Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Delegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like “have Antigravity do X”, “delegate this to agy”, “run it through agy”, or “use Antigravity to implement/fix/refactor” - or wants to run a queue of coding tasks through agy while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final verification table. Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes without losing correctness.
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers installed CLIs, proposes a lane map for user approval, and writes global or project config only after explicit yes. Use when the user asks to set up, configure, or reconfigure delegation lanes, a fleet of lanes, or which implementer handles feature/tests/ui work — not for dispatching a coding task to an implementer.
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
Run repeated rollouts ("Prime Gauss" style recursive prompting) while keeping an append-only decision ledger of trials, marks, coherence checks, and promotion gates, so recursive confidence never auto-approves live trading, deploy, or destructive actions. Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: the user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, a common-pitfall review, or a baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; migrates or upgrades a legacy GenAiPlannerBundle Agentforce agent (NOT an Einstein Bot) to an aiAuthoringBundle (Agent Script) agent; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; the source is an Einstein Bot (BotDefinition/BotVersion) — use agentforce-bot-upgrade; or the primary input is a production session or trace ID rather than an agent artifact.
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, verified browsers, automatic CAPTCHA solving and residential proxies — ideal for protected websites and JavaScript-heavy pages.
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scale rigor to the task, run a hypothesis loop, and log decisions. Use for /figure-it-out or "figure it out".
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins. Renders a human-readable architecture document and Mermaid invocation graph from design-time metadata (not runtime audit rows). TRIGGER when user asks to describe, diagram, inventory, audit, document, or diff (e.g. v3 vs v5) the architecture / action tree / topic structure / tool inventory of a specific agent by agent API name in a specific org. DO NOT TRIGGER for runtime session traces, conversation transcripts, generation timings, or gateway audit chains — this skill reads design-time metadata only (use agentforce-d360-analyze for session traces).
Vision-driven browser automation using Midscene. Operates from screenshots — no DOM or accessibility labels needed. Runs in headless Puppeteer — does NOT take over the user's mouse or keyboard. Also supports CDP mode and Bridge mode to connect to an existing Chrome. Use this skill when the user wants to: - Browse, navigate, or open web pages - Scrape, extract, or collect data from websites - Fill out forms, upload local files, click buttons, or interact with web elements - Verify, validate, test, or QA frontend UI behavior - Take screenshots of web pages - Automate multi-step web workflows - Test what was just built, see if it works in browser - Connect to Chrome via CDP, DevTools Protocol, or remote debugging - Connect to user's Chrome browser, control my browser, operate my Chrome Powered by Midscene.js (https://midscenejs.com)
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.
Vision-driven Android device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Control Android devices with natural language commands via ADB. Perform taps, swipes, text input, app launches, screenshots, and more. Trigger keywords: android, phone, mobile app, tap, swipe, install app, open app on phone, android device, mobile automation, adb, launch app, mobile screen, test android app, verify mobile app, QA on phone, check the app on android, test on device, see if the app works on phone, end-to-end test on android, visual verification on mobile. Powered by Midscene.js (https://midscenejs.com)
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, attach a workspace, defer capability loading, stream output, define agents from YAML, or test agent behavior.
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for “recall my work on X”, “catch me up”, “what have I been working on”, “where did I leave off”, before starting or resuming work.
Write, run, and analyze structured test suites for Agentforce agents — functional AND security. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf agent test create, run, run-eval, or results commands; asks about test coverage strategy, metric selection, or custom evaluations; interprets test results or diagnoses test failures; asks about batch testing, regression suites, or CI/CD test integration; requests security testing, OWASP LLM Top 10, red-teaming, penetration testing, prompt-injection tests, a security grade, or a vulnerability assessment of an agent. DO NOT TRIGGER when: user creates, modifies, previews, or debugs .agent files (use agentforce-generate); deploys or publishes agents; writes Agent Script code; uses sf agent preview for development iteration; analyzes production session traces (use agentforce-observe); performs a static safety review of .agent file content (use agentforce-generate Section 15).
Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries; creates, lists, updates, or deletes an AHM data alert on an agent metric (escalation rate, deflection, etc.); asks why an alert is not firing or wants to check whether alerts have fired (notification counts, or the per-alert Incidents view). DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use agentforce-generate); writes or runs test specs (use agentforce-test); uses sf agent preview for local development iteration; deploys or publishes agents.
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
Before answering any event-organizing request that opens a new project or a new session, run this router first - it maps the task onto the 72-skill samber/dev-event-organizer-skills collection, or says plainly that none fits, and bootstraps or resumes the project's shared context so the next session starts warm. This fires on a conversational state, not on a subject - invoke it at every event project start even when the collection's skills are already in daily use on another event, at every recurring check-in on the same project, and whenever routing between siblings is unclear. Covers conference, meetup and hackathon kickoffs, "which event skill do I need", "where do I start organizing this event", event organizer skill routing, and recurring event check-ins. Use this whenever someone describes an event-organizing problem without naming a skill, even if they never say "kickoff", "routing" or "start".
Generate text, have conversations, write code, reason, and call functions with Qwen models. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, or explicitly invokes this skill by name (e.g. use qianwen-text). DO NOT TRIGGER when: general coding questions without Qwen, non-Qwen AI model usage (OpenAI, Gemini, etc.), image/video understanding (use qianwen-vision), image/video/audio generation.
Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of multimodal data for real-time technical guidance and safety monitoring. Generates a custom Google Cloud solution that uses opinionated best practices and architecture guidance. Use when users need agentic assistance to design and create a multi-product solution in the cloud for live bidirectional multimodal streaming workloads. Don't use for simple text-based chat applications or workloads without real-time streaming requirements.
Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qianwen-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.
Sets up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they run. For when users want to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.
Builds an app, site, bot, or feature end-to-end from a dictated idea — requirements, briefing, spec, tickets, subagents, review, acceptance — with a live dashboard, for users who expect a finished result without reviewing specs or code. Starts only on /autopilot; a bare /autopilot resumes an interrupted run.
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled Environments, synthetic data, Verifiers, Harbor runs, calibration, or continuous benchmark maintenance.
Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates. Use when coordinating multiple agents in parallel across branches or worktrees — multi-agent fan-out, agent Kanban, squad coordination, or merging agent output into one product.
Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to scaffold a bot with create-chat-sdk, build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, set up webhook routes or multi-adapter bots, send rich cards or streamed AI responses to chat platforms, or build a custom adapter or state adapter.
Data Cloud 360° view of a single Agentforce session. TRIGGER when user asks to trace, inspect, summarize, or describe a specific Agentforce session by session id (Agent Session UUID `019d…` or MessagingSession id `0Mw…`). Also triggers on session discovery — find/list/search sessions by time, agent, channel, outcome, or conversation text — when the user has no session id yet. DO NOT TRIGGER for design-time architecture questions (use agentforce-architecture-analyze instead) or for runtime perf/latency/SLO questions that require platform telemetry beyond Data Cloud.
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices. Use when architecting multi-product solutions for agent-based data analytics or ML workloads. Don't use for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.