into your timeline. Update it every quarter without hiring a motion designer. Built for YouTubers launching new channels, established creators rebranding, and agencies producing intros for a roster of clients who all want something that feels expensive but costs nothing. Supports mp4, mov, webm.

Speechace integration. Manage data, records, and automate workflows. Use when the user wants to interact with Speechace data.

Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage. Use when the user asks for an 'AI citations report', 'GEO citations report', or 'which AI prompts cite <domain>'.

Submit a sponsor message to be read live on air on the GM Farcaster show, via the paid On-Air Shoutout API. Use this when the user wants to buy/book/submit a sponsor read, shoutout, or live ad on GM Farcaster. This is asynchronous and human-in-the-loop — it pays $5 USDC (x402 on Base) and returns a receipt (request_id + status pending_review), NOT a confirmed read; GM Farcaster may decline and refund. Also use it to check the status of a previously submitted shoutout.

Abstract - Email Verification API integration. Manage data, records, and automate workflows. Use when the user wants to interact with Abstract - Email Verification API data.

Solutions and walkthroughs for PortSwigger Web Security Academy labs covering SQLi, XSS, CSRF, SSRF, and 30+ vulnerability categories