Loading...
Loading...
Found 500 Skills
Build, scaffold, extend, deploy, and troubleshoot event-driven AI agents and scheduled serverless agent apps on Azure Functions using azurefunctions-agents-runtime. Use when the user wants a scheduled agent, morning briefing, daily digest, timer agent, inbox summary, email or Teams briefing, background AI workflow, connector-triggered agent, event-driven AI automation, HTTP/chat agent, webhook-style agent, or Azure Functions hosted agent. Covers .agent.md, agents.config.yaml, Foundry gpt-4.1/gpt-5.x model choice, dynamic sessions for code execution and web browsing, built-in chat/API/MCP endpoints, remote MCP servers, Connector Namespaces, Office 365 or Teams MCP tools/triggers, custom Python tools, Agent Skills, azd deployment, local.settings.json, Application Insights, local development, and troubleshooting.
スキルを作成・更新・プロンプト改善するためのメタスキル。 **collaborative**モードでユーザーと対話しながら共創し、 抽象的なアイデアから具体的な実装まで柔軟に対応する。 **orchestrate**モードでタスクの実行エンジン（Claude Code / Codex / 連携）を選択。 Anchors: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: 戦略的設計・ユビキタス言語・Bounded Context / 目的: ドメイン構造の明確化 • Clean Architecture (Robert C. Martin) / 適用: 依存関係ルール・層分離設計 / 目的: 変更に強い高精度スキル • Design Thinking (IDEO) / 適用: ユーザー中心設計 / 目的: 共感と共創 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt, Codexに任せて, assign codex, Codexで実行, GPTに依頼, 実行モード選択, どのAIを使う, IPC Bridge統一, API統一パターン, safeInvoke/safeOn, Preload API標準化, IPC handler registration, Preload API integration, contextBridge, Electron IPC pattern
Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs.
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
Upgrade a coded website to award-tier, editorially-crafted design using fal.ai. Takes a local HTML file or a dev-server URL, screenshots it, has an opus-4.7 vision model write a gpt-image-2 edit prompt, uses fal-ai/gpt-image-2/edit to produce the redesigned reference image, then opus-4.7 vision writes a Markdown build-spec with a "Hard constraints" section + a tokens.json. Also supports iterate (screenshot implemented site → delta-spec vs reference) and greenfield generate (brief → mockup → single-file HTML). Invoke when the user says "improve the design", "make it world-class", "redesign this landing page", "upgrade this site", "design pass", or points at a local HTML / dev server for a visual review.
Generate, revise, translate, and manage App Store / Google Play marketing screenshots. Full flow: initialize a .shots workspace, scrape App Store metadata, research the product from the repo and listing, identify theme, colors, audience, and competitor space, save a strategy brief, craft benefit-driven headlines, and generate 3-up GPT-Image 2 composites via OpenAI direct or fal.ai before cropping them into upload-ready panels. Supports iPhone, iPad, and Android Phone platforms. Triggers: "app store screenshots", "marketing screenshots", "store listing images", "screenshot generation", "app store assets", "google play screenshots", "shots", ".shots", "revise shots", "change screenshots", "fix panels", "redo screenshots", "translate screenshots", "localize", "scrape app store", "fetch metadata", "import app store". Do NOT use for general image generation, social media graphics, or non-store marketing assets.
Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include "read this aloud", "generate voice for ...", "create a narration of ...", "tts this", "把这段念出来", "做个配音", "合成语音", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.
Desktop automation CLI for AI agents (macOS, Linux, Windows). Screenshot, click, type, scroll, drag with native Zig backend. Use this skill when automating desktop apps with computer use models (GPT-5.4, Claude). Covers the screenshot-action feedback loop, coord-map workflow, window-scoped screenshots, and system prompts for accurate clicking.
Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (GPT-5/o3) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'second opinion on this code', 'independent code review', 'what does codex think', 'get codex to review'.
Write a high-quality prompt for any LLM or AI assistant — Claude, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Copilot, or any coding / chat agent. Use this skill whenever the user asks to write, improve, refine, shorten, or rewrite a prompt; asks "how should I phrase this for [model]" or "what's a good prompt for [task]"; describes a task they want an AI to do but hasn't yet formulated it as a prompt; or pastes an existing prompt and asks for revision. Based on Boris's (Anthropic, Claude Code creator) prompt methodology — short and accurate prompts, plan-before-code, feedback loops, persistent context in files. The universal principles (short, plan-first, feedback-loop, no-padding) apply to any LLM; the Claude-Code-specific anchors (CLAUDE.md, @file, slash commands) only apply when the target is Claude Code. If the user's intent is unclear (target model, deliverable, scope, or whether the AI has a way to self-verify is missing), ask 1–3 targeted clarifying questions via AskUserQuestion before writing the prompt.
Multi-model deep review of the Ralph bd graph and plan via three parallel opencode processes (claude opus, gemini, gpt). Use for high-stakes runs where cross-model consensus reduces single-model bias.
Generative Engine Optimization (GEO) — make content rank in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Audits existing content, rewrites for AI citation, and produces per-engine strategy. Use when asked to "optimize for AI search", "rank in ChatGPT", "GEO audit", "improve AI citations", "rank in Perplexity", "AI Overview optimization", "AI Overview ranking", "LLM SEO", "answer engine optimization", "AEO", "get cited by AI", "GEO", "generative engine optimization", "show up in ChatGPT", "appear in AI answers", "be cited by Perplexity", "SGE optimization", "Search Generative Experience", or "make my content show up in AI answers". Distinct from regular SEO — this targets generative engines, not traditional Google rankings.