Loading...
Loading...
Found 1,066 Skills
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
Comprehensive guide for writing modern Neo4j Cypher read queries. Essential for text2cypher MCP tools and LLMs generating Cypher queries. Covers removed/deprecated syntax, modern replacements, CALL subqueries for reads, COLLECT patterns, sorting best practices, and Quantified Path Patterns (QPP) for efficient graph traversal.
Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety plan, roadmap). Use for AI product strategy, LLM/agent strategy, AI roadmap, AI-first product direction.
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.
Multimodal media authentication and deepfake forensics. PRNU analysis, IGH classification, DQ detection, semantic forensics, and LLM-augmented sensemaking for the post-empirical era. Use when working with deepfake, media forensics, fake detection, synthetic media, prnu, image authentication, video verification, disinformation.
Longbridge Developers platform expert. Use when: (1) querying market data or executing trades via CLI (`longbridge` command), (2) writing Python/Rust programs using the `longbridge` SDK, (3) configuring the Longbridge MCP server for AI tools (Cursor, Claude Code, ChatGPT), (4) integrating Longbridge docs into LLM/RAG systems via llms.txt or Markdown API. Covers all markets: HK, US, CN (SH/SZ), SG, Crypto. Triggers on `longbridge` imports, stock symbols (TSLA.US, 700.HK), API key setup, order placement, WebSocket subscriptions, or any Longbridge platform capability question.
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
Production-ready skill for integrating TheSys C1 Generative UI API into React applications. This skill should be used when building AI-powered interfaces that stream interactive components (forms, charts, tables) instead of plain text responses. Covers complete integration patterns for Vite+React, Next.js, and Cloudflare Workers with OpenAI, Anthropic Claude, and Cloudflare Workers AI. Includes tool calling with Zod schemas, theming, thread management, and production deployment. Prevents 12+ common integration errors and provides working templates for chat interfaces, data visualization, and dynamic forms. Use this skill when implementing conversational UIs, AI assistants, search interfaces, or any application requiring real-time generative user interfaces with streaming LLM responses. Keywords: TheSys C1, TheSys Generative UI, @thesysai/genui-sdk, generative UI, AI UI, streaming UI components, interactive components, AI forms, AI charts, AI tables, conversational UI, AI assistants UI, React generative UI, Vite generative UI, Next.js generative UI, Cloudflare Workers generative UI, OpenAI generative UI, Claude generative UI, Anthropic UI, Cloudflare Workers AI UI, tool calling UI, Zod schemas UI, thread management, theming UI, chat interface, data visualization, dynamic forms, streaming LLM UI
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered search visibility in ChatGPT, Perplexity, Google AI Overviews, and other AI search platforms. Use when working with aeo, geo, ai search, chatgpt search, perplexity, ai overviews, generative search, llm visibility.
Use this when the user explicitly requests to "verify/optimize in-text citations of the `{topic}_review.tex` review" or to "run check-review-alignment". Use the host AI's semantic understanding to verify each citation against the literature content one by one. **Only when fatal citation errors are found**, make minimal rewrites to the "sentences containing citations", and reuse the rendering script of `systematic-literature-review` to output PDF/Word (the script does not directly call the LLM API locally). Core principle: **Do not modify for the sake of modifying**. When it is uncertain whether it is a fatal error, keep the original content and issue a warning in the report. ⚠️ Not applicable in the following cases: - The user only wants to generate the main body of a systematic review (should use systematic-literature-review) - The user only wants to add/verify BibTeX entries (should use a dedicated bib management process)
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.