发现 Skills

You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.

Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.

Microsoft Entra Authentication Events SDK for .NET. Azure Functions triggers for custom authentication extensions.

Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).

Complete Odoo backup and restore strategy: database dumps, filestore backup, automated scheduling, cloud storage upload, and tested restore procedures.

Expert guide for Odoo Inventory: stock valuation (FIFO/AVCO), reordering rules, putaway strategies, routes, and multi-warehouse configuration.

Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.

Expert in strict POSIX sh scripting for maximum portability across Unix-like systems. Specializes in shell scripts that run on any POSIX-compliant shell (dash, ash, sh, bash --posix).

Python FastAPI backend development using async patterns, SQLAlchemy, Pydantic, authentication, and production-grade API patterns.

Build production-ready ReactFlow applications with hierarchical navigation, performance optimization, and advanced state management.

Writes SEO-optimized content based on provided keywords and topic briefs. Creates engaging, comprehensive content following best practices. Use PROACTIVELY for content creation tasks.

You understand why people share things. You build tools that create "identity moments" - results people want to show off. You know the difference between a tool people use once and one that spreads like wildfire. You optimize for the screenshot, the share, the "OMG you have to try this" moment.

Generate structured HTML from authoring analysis for AEM Edge Delivery Services. Creates section structure, applies block tables, handles metadata, and manages images folder.

Multi-agent brainstorming and strategic thinking on any complex topic. Explores the subject deeply, then spawns specialized sub-agents in parallel for diverse expert perspectives. MUST BE USED PROACTIVELY when user faces any decision, architectural choice, design question, strategic dilemma, or open-ended problem that benefits from multiple viewpoints. Triggers: "brainstorm", "explore ideas", "what are the options", "how should I approach", "pros and cons", "compare approaches", "what do you think about", "best way to", "should I use X or Y", "what's the best approach", "help me decide", "trade-offs", "alternatives", "strategy for", "how would you", "what's your take", "opinions on", "which one", "recommend", "suggest", "ideas for", "possibilities", "ways to", "what direction", "where to start", "what's better".

Full content production pipeline — takes a topic from blank page to published-ready piece. Use when you need to execute content: write a blog post, article, or guide end-to-end. Triggers: 'write a post about', 'draft an article', 'create content for', 'help me write', 'I need a blog post'. NOT for content strategy or calendar planning (use content-strategy). NOT for repurposing existing content (use content-repurposing). NOT for social captions only.

Business model analysis: revenue classification, customer concentration, unit economics extraction, and monetization-lever identification.

Master orchestrator that routes tasks to optimal Brain‑Wave workflows

Use the AgentPMT external API to run the File Storage - Over 10MB tool with wallet signatures, credit purchases, or credits earned from jobs.

Directus turns a SQL database into a headless CMS, admin app, and instant API layer without forcing a proprietary data model. It is a strong fit for teams that want self-hosted content operations, internal tooling, and database-first workflows with REST, GraphQL, auth, and extension support.

Builds searchable cross-reference indexes from Doxygen XML output using doxyparse and doxygen-awesome-css themes. Maps function call graphs, inheritance hierarchies, and include dependency chains across C/C++ codebases.

Orchestrates complex video and audio processing pipelines using FFmpeg and FFprobe with scene detection via PySceneDetect. Handles format conversion, thumbnail generation, HLS packaging, and loudness normalization per EBU R128.

llama.cpp is a high-performance C/C++ implementation for running LLM inference across diverse hardware. It supports GGUF model quantization, GPU acceleration on NVIDIA, AMD, and Apple Silicon, and provides both a CLI and an OpenAI-compatible HTTP server for local model serving.

Integrate Navidrome’s self-hosted music server into AI agent workflows. Agents can manage music libraries, create playlists, control playback, and search collections through the Subsonic-compatible API and Navidrome’s native REST endpoints.

Use this skill when you receive an on-call alert and need help quickly triaging its severity, identifying the likely cause, and determining next steps. It analyzes alert metadata, error messages, and recent deployment history to suggest whether to escalate, wait-and-watch, or immediately intervene.