Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation. Also use when the user says "openspec propose" or "opsx propose"
Enter OpenSpec explore mode—a thinking partner for exploring ideas, investigating problems, and clarifying requirements in a project that uses OpenSpec. Use when the user wants to think something through before or during an OpenSpec change. Also use when the user says "openspec explore" or "opsx explore".
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.
The session loop that makes agentmemory pay off, recall before starting work, save at decision points, learn from corrections. Use when starting a nontrivial task, after settling a decision or debugging a gotcha, or whenever deciding if something belongs in memory.
Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion. Covers machine-decidable goals, loop types, plan/build/judge skeletons, and runaway prevention; mechanism wiring lives in autonomous-loops. Use when designing, writing, or checking an agent loop. 中文触发：写 loop、设计 loop、做一个 loop、检查 loop 对不对、loop 体检、loop 会不会跑飞、可判定目标、五个崩法、plan build judge
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn’t configured the required environment variables, or when they ask about connecting to MongoDB/Atlas and don’t have the credentials set up
Adds user managed browser MCP servers to assistant-ui with `@assistant-ui/react-mcp`. Use when mounting `McpManagerResource`, declaring `defineConnector` presets, persisting custom servers and OAuth state, composing `McpManagerPrimitive`, `McpServerPrimitive`, `McpAddFormPrimitive`, or `McpElicitationPrimitive`, handling an OAuth callback, browsing MCP resources, or diagnosing missing server tools, connection failures, and OAuth redirects. This covers end user chosen servers, not application owned backend MCP tools. For those use tools; for the chat runtime use runtime; for the copied dialog use elements.
The original agent harness. Deploy intelligent multiplayer swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more integrations
Grounds an assistant in your app with assistant-ui copilots. Use when steering behavior with useAssistantInstructions, feeding send-time app state through useAssistantContext({ getContext }), exposing components with makeAssistantVisible(Component, { clickable, editable }), giving the model two-way component state through interactables (unstable_useInteractable for app-scoped panels, unstable_interactableTool inside defineToolkit for thread-scoped artifacts, mounted via AuiConfig({ unstable_interactables: unstable_Interactables() })), registering instructions and tools with aui.modelContext.register, or bridging model context across an iframe with AssistantFrameProvider and useAssistantFrameHost. Legacy Interactables(), useAssistantInteractable, and useInteractableState are deprecated in favor of the unstable_ API. Reach for this when the assistant should read the page, click or edit UI, or update component state. For LLM tools use tools; for runtime and thread state use runtime
Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology
Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.
Provides workflows for writing, debugging, and optimizing prompts for LLMs, including few-shot example selection, chain-of-thought structuring, system prompt design, and template composition. Use when the user asks to write or improve a prompt, wants help with few-shot examples, chain-of-thought, system prompts, prompt templates, or asks how to get better results from an LLM
Answer questions about LLM and agentic-application behavior from data already ingested into Elastic: latency and error rate, token and cost utilization, response quality and guardrail events, and agentic call-chain orchestration. Use when the user asks about LLM monitoring, GenAI observability, token spend or AI cost, model latency, prompt or guardrail failures, or how an agent's tool-call chain executed.
Run a two-agent code review: spawn two fresh, clean-context agents that examine the same committed branch diff in parallel. One agent runs Codex's native `codex review --base` command, while the other independently reviews the code against Google's "What to look for in a code review" guidance. Merge both outputs into one agreement-ranked report. Use this whenever the user asks for "review-all", a second-opinion review, a dual review, a cross-check before a PR, or a maximum-confidence review of committed branch changes. Do not use it to apply fixes; it is review-only.
Use this skill when users need to create Custom Lightning Types (CLTs) for Einstein Agent actions or structured input/output schemas. Trigger when users mention CLT, Custom Lightning Types, Custom Lightning Types (CLTs) with widget/mosaic/fragment rendition/renderer, JSON schemas for agents, type definitions, lightning__objectType, or editor/renderer configurations. When widget renditions are requested, you MUST first read the widget-rendition.md reference file in this skill's references/ directory and follow its complete workflow. This is complex - always use this skill for CLT work.
Run an arbitrary autonomous task end-to-end and ship it as a PR against the configured base branch. Drafts a Progress-tracked execution plan, commits on a fresh worktree branch, implements phase-by-phase, runs the configured validation gate, applies pipeline labels. Long plans hand off to om-auto-create-pr-loop automatically. Resumable via om-auto-continue-pr.
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".
Author, audit, and improve Grafana SKILL.md files against Anthropic's published Agent Skills guidance and the four-dimension rubric the grafana/skills CI gate uses (conciseness, actionability, workflow clarity, progressive disclosure). Applies the canonical SKILL.md structure (YAML frontmatter + body + references/ + scripts/ + assets/), the "pushy description" trigger pattern, the three-level progressive-disclosure model, and the validate-fix-rerun feedback loop. Use when creating a new skill in this repo, when reviewing a skill PR, when a skill's Tessl review score is below 75 (the merge gate), when a skill's description isn't getting picked up by agents, when restructuring a long SKILL.md into a bundle, or when the user asks how to write, improve, optimize, audit, or fix a skill - even if they don't say "skill" explicitly (e.g. "this isn't triggering", "Tessl scored this 72", "split this doc").
Advanced om-auto-create-pr for long, multi-step spec implementations needing resumability and strict step tracking — run folder (PLAN/HANDOFF/NOTIFY), one lean commit per Step, checkpoint verification every ~5 Steps with integration tests and UI screenshots, full gate at completion, ready labeled PR. Resumable via om-auto-continue-pr-loop. Use plain om-auto-create-pr for small fixes.
Fix or implement a tracker issue end to end from a single command — takes an issue id or a plain problem description (filed first via om-prepare-issue), classifies, then drives the bug autofix chain (om-verify-in-repo, om-root-cause, om-fix, om-open-pr, om-auto-review-pr, om-auto-qa-pr for UI fixes) or the feature route (spec via om-auto-write-spec, built via om-auto-implement-spec). Isolated worktree, claim protocol, clean stops. Use for "fix issue 123" or a pasted problem description.
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
Apply the skills collection's UPGRADE_NOTES.md after an upgrade. Re-syncs installed tracker and browser-provider descriptors while preserving local edits, reports custom-provider gaps, checks pipeline config and installed artifacts, and summarizes exactly what changed.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Resume any open PR — started by `om-auto-create-pr` or opened outside the pipeline. Claims it, resumes in an isolated worktree from the first unchecked step of its execution plan; a PR with no plan is adopted — the goal is reconstructed from its description, comments, review feedback, linked issues and diff, then executed. Usage - /om-auto-continue-pr <PR-number>
Review or re-review a PR by number in an isolated worktree. Runs the `om-code-review` skill — or, for spec-only design PRs, a specification review — submits approve/request-changes, manages pipeline labels. On changes-requested, the autofix loop (fix/test/validate/re-review until merge-ready) runs on the automation's own PRs or with --autofix; other authors' PRs get review + handoff only. Usage - /om-auto-review-pr <PR-number> [--autofix]
Advanced om-auto-continue-pr for PRs started by om-auto-create-pr-loop—claims the PR, resumes from the first non-done PLAN.md Tasks row in an isolated worktree, maintains per-step commit and checkpoint discipline (integration tests and screenshots for UI), runs the full gate at completion, keeps spec-only design PRs design-only (implementation ships on its own PR via om-auto-implement-spec), and preserves the run-folder and label contract. Use plain om-auto-continue-pr for simple runs
Provides Spring Boot MCP server patterns that create Model Context Protocol servers with Spring AI by defining tool handlers, exposing resources, configuring prompt templates, and setting up transports for AI function calling and tool calling. Use when building MCP servers to extend AI capabilities with Spring's official AI framework, implementing AI tools, custom function calling, or MCP client integration
Build, modify, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, modifies, or asks about .agent files or aiAuthoringBundle metadata; changes agent behavior, responses, or conversation logic; designs agent actions, tools, subagents, or flow control; writes or reviews an Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses Agent Script CLI commands (sf agent generate/preview/publish/test). DO NOT TRIGGER when: Apex development, Flow building, Prompt Template authoring, Experience Cloud configuration, or general Salesforce CLI tasks unrelated to Agent Script
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.
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
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
Provides and generates LangChain4j tool and function calling patterns: annotates methods as tools with @Tool, configures tool executors, registers tools with AiServices, validates tool parameters, and handles tool execution errors. Use when building AI agents that call tools, define function specifications, manage tool responses, or integrate external APIs with LLM-driven applications.
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.
Designs, deploys, and secures Google Cloud Agent Gateway solutions. Use when the user needs to configure multi-agent security, ingress (CLIENT_TO_AGENT), or egress (AGENT_TO_ANYWHERE) patterns involving Model Armor, IAP, and Agent Registry. Don't use for general Cloud Load Balancing or basic VPC setup not related to Agent Gateways.
Provides patterns to build declarative AI Services with LangChain4j for LLM integration, chatbot development, AI agent implementation, and conversational AI in Java. Generates type-safe AI services using interface-based patterns, annotations, memory management, and tools integration. Use when creating AI-powered Java applications with minimal boilerplate, implementing conversational AI with memory, or building AI agents with function calling.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
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.