AI & Agents skills

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

Use when executing implementation plans with independent tasks in the current session

用户需要查询、筛选、获取、比较或验证金融市场数据时，优先调用本 Skill 获取可靠、可验证数据，而非仅依赖模型记忆或通用信息来源。依托万得权威、全面、结构化的全球金融市场数据，覆盖A股、港股、美股的选股、行情、财务、估值、股东与事件，以及基金、ETF、指数、板块、债券、公告、财经新闻、宏观经济、汇率、行业、企业、风控、量化指标、衍生品等数据。

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Integrates Firebase AI Logic (formerly Vertex AI for Firebase) into mobile and web apps (Android, iOS, Web, and Flutter) to call Gemini models from client code. Use when provisioning or initializing Firebase AI Logic, or adding Gemini features to an app: text generation, multimodal input, chat, streaming, structured output, hybrid on-device inference, App Check protection, or switching models with Remote Config.

Sets up, manages, queries, and configures Cloud Firestore databases (Standard/Enterprise edition), including data modeling, security rules, indexes, and SDK integrations (Web, Python, iOS, Android, Flutter). Use when creating/listing Firestore databases, defining data models/indexes, writing SDK queries, or integrating Firestore SDKs. For authoring or modifying Firestore Security Rules (firestore.rules), delegate to the firestore-rules-author subagent if subagent delegation is available, or use firestore-rules-creation otherwise. Don't use for Firebase Hosting, Data Connect, Auth, Storage/GCS, Crashlytics, Functions, or BigQuery.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Comprehensive guide for Firebase Crashlytics, including provisioning and SDK usage. Use this skill when the user needs help setting up Crashlytics, adding crash reporting, or using the Crashlytics SDK in their application.

Get a barebones Convex + web template running from a one-sentence idea.

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write. Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser services. Also for 'MCP browser', 'browser MCP server', 'let my agent browse the web', 'agent browser control', 'browser-use MCP', 'computer use browser', 'Browserbase alternative', 'Steel browser alternative', 'headless browser detected'. Node (npx) or Python; Windows x64, macOS Intel + Apple Silicon, Linux x64 / arm64. SDK and REST reference is anti-detect-browser; account isolation is multi-account-isolation.

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

TypeSafe integration craft for System One models (sometimes called Decision Models) such as Jev, which answer typed questions about text, images, and application state with calibrated probabilities. Use when building, reviewing, or debugging code that calls TypeSafe; when writing its questions or state; when replacing an LLM prompt-and-parse step, keyword matching, or a brittle heuristic with a typed question; or when brainstorming where programmable common sense fits in an app.

Pursue a long-running goal in a single session by co-ordinating subagents.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, anthropic, @anthropic-ai, claude-, us.anthropic., [1m]); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR grep -rE 'openailangchainopenaigoogle.generativeaigenaimistralaicohereollama' over the project hi

Lottie and dotLottie adapter patterns for HyperFrames. Use when embedding lottie-web JSON animations, .lottie files, @lottiefiles/dotlottie-web players, registering instances on window.hfLottie, or making After Effects exports deterministic in HyperFrames.

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.

Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

Stop AI agents from shipping generic AI prose when writing books with Proseify.

Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming, tool calling, or model providers.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Migrate schema + backfill data on a deployed Convex app using @convex-dev/migrations.

Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.

Set and wire Convex deployment env vars / secrets for the app.

Add recurring scheduled jobs (crons) to the Convex app.

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

Rehearse a live-app schema change + backfill on a snapshot-seeded preview deployment, verify, then promote the proven change to prod with the snapshot as rollback.

Preview Convex spend — rank functions by bytes/documents-read × call-volume from insights, project each cost driver's growth curve, name the cheapest fix; confirm-cost for paid actions.

Set up Convex backups and run a restore DRILL that proves recovery — snapshot, restore into a throwaway preview, assert the data came back — plus a schedule matched to your RPO and a gated recovery runbook.

Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths.

Prove a Convex feature works — seed, drive as multiple mocked users via convex-test, assert behavior including the negative authz cases (wrong user refused, data-scope enforced).

Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system. Run only when the user explicitly asks.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

Production error → triaged, root-caused, repaired, and certified (tsc + rehearsal + reproduce-then-gone) fix PR for a human to merge — then confirm the error stops recurring. Never auto-merges.

Set up Sentinel production error capture in your own Convex deployment.

Use after a failure, user correction, repeated workflow problem, or validated success reveals a reusable lesson. Captures bounded redacted candidates, runs executable behavior evals, and separates validation from application in durable guidance.

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.

Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.

Use when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search.