发现 AI Agent Skills

Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter), generates detailed blueprints with visualization options, naming conventions, file placement patterns, and extension templates for maintaining consistent code organization across diverse technology stacks.

Invoiced integration. Manage Organizations. Use when the user wants to interact with Invoiced data.

Runs NVIDIA garak probe suites (jailbreak, prompt injection, data leakage, toxicity, and more) against an LLM endpoint - Hugging Face models, OpenAI-compatible APIs, or Bedrock - then interprets the resulting hit-rate report for triage. Use when baselining LLM security before/after deployment, validating that a guardrail or fine-tune reduces jailbreak/injection success rates, or producing evidence for an AI risk assessment.

Video Editor Deutsch - KI Video Bearbeiten, Schneiden und Exportieren. Videos schneiden, zusammenfuegen, Hintergrundmusik hinzufuegen, Farbkorrektur anwenden, Untertitel einfuegen und als MP4 exportieren. Ein KI-Video-Editor der komplett ueber Chat funktioniert, ohne Timeline und ohne Videobearbeitungssoftware. Lade ein Video hoch oder sende einen Link und beginne mit der Bearbeitung in natuerlicher Sprache. Unterstuetzt Videobearbeitung fuer TikTok, Instagram Reels, YouTube Shorts und Social Media Inhalte. Video schneiden, Video zusammenfuegen, Musik zu Video hinzufuegen, Text in Video einfuegen, Video kuerzen, Video drehen, Untertitel erstellen, Farbkorrektur, Video exportieren. KI-Videobearbeitung auf Deutsch. Exportiert als MP4. Akzeptiert mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

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

Architecture specialist for software/system design, module and service boundaries, tradeoff analysis, and stakeholder synthesis. Uses context-aware methods such as diagnostic routing, design-twice comparison, ATAM-style risk analysis, CBAM-style prioritization, and ADR-style decision records.

Catalyst Zoho MCP — manage Catalyst infrastructure (tables, buckets, cache) via CatalystbyZoho_* MCP tools using natural language. Trigger on 'Zoho MCP', 'MCP tools', 'catalyst MCP', 'CatalystbyZoho', 'create table with AI', 'MCP setup', 'MCP config', 'global MCP server', 'infrastructure as conversation', 'MCP first', 'avoid Catalyst console', or 'use MCP instead of console'.

Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creators need to combine subjects, materials, compositions, and styles from multiple references with Nano Banana through the AI Hive OpenAPI. It handles required media uploads, live model and price lookup, task submission, progress polling, and result downloads. Useful for product photography, marketplace images, product detail pages, posters, ad creatives, social commerce, seeding content, retouching, and background replacement. Search intents include multi-reference image, multi-image composition, reference fusion.

Apply production-ready Groq SDK patterns for TypeScript and Python. Use when implementing Groq integrations, refactoring SDK usage, or establishing team coding standards for Groq. Trigger with phrases like "groq SDK patterns", "groq best practices", "groq code patterns", "idiomatic groq".

React coding conventions for this codebase. Use when writing or reviewing React components, when asked about component structure, section ordering, Tailwind CSS usage, state management patterns, conditional rendering, list rendering, or React 19 conventions. Covers component section layout (🔖🧩🪝🏗💪🏁🎨), Tailwind CSS with theme tokens, TanStack Router file-based routing, lexico-components usage, and testing with Vitest + RTL.

Verify a governed OpenEvidence workflow across supported web and mobile surfaces without fictitious dev or staging hosts. Use when working with OpenEvidence in a healthcare organization. Trigger with "openevidence multi env setup", "OpenEvidence web", or a matching workflow request.

Assemble a minimal Canva Connect diagnostic bundle without credentials, customer content, raw payloads, or full headers. Use when preparing an incident handoff or provider escalation. Trigger with: "Canva debug bundle", "collect Canva evidence", "sanitize Canva diagnostics".

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Onboard a developer to a repository using Ontoly graph summaries. Use when asked to explain a new codebase, identify entrypoints, map packages, or suggest first files to inspect.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Launch Chrome with an unpacked extension and test its UI via CDP. Auto-installs Chrome for Testing if needed. Loads the extension, opens sidepanel/popup/options page, and hands off to cdp-connect for interaction (click, type, screenshot, ax-tree). Handles Chrome 137+ branded build restrictions (Extensions.loadUnpacked via pipe), sidepanel user gesture requirements, and React input quirks. Use when you need to test a Chrome extension's UI, automate extension interactions, or validate extension behavior on a target page. Triggers on: chrome extension test, test extension, load unpacked extension, extension sidepanel, extension popup, test chrome extension, extension testing, chrome extension automation, ext pilot, cdp extension.

Add a new sound effect to @remotion/sfx

Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.