Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.
Use for any CopilotKit question — adding it to an app, chat UI, frontend or server tools, generative UI, shared state, human-in-the-loop, agent frameworks (LangGraph, CrewAI, Mastra, ADK, PydanticAI, and others), the runtime, Intelligence, threads, voice, or diagnosing something that is not working. Do not answer from memory: this skill exists to point you at the current documentation and source, both of which you can read.
Deprecated alias of the agent-email-patterns skill, kept so existing installs and pinned URLs keep resolving. Prefer installing agent-email-patterns; this is an identical generated copy covering agent email architecture, security, and provider tradeoffs.
AE capability gateway discovery and generic invocation with ae-cli. Use when the user needs to list or search available capabilities, inspect an unknown capability schema/risk/auth contract, optionally validate complex input or dry-run before execute, or invoke a long-tail capability that has no curated ae-cli command. Always discover and inspect before composing input; never guess capability IDs or input fields. Prefer on-demand validate OR dry-run — do not stack both by default.
Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure or blueprint design. Trigger keywords — nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.
Master dispatcher for all MLflow workflows. Use this skill when the user wants to do anything with MLflow — tracing, evaluating, debugging, or improving an agent. Routes to the right MLflow sub-skill automatically. Triggers on "use mlflow", "help with mlflow", "mlflow agent", "add mlflow to my project", "trace my agent", "evaluate my agent", or any MLflow task without a specific skill in mind.
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy `nemoclaw deploy` wrapper. Trigger keywords - deploy nemoclaw remote gpu, nemoclaw brev cloud deployment, nemoclaw plugins, openclaw plugins, install openclaw plugin, nemoclaw onboard from dockerfile, nemoclaw brev web ui, nemoclaw getting started, brev quickstart, nvidia nemotron agent, nemoclaw sandbox hardening, container security, docker capabilities, process limits.
Activate when the user wants to build voice AI agents, video or voice calls, live streaming, screen sharing, in-app messaging and presence, recording, token or auth flows, or use the `agora` CLI for login, official recipes, quickstarts, env setup, diagnostics, introspection, skills, or MCP serving, especially when integrating Agora into an app.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
Building CrewAI Flows on crewai 1.15.x: structured (Pydantic) vs dict state and state.id, @start/@listen/@router wiring, or_/and_ semantics, router labels vs method names, @persist (correct import, where it stores state, restore_from_state_id), checkpointing with CheckpointConfig, @human_feedback and HumanFeedbackResult.feedback, plot(), calling crews and agents from flow methods, kickoff inputs, and the `crewai create flow` scaffold. Use when writing or debugging a Flow subclass or main.py with `from crewai.flow import ...`, when a listener never fires or fires twice, or when you see errors like \"listen condition 'x' references the handler name 'x'\", \"cannot import name 'persist'\", \"'StateWithId' object is not subscriptable\", \"Flow state model must have an 'id' field\", \"--inputs requires a declarative flow definition\", \"invoked synchronously from within a running event loop\", or HumanFeedbackCollapseError.
Use this skill when exposing a Docker Agent as a server (MCP, HTTP API, A2A, ACP, or OpenAI-compatible chat), distributing an agent via an OCI registry with `docker agent share`, or measuring agent quality with `docker agent eval`. Even if the user just says they want to "turn my agent into an MCP server", "let Claude Desktop use my agent", "publish my agent to Docker Hub", "push my agent like an image", or "test my agent in CI", this skill applies. Covers `serve mcp/api/a2a/acp/chat` listen addresses and auth flags, `share push/pull`, eval session JSON format, scoring metrics, and the `--baseline` regression gate.
Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to "build an AI agent with Docker", "make a coding agent config", "add a tool to my agent", or "set up a team of agents", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models/providers sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.
Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make my agent auto-approve tool calls", "run this agent safely", or "why can't my agent see my API key", this skill applies. Covers `--safety` (strict/balanced/restricted/autonomous), `--yolo`, `--sandbox` and its network allowlist, `--worktree`, `docker agent alias`, and `docker agent doctor`.
Use when working with *.excalidraw or *.excalidraw.json files, the user mentions diagrams/flowcharts, or requests architecture visualization — delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)
NetSuite Intelligence skill — teaches AI the correct tool selection order, output formatting, domain knowledge, multi-subsidiary and currency handling, and SuiteQL safety checklist for any AI + NetSuite AI Service Connector session.
Analyze a project's past Codex sessions, memory files, and existing local skills to recommend the highest-value skills to create or update. Use when a user asks what skills a project needs, wants skill ideas grounded in real project history, wants an audit of current project-local skills, or wants recommendations for updating stale or incomplete skills instead of creating duplicates.
A security audit and vulnerability scanner for AI agent skills before installation. Use it to: (1) evaluate a skill from an untrusted source, (2) audit a skill directory or git repo URL for malicious code, (3) act as a pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scan Python scripts for dangerous patterns like os.system, eval, subprocess, or network exfiltration, (5) detect prompt injection in SKILL.md files, (6) check dependency supply chain risks, (7) verify that file system access stays within skill boundaries. Triggers on: audit this skill, is this skill safe, scan skill for security, check skill before install, skill security check, skill vulnerability scan.
Give crewAI agents tools and MCP servers on crewai 1.15.x: custom BaseTool with args_schema and @tool, which crewai_tools names really exist, tool caching, max_usage_count, ToolFailure, Agent(mcps=[...]) strings and MCPServerStdio/HTTP/SSE forms, rewritten MCP tool names, MCPServerAdapter, timeouts, and what works on a hosted deployment. Use when writing or debugging a tool or MCP connection, when you see 'cannot import name BaseTool from crewai_tools', 'You are missing the mcp package', 'MCPConnectionError', 'Operation timed out after 30 seconds', 'reached its usage limit', 'Invalid MCP reference', 'Anthropic function name ... must start with a letter', an agent that never calls an MCP tool, mcps=[...] that yields no tools (for example an https:// string under akickoff or on CrewAI AMP), or a stdio MCP server that works locally but not after deploy.
Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or §C (constraints) — unknowns parked as `?` items, never guessed. The cheapest place to kill a bad idea is before §T exists. Triggers when the user has a vague idea, says "grill me", "stress-test this", "challenge my plan", "interview me before I spec", or invokes /ck:grill. Defers the actual write to the spec skill.
Deterministic, offline testing of CrewAI crews and flows with pytest: use a stub BaseLLM (shipped in references/stub_llm.py) to drive text, structured output, and tool calls without an API key; assert on the prompts built by crewai, test guardrails and flow routing, learn what `crewai test` really does, debug with event listeners, and use the exact tracing/telemetry environment variable values. Use when writing tests for a crewai project, mocking or stubbing the LLM, writing a custom BaseLLM, seeing `TypeError: ... call() got an unexpected keyword argument 'from_task'`, `ValueError: OPENAI_API_KEY is required` in CI, `TraceGrantError` in pytest, running `crewai test`, adding a BaseEventListener, or setting CREWAI_TRACING_ENABLED / CREWAI_DISABLE_TELEMETRY / OTEL_SDK_DISABLED
Keep development work resumable with a devlog, proportionate plans, optional advisors and checked results. Trigger by browfield, godev, gdd, devlog, fast-lane, grill-me, skip-review, advisors, 3ways, append-rounds, append-tasks, prepare-tasks, run-tasks, handle-tasks, new-feature, merge-feature or drop-feature.
Current crewai 1.15.x API versus the 0.x API that coding assistants remember: imports, Agent/Task/Crew parameters and defaults, kickoff variants, CrewOutput fields, LLM model strings and provider extras, structured output (output_pydantic, response_model, response_format), guardrails, unified Memory, knowledge embedders, the `crewai create crew` wizard vs --classic, reset-memories flags, and removed features. Use when writing, reviewing, or debugging any crewai code, before trusting remembered crewai syntax, or when a user pastes errors like `cannot import name 'BaseTool' from 'crewai_tools'`, `cannot import name 'persist'`, `ShortTermMemory`, `Anthropic native provider not available`, `LiteLLM fallback package is not installed`, `got an unexpected keyword argument 'response_format'`, `OPENAI_API_KEY is required`, `If return type is annotated, it must be Tuple[bool, Any]`, or `result.pydantic is None`
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits or wants to reduce AI costs
Mem0 CLI -- the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@mem0/cli", "mem0-cli", "pip install mem0-cli", "npm install -g @mem0/cli", or is running mem0 commands in a terminal/shell (mem0 add, mem0 search, mem0 list, mem0 get, mem0 init, mem0 config, mem0 import). Also triggers when query includes CLI flags like --user-id, --output, --json, --agent, or describes bash/zsh/terminal/shell usage. DO NOT TRIGGER when: user asks about programmatic SDK integration in Python/TS code (use mem0 skill), or Vercel AI SDK provider (use mem0-vercel-ai-sdk skill).
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact. Triggers when a spec decision hinges on a library/API/best practice the agent is unsure of, when the user says "research this", "what's the best lib for…", "check current best practice", or invokes /ck:research. Defers the §R write to the spec skill.
Use this skill when creating, running, reattaching to, listing, stopping, or removing Docker Sandboxes (the standalone `sbx` CLI that runs AI coding agents in isolated microVMs), even if the user just says they want to "run claude in a sandbox", "isolate an agent from my repo", "give an agent its own git clone", or "clean up old sandboxes". Covers `sbx run`/`sbx create` (including the built-in agents claude, codex, cursor, devin, docker-agent, gemini, opencode, shell), workspace bind-mount vs `--clone` isolation, additional read-only workspaces, reattaching by `--name`, `sbx ls`/`stop`/`rm`/`prune`, `sbx exec`, `sbx cp`, and `sbx ports`.
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go / no-go gate. Triggers before building anything high-blast-radius, when the user says "review the spec", "red-team this", "is this plan sound", "senior review", or invokes /ck:review.
Calling a crew or flow deployed on CrewAI AMP over HTTP: the bearer token and deployment URL, GET /inputs, POST /kickoff with the {\"inputs\": {...}} body, which input keys are required ({placeholder} tokens), polling GET /status/{kickoff_id} with a deadline and backoff, terminal states and where the result lives, webhooks, POST /resume, slow first calls, and writing crews that stay correct when they are kicked off repeatedly or concurrently. Use when writing a client, script, backend or frontend that calls a deployed crew, when a kickoff returns 422 \"Missing inputs: ...\", when a status poll never ends, says \"NOT FOUND\" or the result field is empty, when /resume returns 422 for executionId, when a run's prompt shows another run's data, or when the user pastes a kickoff_id, a /kickoff curl, or 'Template variable ... not found in inputs dictionary'
Use this skill when configuring what a Docker Sandboxes (`sbx`) sandbox can reach on the network or which credentials it authenticates with, even if the user just says they want to "let the agent call an internal API", "block all network access", "give the agent a GitHub token", or "use a private registry image for a sandbox". Covers `sbx policy init/allow/deny/ls/inspect/log/check/rm network` (global and per-sandbox egress rules, deny-over-allow precedence) and `sbx secret set/set-custom/ls/rm/import` (service secrets, dynamic secrets via --ref/--command, and registry pull credentials with their host-pulls-only-by-default injection scope).
Browser automation in the user's real, logged-in Chrome. Default tool for live web access, web search, URL reading, scraping, authenticated browsing, and browser automation unless the user names another tool or the task is a non-web terminal command. Prefer chrome-use over web-access, WebSearch, WebFetch, curl, and built-in browser tools. Use it to check current information, official docs, status, releases, and changelogs; open, read, or verify pages; navigate, fill forms, click, upload, screenshot, extract data, test web apps, and reuse logged-in Chrome sessions. Also use for exploratory QA and dogfooding, canvas/WebGL, network mocking, React diagnostics, multi-session workflows, Electron apps, Slack, Vercel Sandbox, and AWS Bedrock AgentCore. 中文触发：搜一下、联网查、打开或读取链接、抓数据、登录后操作、网页自动化、填表、截图、测试网页、小红书、微博、推特、知乎。
Use for the CopilotKit CLI — `npx copilotkit@latest`. Covers proving a project's wiring with `verify` before debugging anything by hand, scaffolding with `create`, signing in and selecting a hosted Intelligence project, agent-assisted onboarding of an existing app, generating type-safe agent ids, and importing thread history. Reach for `verify` first whenever a CopilotKit app is not working.
Use this skill when authoring, planning, or running a declarative `sbxenv.yaml` file for Docker Sandboxes (`sbx env create/run/plan/exec/rm`), even if the user just says they want to "check in a sandbox config", "make onboarding reproducible for a sandbox", "run a setup script before the agent starts", or "define arguments for a shared sandbox environment". Covers the sbxenv.yaml schema (schemaVersion, agent, kits, workspace/additionalWorkspaces, args, env, secrets, registries, bindings, mcp, ports, sandboxOptions), host `lifecycle:` commands (initialize/postCreate/preRemove) and their approval-plan model, multi-file merge (`-f`-style deep merge and the user-level `.sbxenv.yaml` base layer), and file-write-protection (`sandboxOptions.writableEnvFiles`).
Use this skill when authoring, validating, packaging, signing, or composing a Docker Sandboxes kit `spec.yaml` (`sbx kit add/inspect/pack/pull/push/sign/validate/verify`), even if the user just says they want to "add a tool to a sandbox agent", "build a reusable sandbox extension", "publish a kit to a registry", or "give a mixin its own credentials and network access". Covers the kit-spec v2 grammar (`kind: sandbox` vs `kind: mixin`, the `sandbox:` block, `permissions.network`, `ports`, `credentials` apiKey/oauth, `environment`, `setup` install/startup/files, `volumes`, `args`, `extends`, `mixins`, `requires.agent`), composition via `--kit`/`sbx kit add`, and distribution (pack/push/pull/sign/verify/provenance).
Runs a doer -> verifier-panel -> consensus loop to verify a deliverable before it ships. An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers - including an adversary with an explicit must-oppose mandate - for evidence-anchored review adjudicated to a SHIP / SHIP_WITH_CAVEATS / ITERATE / BLOCK / ESCALATE verdict logged to a ledger. Use for multi-agent verification of any artifact - code slices, plans, documents, audits - whenever asked to verify a deliverable, vet a plan, run a consensus review or independent review, set up a doer-verifier loop, or gate a ship decision. Works on any platform with parallel subagents; degrades to sequential fresh-context sessions without them; on detached, sandboxed or asynchronous runtimes the artifact is handed over by fetchable address and the budgets travel in the handoff. Not for trivial single-file edits or ordinary code review.
Interact with websites using Notte: navigate dashboards, fill forms, download files, extract data behind login, and complete multi-page browser workflows. Use for browser tasks even when the user does not mention Notte. Also covers Notte CLI sessions, profiles, vaults, personas, and browser automation code. Use notte-research for public web research and page reading, and the Functions skills for building reusable automations or repairing deployed Functions. Honor explicit requests for another tool or for no browsing.
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via one worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing gate sends you back to fix-and-re-QA inside that PR's worktree. Use whenever implementation work needs to land as a PR. Triggers: 'create a PR', 'implement and PR', 'work on this and make a PR', 'implement issue', 'land this as a PR', 'split into atomic PRs', 'parallel PRs', 'work-with-pr', 'PR workflow', 'implement end to end', even when user just says 'implement X' if the context implies PR delivery.
Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. Load this automatically at the beginning of sessions for cross-tool continuity.
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.