635 Claude Code skills tagged Openai. Browse all AI provider, model, or runtime-related skills in the open ClaudSkills registry — free to install, one-click via the desktop app.
Showing top 200 of 635 skills, ranked by quality score.
Generate or edit raster images for product design, frontend concepts, game assets, marketing visuals, and conceptual paper figures. Use when Claude should create a real image file
growth
Generate, revise, translate, and manage App Store / Google Play marketing screenshots. Full flow: initialize a .shots workspace, scrape App Store metadata, research the product fro
growth
A multimodal precision oncology agent leveraging GPT-4 and vision transformers for cancer diagnosis, biomarker detection, and treatment planning.
general
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Combines Wikipedia's "Signs of AI writ — from nd
science
Reproduce the Artificial Analysis (AA) language-model performance workload shapes against an OpenAI-compatible chat endpoint using NVIDIA AIPerf. Drives the three AA text shapes (1
general
Profile live inference traffic into a token/shape distribution artifact that drives profile-matched speculative-decoding draft training -- an analog of Fireworks FireOptimizer's "p
content
Brand mark / wordmark / logo generator. Defaults to ideogram-3-quality for cleanest embedded text (other text-strong fallbacks: gpt-image-2). Single-image output (no aspect multipl
tools
Meme-format graphic generator — top text + bottom text + optional centerpiece image. Wraps image-prompt --execute with a meme aesthetic anchor (Impact-style bold typography with st
tools
Text-to-speech skill — script in, MP3 out. Wraps the runner's audio modality (ElevenLabs eleven-tts + OpenAI gpt-4o-mini-tts). Supports voice picker, multilingual TTS (Eleven), spe
general
Erzeugt einen konsistenten Satz Bilder (Slide-Hintergruende, Bildserien) via OpenAI gpt-image-1. Trigger bei 'Slide-Hintergrund', 'deck background', 'Folien-Bilder generieren', 'pr
tools
Transcribes audio and video files to text using Qwen3-ASR. Supports two modes — local MLX inference on macOS Apple Silicon (no API key, 15-27x realtime) and remote API via vLLM/Ope
content
Generate or edit game-oriented raster assets using OpenAI gpt-image-2 through a bundled zero-dependency CLI. Ideal for sprites, tiles, UI elements, icons, portraits, backgrounds, c
general
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent handoffs, function tools, guardrails, sessions, streaming, or tracing with the `openai-agents` / `a
security
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivation
general
SponsorGap platform help — newsletter sponsorship intelligence with 38K+ brand database, GPT-powered sponsor matching, verified decision-maker contacts, competitor monitoring, spen
sales
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to
science
End-to-end AI website generation pipeline. Single Claude Code prompt builds complete Vite+React+Tailwind sites from business data. Pre-research via APIs, media acquisition, brand e
science
Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter
general
Create your OpenAI Apps SDK skill in one prompt, then learn to improve it throughout the chapter
general
Set up 9Router as a local AI gateway so coding agents never stop when a provider quota runs out — one OpenAI-compatible endpoint (localhost:20128) fanning out to 40+ providers with
engineering
Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.
general
Création d'assistants IA hébergés avec l'API OpenAI Assistants v2. File search avec vector stores, code interpreter, function calling, threads persistants et streaming. S — from kh
general
Ollama, LM Studio, vLLM gibi yerel OpenAI uyumlu /v1 uçları için port, model ve tool desteği fallback’ini yapılandırırken kullan.
general
Uzak OpenAI uyumlu API ile base_url, api_key, model ve proxy kullanımını yapılandırırken kullan.
general
Fine-tune Gemma 4 26B-MoE and Qwen3-VL-30B-A3B with LoRA rank 16 BF16, deploy Qwen3.5-35B-A3B with vLLM on Azure H100 NVL 96GB for AgroSatCopilot. Use when fine-tuning VLMs with Lo
general
Pola lengkap fitur AI Brief Assistant untuk Marketiv Flutter app — tombol "✨ Bantu dengan AI" di form buat campaign yang memanggil Appwrite Function generate-brief-fn (yang kemudia
general
Generate a high-cut-density action / fight scene by first composing a 16-cell storyboard image, then driving Seedance 2.0 image-to-video off that storyboard. Stacks GPT-Image-2 (ch
general
Configures TrueFoundry AI Gateway for unified OpenAI-compatible LLM access. Covers auth (PAT/VAT), model routing, rate limiting, and budget controls.
general
Generate AI images using OpenAI's gpt-image-1 model with customizable aspect ratios and artistic themes. Use when the user wants to create images, generate artwork, or mentions ima
general
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, GPT-5.4 Image 2, proxied through Cloudflare AI Gateway BYO
security
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini — from bg
content
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini — from bg
content
Bulk-generates SEO meta descriptions from page content using OpenAI's GPT-4o API with custom system prompts tuned for SERP CTR optimization. Validates character limits, checks for
tools
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabil — from op
science
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabil — from bg
science
Implement comprehensive safety guardrails for LLM applications including content moderation (OpenAI Moderation API), jailbreak prevention, prompt injection defense, PII detection,
content
5-model AI review: Claude Opus 4.6 + Gemini 3.1 + GPT-5.2 + Codex 5.3 + Perplexity — objectieve review van Bottie's autoresearch systeem
science
Migrate to Claude API from OpenAI, Gemini, or other LLM providers. Use when switching from GPT-4 to Claude, migrating from Text Completions, or building a multi-provider abstractio
general
Produces build artifacts with Software Bill of Materials (SBOM) and supply chain metadata for security and compliance. Use for "artifact publishing", "SBOM generation", " — from ac
security
Consult Hermes (the user's multi-provider LLM CLI, currently routing to GPT-5.5 / codex-class) as a strategic advisor (军师) via a `hermes chat -q` shell-out, then synthesize Hermes'
tools
Submit complex code questions to OpenAI GPT-5 Pro for deep analysis when you have 20 minutes. Use when the user asks for architectural analysis, comprehensive code review, debuggin
engineering
根据用户描述生成高质量绘图 prompt，并按通用、roadmap、schematic 模式调用 gpt-image-2 或 Nano Banana/Gemini 图片模型 API；第 2 轮起基于上一轮 PNG 做 image-to-image 微调，迭代出满足视觉要求的 PNG 结果。
product
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with \"auto review loop llm\" or \"llm revi
science
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
engineering
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgen — from en
engineering
Azure OpenAI Service 2025 models including GPT-5, GPT-4.1, reasoning models, and Azure AI Foundry integration
engineering
Azure OpenAI API patterns for rate limiting, function calling, error handling, and token optimization
engineering
Azure OpenAI Service integration. Manage Models, Deployments, Prompts, Completions. Use when the user wants to interact with Azure OpenAI Service data.
engineering
案件・LP・N1から N 枚の広告バナーを gpt-image-2 で生成する Skill。必須スロットが揃うまで画像APIを叩かない契約付き。Agentic RAGで不足スロットを自生成し、広告コンセプト15字以下・刺さる本能・ベネフィット起点キービジュアル・記憶に残るコピーを中核に、同一ニュアンスへの収束を防ぐ。
tools
OpenAI president Greg Brockman gave [$25 million](https://www.sfgate.com/tech/article/brockman-openai-top-trump-donor-21273419.php) to MAGA Inc in 2025. They gave Trump 26x more th
content
Use when building AI agents with OpenAI's Agents SDK. Triggers include creating agents, implementing tools, multi-agent handoffs, guardrails, MCP integration, tracing. Also for usi
engineering
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifyin
general
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI reso — from ba
engineering
Send prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2 Pro's research-grade intelligence. — from content/co
content
Send prompts to ChatGPT Pro via Playwriter browser automation. Use for cross-validation, second opinions, or leveraging GPT-5.2 Pro's research-grade intelligence. — from majiayu000
content
USE THIS for Claude models. Access Claude 4.5 Opus, Claude 4.5 Sonnet, Claude 4 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Haiku. No Anthropic account needed. OpenAI-compatible API. Zer
general
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main contex
general
Command-line interface for Novita AI - An OpenAI-compatible AI API client for DeepSeek, GLM, and other models.
tools
Expert skill for integrating cloud AI APIs (Claude, GPT-4, Gemini). Covers secure API key management, prompt injection prevention, rate limiting, cost optimization, and protection
security
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository. — from engineering/engineering-misc
engineering
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools ( — from ne
engineering
Scans repository structure and generates comprehensive architecture documentation including system overview, entry points, module relationships, data flow diagrams, and " — from en
engineering
Sets up and optimizes OpenAI Codex CLI + GPT-5.5 on Amazon Bedrock (GA June 2026). Handles AWS credential wiring (API key or SDK chain), region selection, VPC endpoint isolation, R
security
Budget-aware Codex routing for making Codex limits and credits last longer. Use when the user mentions Codex limits, usage, credits, budget, cheaper models, GPT-5.5 orchestration,
general
OpenAI Codex CLI orchestration for AI-assisted development using gpt-5.2-codex model. Capabilities: code generation, refactoring, automated editing, parallel task execution, sessio
tools
Codex CLI (OpenAI gpt-5.4) に直接相談するスキル。設計判断・実装方針・コードレビュー・デバッグ方針など、別モデルの視点が欲しい時に使用する。「codexに相談」「codexに聞いて」「別の視点が欲しい」「セカンドオピニオン」「codexでレビュー」「codexとペアプロ」「codexとTDD」「codexでペアプログラミング」「ペア
general
Use when the user wants to generate PNG images with OpenAI gpt-image-2 through their local Codex login, without Hermes, OpenClaw, OpenAI API keys, or the OpenAI Python SDK. Also us
engineering
Spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, and documentation via AGENTS.md persona injection (gpt
security
Reusable planner role for Codex orchestration. Use when a task needs architecture, sequencing, risk analysis, or a test plan before implementation. Default model: GPT-5.5.
engineering
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode fo
general
Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio M — from ph
general
Compare OpenAI Codex GPT-5.3 and code-searcher responses for comprehensive dual-AI code analysis. Use when you need multiple AI perspectives on code questions.
general
Scores content using Flesch-Kincaid, Gunning Fog, and SMOG readability indices via textstat Python library. Provides sentence-level rewrite suggestions using OpenAI GPT-4o API.
content
Use when configuring or debugging the context-overlay OpenAI-compatible proxy for deterministic prompt/context injection, prompt patching, rule matching, request routing, rejection
engineering
Multi-model AI council for actionable project advice. Leverages Gemini 3 Flash and GPT-5.2 skills in parallel, then synthesizes through an Opus Judge for stage-appropriate, non-ove
general
Connect to Hannah and Elena agents from Serviceplan - specialized AI coworkers for marketing research and operations planning. Access via email or OpenAI-compatible API.
growth
Manages OpenAI DALL-E 3 API workflows for brand-consistent image generation with style references, aspect ratio control, and automated prompt refinement using GPT-4 Vision feedback
growth
Generates image variations and edits using the OpenAI Images API (DALL-E 3 and gpt-image-1). Manages prompt engineering for consistent style, handles mask-based inpainting, and out
general
Detects data integrity issues including orphaned records, broken foreign key relationships, constraint violations, and provides automated fix migrations. Use for "data in — from ge
general
Defines database performance monitoring strategy with slow query detection, resource usage alerts, query execution thresholds, and automated alerting. Use for "database m — from ge
general
Deploy and serve Moonshot Kimi-K2.6 (1T MoE, INT4/Marlin, 256K context, vision) on an Ubuntu server with 8× NVIDIA RTX PRO 6000 Blackwell (sm_120) GPUs using a uv venv + SGLang, ex
engineering
Build, create, debug, review, implement, and optimize agentic AI applications using the OpenAI Agents SDK for TypeScript. Use when creating new agents, defining tools, implementing
tools
Research-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose
science
Use when you need maximum quality from a smaller/cheaper model — generates training data from a teacher model and fine-tunes a student model weights. Common scenarios - distilling
general
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT- — from mi
general
Builds repeatable evaluation systems with golden datasets, scoring rubrics, pass/fail thresholds, and regression reports. Use for "LLM evaluation", "testing AI systems", "quality a
engineering
AI inference you own, forever powering your OpenClaw agents via the Morpheus decentralized network. Stake MOR tokens, access Kimi K2.5 and 30+ models, and maintain persistent infer
security
Run python examples in auto mode with logging, rerun helpers, and background control. — from engineering/observability
engineering
Внешнее ревью PR через Node.js native скрипт (Sprint Pipeline v3.6, Mode A). Две полноразмерные модели параллельно — gpt-5.4 (reasoning) + gpt-5.3-codex (code). Fallback режимы — C
general
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions — from op
engineering
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1.2.3...<commit>) for breaking changes, regressions — from op
engineering
Image generation via flow_router OpenAI-shape /v1/images endpoint. Routes to active media providers (OpenAI, Stability, BFL, Gemini, etc.).
general
Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgen — from to
tools
Guide users through obtaining and configuring free API keys for LLM providers. Use when the user wants to set up a free LLM API, get a free API key, connect to a free model provide
general
Premium frontend design skills that override LLM defaults. Prevents generic 'AI-looking' UI. Enforces deterministic typography, calibrated color, asymmetric layouts, spring physics
science
Coordinate multiple game-development skills and produce outcome-first briefs, plans, reviews, and validation flows. Use when Codex is asked to explore the game skillset, route a br
general
Use when deciding whether to route a task to Google's Gemini Pro frontier model (current Gemini 3.1 Pro generation, moving to Gemini 3.5 Pro) instead of Claude Opus or GPT-5 — espe
engineering
在本机 Mac 或 Apple Silicon 上部署 Gemma 4 12B。本地安装/升级 llama.cpp，下载 GGUF 量化模型，用 llama-server 暴露 OpenAI-compatible API，或用 Ollama 暴露本地模型服务，按用户需求把 12B 上下文从默认 32K 提升到 64K/128K，配置 tmux 后台运行，验证
general
Use gpt-engineer when an agent/operator needs to turn a prompt file into a local project scaffold, inspect the generated code, and run a supervised improvement loop before adopting
general
Generate images, video, audio and avatars (700+ models) or call OpenAI-compatible LLMs (290+ models — Claude, GPT, Gemini, DeepSeek, Llama) through the WaveSpeedAI inference platfo
general
Access GPT-4.1 with improved capabilities. Better reasoning and longer context. No API keys needed. $2 FREE credits to start. Pay-as-you-go pricing via SkillBoss.
general
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
science
Use when deciding whether to route a task to OpenAI's GPT-5.5 frontier model versus Claude Opus or Sonnet — picking the model lane for infrastructure scripts, CI pipelines, concret
security
Migrates your agentic coding pipeline to GPT-5.5 — audits the current model config, switches the API endpoint, validates tool-call compatibility (including parallel-call race condi
general
USE THIS for GPT models, OpenAI models. Access GPT-5, GPT-5.1, GPT-5-mini, GPT-5-nano, o1, o3-mini, o4-mini, GPT-4o, GPT-4o-mini, GPT-4.1. No OpenAI account needed. Zero markup. Op
general
Use when blocked, stuck, or needing fresh perspective. Consults GPT experts via Codex CLI with graceful fallback.
general
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image
growth
Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no per-image billing. Su
general
Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction pre
security
Helps users discover prompt and image examples from a public image-prompt library when they need prompt ideas, visual references, style examples, reusable image-generation prompts,
content
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or i
content
Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sh — from ai
general
Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sh — from bg
general
生图 / 生成图片 / 画图 — 用 OpenAI gpt-image-2 生成图像。支持文生图、参考图生图 (img2img)、蒙版修补 (inpainting)。当用户要求用 GPT 画图、OpenAI 生图、gpt-image-2、文+图生图、参考图片生成、img2img、inpainting 时必加载此技能。Auth 自动继承 OPENAI_API_
general
OpenAI GPT Image 2 이미지 생성/편집 스킬. 모델은 gpt-image-2로 고정. 텍스트→이미지, 이미지 편집(마스킹), 멀티 이미지 합성, Responses API 멀티턴 편집, 스트리밍 부분 이미지를 수행. 사용 시점: OpenAI/ChatGPT 이미지 생성, AI 이미지 생성(특히 텍스트 렌더링 품질이
general
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- 10 curated styles (Spatial Glass / Tech Blue / Editorial Mono / Dark Aurora / Risograph / Wabi / Swiss G — from ni
content
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- 10 curated styles (Spatial Glass / Tech Blue / Editorial Mono / Dark Aurora / Risograph / Wabi / Swiss G — from ma
content
Send a prompt to ChatGPT Pro Extended via gpt-pro-relay on macmini — over SSH from any other machine, or directly when invoked on macmini itself. Use for "ask gpt-pro", "send to gp
tools
외부 GPT 또는 deep research 워크플로우로 넘길 구조화 프롬프트를 만듭니다. 모듈/아키텍처/이슈 단위로 맥락을 추출해 붙여넣기 가능한 리서치 요청을 만들 때 사용합니다.
science
Atua como um desenvolvedor backend sênior especialista em código limpo, arquitetura minimalista, legibilidade extrema, manutenção fácil e uso correto de linguagem, framework e banc
product
Skill SERBA BISA level SUPERMAN untuk ChatGPT — aktivasi otomatis untuk SEMUA tugas berat, kompleks, kreatif, teknis, analitis, dan multi-domain. Gunakan skill ini SETIAP KALI peng
engineering
Use when generating elite GSAP-heavy frontend pages with strict AIDA structure, wide hero typography, and gapless bento grids.
general
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6- — from Le
growth
Gpt-trainer integration. Manage Users, Roles, Goals, Pipelines, Filters, Organizations. Use when the user wants to interact with Gpt-trainer data.
general
Build, refine, and master agents using the xAI Grok API — OpenAI-compatible endpoint with grok-4.20 and grok-4-1-fast model families. Covers function calling, 2M context, multi-age
engineering
Generate images with an OpenAI-compatible image provider such as happy/gpt-image-2, with retries and bounded batch concurrency.
general
Use when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to g
general
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conver
general
Gera imagens via gpt-image-2 (OpenAI) através da FAL API. Setup conversacional do estilo a cada uso — tu fala como quer (livre, descrição em palavras, brand guide colado, ou um exe
engineering
Single-image generation skill for posters, key art, and editorial illustrations. Defaults to gpt-image-2 but is provider-agnostic — the same workflow drives Flux, Imagen, or Midjou
content
Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content, extract te
general
Azure OpenAI画像生成CLIツール (gpt-image-1.5 / gpt-5.1)。テキストから画像生成、画像のAI編集、画像の内容説明を行う。Use when the user wants to (1) generate images using Azure OpenAI, (2) edit existing images with AI,
general
Import prompts from OpenAI Playground exports — maps messages, model settings, and template variables.
general
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or — from vll
general
Proxy OpenAI-compatible model traffic so operators can inspect prompts, detect risks, and enforce budget or policy controls.
general
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT- — from mi
general
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT- — from mi
science
Kokoro-FastAPI is a Dockerized FastAPI wrapper around the Kokoro-82M text-to-speech model with OpenAI-compatible speech endpoints. It supports local TTS serving, multi-language syn
engineering
Scaffold a basic LangChain/LangGraph ReAct agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, generate, or scaffold a LangChain or LangGr
general
Works correctly with LangChain 1.0's typed content blocks on AIMessage.content — text, tool_use, image, thinking, document — across Claude, GPT-4o, and Gemini, including multi-moda
content
Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on the content-block, token-accounting, and structured-output quirks that silently break production code. U
content
Manage LangChain 1.0 prompts like code — LangSmith prompt hub versioning, XML-tag conventions for Claude, few-shot example selection, discriminated-union extraction schemas, and A/
engineering
Develop apps/openai-serve (Go). Keep OpenAI gateway behavior correct and avoid logging prompts/outputs.
general
Repository orientation and which Codex skills to use for each area (go-lcpd, protocol spec, docs, openai-serve, ExecPlans).
general
libllm - LLM API client for OpenAI-compatible endpoints. LlmApi class handles chat completions and embeddings via HTTP. Supports GitHub Models, Azure OpenAI, and standard OpenAI en
general
libutil - General utilities. countTokens and estimateTokens for GPT-style token counting. generateHash creates SHA256 hashes. generateUuid creates unique IDs findProjectRoot locate
tools
LiteLLM is an open-source Python SDK and proxy server that provides a unified OpenAI-compatible interface to call 100+ LLM APIs including OpenAI, Anthropic, Azure, Bedrock, and mor
security
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/Apple Si
general
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model. When building offline/air-gapped AI
general
Implement or refactor a reusable LLM client layer for text-only or multimodal projects. Use when a project needs one final repo-local client module, OpenAI-compatible provider supp
engineering
当需要部署或训练 LLM/VLM 时使用；覆盖 vLLM OpenAI-compatible 服务、多模态输入限制、Qwen3.5 工具调用、thinking/reasoning 控制、CUDA Graph 策略，以及 ms-swift SFT/DPO/GRPO full training、数据校验、显存排错和训练检查。
engineering
当需要通过 OpenAI-compatible LLM 网关生成图片时使用，尤其是使用 LLM_API_KEY 和 LLM_BASE_URL 调用 gpt-image-2、gpt-image-1、dall-e-3 等图像模型；覆盖环境变量检查、缺失配置提示、模型选择、/images/generations 请求、长等待时间处理、base64/URL 返回保存
content
Use this when: run a model locally, which model fits my GPU, my inference is too slow, serve LLM in production, how to quantize a model, too many concurrent users, self-host an AI,
general
Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a specific task, understand model capabilities, get pr
general
Manage local Ollama LLM models for development and testing. Use when: running local models, configuring Ollama, switching between fast/quality models, optimizing VRAM usage, troubl
engineering
Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. Use for cheap/bulk text work (summarize, classify, extract JSON, a
tools
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images. Use for self-hosted AI, offline inference, and privacy-focused AI — from mud
engineering
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images. Use for self-hosted AI, offline inference, and privacy-focused AI — from mud
engineering
Run local AI models with LocalAI. Deploy OpenAI-compatible API for LLMs, embeddings, audio, and images. Use for self-hosted AI, offline inference, and privacy-focused AI — from maj
engineering
Use when you have a specified engineering task or task list and need to decide which AI model should handle each work unit — routes tasks across Claude Opus/Sonnet/Haiku, GPT-5.4 f
general
Midjourney v8.1 (2026.03 Alpha) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Midjourney 공식 Parameter List 기반 키워드+`--파라미터` 형식으로 변환합니다. Discord `/imagine` 또는 al
general
MiniMax M-series production wiring patterns for the OpenAI-compatible API at api.minimax.io. Use when wiring MiniMax-M2.7 / MiniMax-M2.7-highspeed / Hailuo into a service (Karakeep
content
MLX LM (mlx-lm) expert — Apple Silicon LLM inference with generate/chat/server commands, Python API, OpenAI-compatible HTTP server, and model conversion/quantization via mlx-commun
engineering
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for unde — from ka
engineering
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, MiniMax, Kimi, GLM, or Cl
science
Patterns for building multimodal AI applications that combine text, images, audio, and video. Covers vision APIs, audio transcription, and unified pipelines. Use when "multimodal A
content
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for unde — from ka
engineering
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - ne
general
Use NodeTool REST API, WebSocket protocol, Chat API (OpenAI-compatible), workflow execution endpoints, and streaming responses. Use when user asks about API endpoints, WebSocket pr
engineering
Distills wiki source files into the RLM summary layer (summary.md, bullets.md, deep.md) using the cheapest available LLM CLI. Routes to Copilot gpt-5-mini first, then Claude Haiku,
general
Ollama runs large language models locally with a simple CLI and REST API. It supports hundreds of open models including Llama, Gemma, Qwen, and DeepSeek, with GPU acceleration and
general
Sets up local semantic memory search for OpenClaw using Ollama + nomic-embed-text. Use when: (1) memory_search returns 'node-llama-cpp is missing' or 'Local embeddings unavailable'
engineering
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface f
general
Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic Open Design use
growth
Wire HuggingFace embedding + reranker models (BGE-M3, BGE-Reranker-v2-m3, etc.) into Open WebUI's RAG pipeline via LiteLLM as a proxy in front of HuggingFace Text Embeddings Infere
engineering
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-co
product
Explains what Airtable is and how data is structured — bases, tables, fields, records, views, automations, and interfaces. Use when you need context about the Airtable data model.
general
Analyze meeting notes to find action items and create Jira tasks for assigned work. When an agent needs to: (1) Create Jira tasks or tickets from meeting notes, (2) Extra — from ph
general
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progre — from ph
general
Search across company knowledge bases (Confluence, Jira, internal docs) to find and explain internal concepts, processes, and technical details. When an agent needs to: (1) Find or
engineering
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a
general
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to:
general
Build and troubleshoot Box integrations for uploads, folders, folder listings, downloads and previews, shared links, collaborations, search, metadata, event-driven automations, and
general
Design App Intents, app entities, and App Shortcuts for iOS system surfaces. Use when exposing app actions or content to Shortcuts, Siri, Spotlight, widgets, or controls.
general
Build, run, and debug iOS apps on Simulator with XcodeBuildMCP. Use when launching an app, inspecting simulator UI or logs, or diagnosing runtime behavior.
general
Capture and interpret iOS Simulator ETTrace profiles. Use when profiling launch or runtime latency, comparing traces, or finding CPU-heavy stacks.
general
Capture and inspect iOS leaks and memgraphs. Use when debugging leaked objects, retain cycles, memory growth, or before/after leak evidence.
engineering
Implement and review iOS 26+ SwiftUI Liquid Glass UI. Use when adopting Liquid Glass or checking its correctness, performance, and design fit.
general
Audit SwiftUI runtime performance from code first. Use when diagnosing slow rendering, janky scrolling, expensive updates, or profiling needs.
general
Build and refactor SwiftUI UI with component patterns and examples. Use when shaping navigation, state, layouts, controls, or screen composition.
engineering
Refactor SwiftUI view files into stable, testable structure. Use when splitting large views, tightening data flow, or cleaning Observation ownership.
engineering
Bridge macOS SwiftUI into AppKit narrowly. Use when implementing representables, reaching NSWindow or panels, handling menus, or using the responder chain.
general
Build, run, and debug macOS apps with shell-first Xcode and Swift workflows. Use when launching apps or diagnosing build, startup, or runtime failures.
tools
Implement and review macOS SwiftUI Liquid Glass UI. Use when adopting system glass, removing conflicting custom chrome, or building glass surfaces.
general
Prepare macOS packaging and notarization workflows. Use when archiving apps, validating bundles, or explaining distribution-only failures.
general
Inspect macOS signing, entitlements, and Gatekeeper issues. Use when diagnosing code signing, sandbox, hardened runtime, or trust failures.
general
Build, run, and test SwiftPM macOS packages and executables. Use when the repo is package-first or has no Xcode project.
general
Build macOS SwiftUI scenes and components with desktop patterns. Use when shaping windows, commands, toolbars, settings, split views, or inspectors.
general
Add and verify lightweight macOS runtime telemetry. Use when wiring Logger events or inspecting logs for windows, sidebars, menus, and actions.
general
Triage macOS tests across Xcode and SwiftPM. Use when narrowing failures, explaining assertions or crashes, or separating setup from regressions.
engineering
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.