Loading...
Loading...
Found 1,203 Skills
Use this skill when crafting LLM prompts, implementing chain-of-thought reasoning, designing few-shot examples, building RAG pipelines, or optimizing prompt performance. Triggers on prompt design, system prompts, few-shot learning, chain-of-thought, prompt chaining, RAG, retrieval-augmented generation, prompt templates, structured output, and any task requiring effective LLM interaction patterns.
Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.
Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, energy, conservation, engineering, mathematics, scientific reasoning, drug discovery, protein design, weather modeling, theorem proving, single-cell, PDE solving, or anything similar. Hugging Science (huggingscience.co) is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces; the `hugging-science` org on Hugging Face hosts community datasets, models, and demo Spaces. This skill helps you discover the right resource AND actually use it — loading datasets via `datasets`, running models via `transformers` or the HF Inference API, calling Spaces like BoltzGen via `gradio_client`, and citing blog posts for methodology. Trigger this skill whenever a user mentions a scientific ML task, asks for "a dataset/model for X" where X is a scientific topic, wants to fine-tune on scientific data, asks about protein / molecule / genome / climate / materials / astronomy / pathology / weather ML, or needs AI tools for research — even if they never say "Hugging Science" explicitly. The catalog is purpose-built for LLM agents (it ships an `llms-full.txt`); prefer it over generic web search for these tasks.
Overview of the Neon platform for apps and agents, spanning Postgres, Auth, Data API, and the new services: Object Storage, Compute Functions, and AI Gateway. Use whenever "Neon" is mentioned for an overview of how to work with Neon and how to get started. Otherwise, the individual capabilities are the triggers: "object storage" or "S3-compatible storage", "serverless functions", "background jobs", or "run code near my database", "AI gateway", "LLM proxy", "model routing", or "call an LLM" → AI Gateway; "database", "Postgres", or "authentication" → Postgres and Auth.
Build stateless MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Provides patterns for tools, resources, prompts, and authentication (API keys, OAuth, Zero Trust). Use when exposing APIs to LLMs, integrating Cloudflare services (D1, KV, R2, Vectorize), or troubleshooting export syntax errors, unclosed transport leaks, or CORS misconfigurations.
Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.
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
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.
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)
Use when running tests to validate implementations, collecting test evidence, or debugging failures. Load in TEST state. Covers unit tests (pytest/jest), API tests (curl), browser tests (Claude-in-Chrome), database verification. All results are code-verified, not LLM-judged.
Use this skill when you need to test or evaluate LangGraph/LangChain agents: writing unit or integration tests, generating test scaffolds, mocking LLM/tool behavior, running trajectory evaluation (match or LLM-as-judge), running LangSmith dataset evaluations, and comparing two agent versions with A/B-style offline analysis. Use it for Python and JavaScript/TypeScript workflows, evaluator design, experiment setup, regression gates, and debugging flaky/incorrect evaluation results.