Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. Applies the RED-GREEN-REFACTOR cycle to process documentation by running a baseline without the skill, writing to address failures, and iterating to close loopholes.
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how much thinking is enough.
Orchestrator for setting up Agentforce in Salesforce Service Cloud ITSM: Agentforce Studio enablement, the IT Service Fulfiller agent, the IT Service Employee agent, specialized employee agents, and human escalation. Use when the user asks to set up Agentforce for ITSM, enable Studio and the Fulfiller/Employee agents together, configure employee-agent escalation, wants a guided Agentforce ITSM walkthrough, or asks what Agentforce features are available for IT Service. Presents available Agentforce capabilities and delegates each selection to a specialized child skill while tracking progress. Triggers on: set up agentforce for itsm, configure agentforce studio and fulfiller, agentforce itsm walkthrough, what agentforce features for it service. DO NOT TRIGGER when: the user asks to enable Agentforce Studio alone, asks to create or activate the Fulfiller or Employee agent alone, asks to configure escalation alone, or asks about CMDB, Incident Management, Teams, or general ITSM setup without Agentforce intent.
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing.
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Optimize LLM prompt caching hit rate to reduce API costs and improve latency. Analyzes prompt structure, identifies cacheable vs non-cacheable content, and recommends restructuring to maximize cache reuse. TRIGGER when: user says "prompt cache", "cache hit rate", "reduce LLM cost", "optimize token usage", "cheaper LLM calls", or asks about prompt caching strategies for OpenAI/Anthropic/other providers. DO NOT TRIGGER when: user just wants to optimize a single prompt's quality (use prompt-optimizer instead), or asks about general caching infrastructure.
Best practices for using agent-browser with Kernel cloud browsers. Use when automating websites with agent-browser -p kernel, tuning stealth or proxy behavior, persisting profiles, handling iframes, discovering Kernel session IDs or live views, or cleaning up cloud sessions.
Create and activate an IT Service Employee agent as a Next-Gen Authoring (NGA) native agent from an ITSM Employee agent template's Agent Script, via the Salesforce CLI (sf): read the template, check idempotency, create the NGA bundle then publish and activate, verify live. Defaults to the broad IT Service Employee template; when the user names a specialized Employee template (Password Manager Assistance, Certificate Management, Onboarding, Hardware Request, and ~47 others catalogued in references/specialized-templates.md — all under the `svc_emp_intelligence__` namespace), pins that one instead. Idempotent per developer name. TRIGGER when the user asks to create/set up/provision/activate the Employee agent, the IT Service Employee agent, or a specialized Employee agent (password manager, certificate, onboarding, hardware request, etc.). DO NOT TRIGGER: prerequisite checks (service-itsm-agentic-setup-agentforce-studio-validate), CMDB CRUD, Fulfiller setup (service-itsm-agentic-setup-fulfiller-agent-configure).
Archive session learnings, debugging solutions, and deployment logs to .archive/yyyy-mm-dd/ as indexed markdown with searchable tags. Use when completing a significant task, resolving a tricky bug, deploying, or when the user says "archive this". Maintains .archive/MEMORY.md index for cross-session knowledge reuse.
Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement. Use when one reviewer isn't enough because the failure modes are heterogeneous, or a claim looks strong to its author and needs cross-lens pressure before it ships.
Create and activate the IT Service Fulfiller agent as a Next-Gen Authoring (NGA) native agent from the shipped ITSM Fulfiller template's Agent Script, using the Salesforce CLI (sf): read the template, check idempotency, create the NGA bundle, publish and activate it, then verify it is live. Idempotent per developer name. The Fulfiller agent is the IT-technician-facing assistant for incident triage, case summarization, field updates, and related-record automations. Use when asked to create the Fulfiller agent, set up the IT Service Fulfiller agent, provision the fulfiller assistant, or activate the Fulfiller agent. Triggers: create fulfiller agent, set up fulfiller agent, provision fulfiller agent, activate fulfiller agent. DO NOT TRIGGER: checking org prerequisites (service-itsm-agentic-setup-agentforce-studio-validate), or CMDB CRUD.
Turn a visual or interaction technique you already built into a reusable web-design skill, by isolating the one mechanism that makes it work while reproducing its approved reference exactly around that focus, and packaging it with a demo that proves both the mechanism and the visual fidelity. Covers finding the mechanism, naming the technique plainly, disclosing the verified runtime and renderer, auditing reference layers, carrying real numbers instead of adjectives, preserving owned staging, keeping expensive gotchas, declaring the boundary against neighbouring skills, and browser-verifying before claiming it works. Use when a page, canvas scene, shader, scroll effect, layout system, or hover interaction turned out well and should become a skill rather than staying in one project
Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns, quality gates, and next-cycle vocabulary. Use after a build, QA pass, demo, user complaint, or abandoned attempt when the useful output is what the next pass must learn rather than the code itself.
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when the user says “make a plan”, “create a plan”, “plan this out”, “plan the implementation”, “help me plan”, “design a plan”, “draft a plan”, “write a plan”, “outline the steps”, “break this down into tasks”, “what's the plan for”, or makes a similar planning request. Also triggers on explicit “/planner” or “/plan” commands.
When data arrives with a minimal request—files, a repo, a paste, or a chat scrollback—read it and propose what the user is trying to do with it, as a proposal to confirm rather than a question to answer. Use when material arrives without a fully formed request, or when the request seems less specific than the data suggests.
Run repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.
Let this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays on the cloud; set this workspace up to make images on my own machine — even when the user asks for no image or file in the same breath. Also use it for a single request the user wants done locally, offline, on-device, or kept private: transcribe this recording, make this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any agent harness. Use it when the user wants to cut cost or tokens on image, audio, or voice API calls, or drop DALL-E, hosted Whisper, ElevenLabs, or other paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo, kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source code; do not use it if the user is adding local AI to an app they ship.
Enable the Agentforce for IT Service Salesforce Go feature toggles (Agentforce Studio, Einstein Generative AI, the parent umbrella, and the Fulfiller/Employee agent templates) using the Salesforce CLI (sf). Turns ON org prefs via the Setup Discovery feature/{apiName}/enable Connect API route. Write-capable, idempotent, dependency-ordered, confirm-to-write required. Use when asked to enable Agentforce Studio, turn on Agentforce for IT Service, enable Einstein generative AI, or configure the org-level Agentforce for IT Service prerequisites. Triggers: enable agentforce studio, turn on agentforce for it service, enable einstein generative ai, configure agentforce org prefs. DO NOT TRIGGER: read-only prerequisite check (service-itsm-agentic-setup-agentforce-studio-validate), create/activate an agent (service-itsm-agentic-setup-fulfiller-agent-configure), or assigning permission sets.
Drive Blender from natural language. Converts plain-English requests ("model a sword and render it with cinematic lighting", "make this glass look frosted", "set up three-point lighting", "export this scene as glTF for the web") into Blender Python code executed via the Blender MCP server. Acts as the orchestrator that picks and chain-loads specialised sub-skills (blender-modeling, blender-materials, blender-lighting, blender-cameras, blender-rendering, blender-animation, blender-export, wireframe-to-3d, blender-pro-workflow, blender-skill-harmonizer, quality-refinement-autoloop). Use this skill whenever the user wants Claude to do anything in Blender, including creating geometry, applying materials, lighting a scene, framing a camera, rendering, animating, or exporting. Make sure to invoke this skill even if the user does not say "Blender" — also covers requests like "create a 3D model of...", "render this...", "make a glTF from...", "set up a scene with...", or any 3D-creation task. Requires the Blender MCP addon (ahujasid/blender-mcp) running on port 9876.
Unified automation entry point. Covers browser automation (Playwright) and Windows desktop app automation (OpenReverse). Browser scenarios: open web pages, click, fill forms, scrape, take screenshots, automate logins, and interact with pages. Desktop scenarios: operate GUI tools such as IDA/x64dbg, Windows UI Automation, vision-driven interaction, and desktop app network packet capture. Trigger keywords: browser automation, desktop automation, open web pages, fill forms, scrape, screenshots, automated login, Playwright, agent-browser, headless, OpenReverse, UIA, CUA, desktop operations, Windows automation.
AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: you need to store successful patterns, search for similar solutions, semantically look up past work, learn from previous tasks, share knowledge between agents, or build a knowledge base. Skip when: no learning is needed, tasks are ephemeral and one-off, external data sources are available, or exploration is read-only.
Validate Agentforce for IT Service prerequisites for a Fulfiller or Employee agent using the Salesforce CLI (sf). This read-only prerequisite check reads the Salesforce Go feature toggles behind the Agentforce for IT Service setup page (Agentforce Studio, the IT Service Fulfiller Template / IT Service Employee Template, Specialized Agent Templates for Employee) via one Connect API call, then a helper script classifies the chosen path as READY / NOT-READY. It never enables anything; when a toggle is off, it hands off to agentforce-studio-configure to enable it. Use when asked to check Agentforce prerequisites, validate that the org is ready for an ITSM agent, or verify that Agentforce Studio is enabled. Triggers: check agentforce prerequisites, validate agentforce readiness, is my org ready for the fulfiller agent, verify agentforce studio enabled. DO NOT TRIGGER for enabling or turning on toggles, creating the fulfiller agent (service-itsm-agentic-setup-fulfiller-agent-configure), or CMDB CRUD.
Build AI agents with structured access to Sanity content via Sanity Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers MCP endpoint setup in the Context app (GROQ mode over a dataset, or Knowledge Base mode), agent implementation, Insights, and advanced patterns. Always use this skill when users mention building a chatbot with Sanity, creating an AI assistant for their content, setting up the Sanity Context MCP server, integrating Sanity with Claude/GPT/any LLM, making content searchable by AI, implementing semantic search over Sanity data, or connecting their CMS to an AI agent.
Uses persistent markdown files for general planning, progress tracking, and knowledge storage (Manus-style workflow). Use for multi-step tasks, research projects, or general organization WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
Resolve missing ITSM Intelligence invocable actions so a Fulfiller NGA agent can activate. Reads which of the three Core Fulfiller persona permsets (IncidentFulfiller, ProblemFulfillerPermSet, ChangeRequestFulfillerPermSet) are provisioned, then assigns the running user the selected persona (plus backing PSL when license-gated) so svc_itsm_intelligence__* actions surface; hands off to service-itsm-agentic-setup-agentforce-studio-validate if none are provisioned. Use when the Fulfiller agent-configure skill reports missing actions on activate, when 'Invocable action svc_itsm_intelligence__X does not exist' surfaces, when a user asks to grant themselves Fulfiller prompt-template access, when asked to assign the Incident, Problem, or Change Fulfiller persona permission set, or when resolving missing ITSM Intelligence action access for the Fulfiller agent. DO NOT TRIGGER for Employee-agent access, Agentforce for IT Service toggles, agent creation, CMDB access, or generic permset assignment.
In-depth persona design for Agentforce agents with 50-point scoring. Trigger when the user designs agent personas, defines agent personality or identity, creates persona documents, encodes a persona into Agentforce Builder fields or Agent Script, translates brand guidelines into an agent voice, or asks about agent tone, voice, or register. Do not trigger when building agent metadata (use sf-ai-agentforce), testing agents (use sf-ai-agentforce-testing), or working with Agent Script DSL (use sf-ai-agentscript).
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.
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.