Loading...
Loading...
Found 338 Skills
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.
Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Covers DSPy model portability — provider config, re-optimization, model comparison, and multi-model pipelines.
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks. Originally from OpenAI's curated skills catalog.
Search and retrieve Microsoft Customer Stories from the official Microsoft Customer Stories site (https://www.microsoft.com/en-us/customers/search). Use when the user asks to find customer case studies, success stories, or reference examples of Microsoft technology adoption. Supports filtering by product (Azure, M365, Dynamics 365, etc.), region/country, industry, business need, organization size, and keyword search. Can also fetch individual story details. Typical triggers include questions like "Find customer stories about Azure OpenAI in Japan", "Show me healthcare companies using Microsoft 365 Copilot", or "日本の製造業でAIを活用した事例を探して".
Implement OpenAI Harness Engineering practices in any repository. Use when setting up or refactoring agent-first workflows, writing or upgrading AGENTS.md and PLANS.md, creating deterministic smoke/test/lint/typecheck harness commands, defining strict architecture boundaries and data-shape contracts, wiring observability from day 1, and adding entropy-control checks plus CI automation for reliable autonomous runs.
Autonomous novel writing CLI agent - use for creative fiction writing, novel generation, style imitation, chapter continuation/import, EPUB export, and AIGC detection. Supports Chinese web novel genres (xuanhuan, xianxia, urban, horror, other) with multi-agent pipeline, two-phase writer (creative + settlement), 33-dimension auditing, token usage analytics, creative brief input, structured logging (JSON Lines), and custom OpenAI-compatible provider support.
Expert knowledge for Azure AI Video Indexer development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Video Indexer APIs/widgets, live camera indexing, custom speech/brand models, or Azure OpenAI integrations, and other Azure AI Video Indexer related development tasks. Not for Azure AI services (use microsoft-foundry-tools), Azure AI Vision (use azure-ai-vision).
Guide to video generation in MassGen. Use when creating videos from text prompts or images across Grok, Google Veo, and OpenAI Sora backends.
Setup and workflow for using sqry semantic code search as an MCP server with OpenAI Codex CLI. Covers installation, MCP configuration via `~/.codex/config.toml`, and recommended patterns for code analysis tasks. Install this skill to give Codex access to sqry's 34 AST-based code analysis tools.
Char (formerly Hyprnote) platform help — open-source, bot-free, local-first AI meeting notepad with system audio capture, markdown output, plugin SDK, and optional cloud STT/LLM (GPL-3.0). Use when setting up Char on macOS for the first time, speaker identification not working in group meetings, configuring local-only transcription with Cactus or Ollama for full offline use, choosing between Char's cloud STT providers (Deepgram, AssemblyAI, Soniox, OpenAI, etc.), app not launching or bouncing on dock without opening, telemetry concerns with PostHog or Sentry in a local-first app, building a Char plugin or using the automation hooks system, comparing Char to Granola or Meetily or Fathom for privacy, or configuring the CLI for template management. Do NOT use for picking between note-takers generally (use /sales-note-taker) or reviewing a single call for coaching (use /sales-call-review).
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.
Production voice AI agents with sub-500ms latency. Groq LLM, Deepgram STT, Cartesia TTS, Twilio integration. No OpenAI. Use when: voice agent, phone bot, STT, TTS, Deepgram, Cartesia, Twilio, voice AI, speech to text, IVR, call center, voice latency.