Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.
The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
Deploy, configure, and integrate Sandbox Agent — a universal API for orchestrating AI coding agents (Claude Code, Codex, OpenCode, Amp) in sandboxed environments. Use when setting up the sandbox-agent server locally or in cloud sandboxes (E2B, Daytona, Docker), creating and managing agent sessions via SDK or API, streaming agent events and handling human-in-the-loop interactions, building chat UIs for coding agents, or understanding the universal schema for agent responses.
Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
Use this skill when the user wants to create a new Model Context Protocol (MCP) server in Python. Also use it to expose Python functions, an API, or a database to AI clients as MCP tools. The skill makes a uv project with the MCP Python SDK v2 (MCPServer), typed tools, in-memory tests, and client configuration. Do not use it for an MCP client or for a server in another language.
Operate OKX.AI agents and marketplace workflows. Use when the user wants to register, update, or view Agent identities; discover, publish, buy, or manage Agent services(tasks), including signal services; create or fulfill marketplace services; manage or view subscriptions; view copy-trade records; review delivered work, rate agent-service orders, request or respond to an evaluation; monitor task/order execution status; send a message to a task counterpart in a task (replying is the same send); query a task's chat history by Job ID and counterpart Agent ID
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when implementing self-critique and reflection loops; building evaluator-optimizer pipelines for quality-critical generation; creating test-driven code refinement workflows; designing rubric-based or LLM-as-judge evaluation systems; adding iterative improvement to agent outputs (code, reports, analysis); or measuring and improving agent response quality.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph with parallel-step detection, adversarial review gate, and plan mutation protocol. Use when planning a large feature, refactor, or roadmap that spans multiple PRs or sessions; not for single-PR tasks or when the user says “just do it”
Build and configure AI agents inside Cargo — create an agent, choose its model and temperature, write its prompt, attach knowledge for retrieval (RAG), connect MCP tool servers, manage memories, and deploy releases. Triggers: "create an agent", "make an agent that", "give the agent our docs", "attach this knowledge base", "attach this library to the agent", "add resources to the agent release", "connect an MCP server", "expose our tools as an MCP server", "use Cargo from Claude Desktop or ChatGPT", "change the agent model", "what does the agent remember", "deploy the agent", "the agent is answering wrong". Skip when: uploading the knowledge files themselves — use cargo-content; sending the agent a message or running it over records — use cargo-orchestration.
Condense any input—an idea, brief, PRD, transcript, or mixed notes—into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says “create a spec,” “distill this into a spec,” “validate this spec,” or “update the spec.”
Make Cargo actually run something, or show what it would run — execute one connector action, run a multi-step workflow, trigger a batch across a whole segment or model, message an AI agent, build or edit a node graph, draw a workflow, tool or play as a diagram, and query the runtime tables (runs, batches, spans, records) with SQL. Triggers: "run this on all my contacts", "execute the action", "kick off a batch", "build a workflow", "schedule a play", "make it run every morning", "ask the agent", "show me the workflow", "what does this tool do", "visualize this play", "draw the graph", "explain this workflow", "how many runs failed today", "what is the output schema for this action", "add a step that". Skip when: explaining why a run misbehaved — use cargo-diagnostics; downloading result files — use cargo-analytics; committing the workflow as code — use cargo-project.
Debug complex issues using competing hypotheses, parallel investigation, evidence collection, and root cause arbitration. Use this skill to debug bugs with multiple potential causes, perform root cause analysis, or organize parallel investigation workflows.
Build a fully automated AI-powered data collection agent for any public source—job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
Router for the Cargo CLI skill bundle — load first for anything Cargo-related, and whenever a task spans two Cargo domains. Explains what each skill owns, declarative GTM as Code projects (cargo-project) vs. the imperative CLI, the UUID and slug flow between skills, async polling of runs and batches, end-to-end use cases, and gotchas that fail silently (inputs in a top-level action's `config` stripped without an error, run vs. batch, model-uuid vs. segment-uuid). Triggers: “set up Cargo,” “what can Cargo do,” “which Cargo skill,” “bootstrap my workspace,” “I have a Cargo account,” “cargo-ai …,” or any `cargo-ai` command whose domain you are unsure of. Skip when the task obviously belongs to one skill — load that skill directly.
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system simultaneously, when establishing file ownership to prevent merge conflicts in a shared codebase, when designing interface contracts so parallel implementers can build against each other's APIs before they are ready, or when deciding whether to use vertical slices versus horizontal layers for a full-stack feature.
Manage the files in a Cargo workspace — upload knowledge (PDF, CSV, text) and build native or connector-backed libraries that agents retrieve from (RAG), and use files as plain storage: write and read by path, list a folder, and share a signed or public link. Triggers: “upload this PDF,” “add these docs as knowledge,” “build a knowledge base,” “sync our help center into Cargo,” “what files are in the workspace,” “index this folder,” “attach our pricing sheet,” “store this file,” “save the report somewhere,” “give me a link to the file,” “make this file public.” Skip when wiring a file or library into an agent — use cargo-ai; when uploading a CSV that drives a batch run — that is a workspace-management file upload.
Use Link CLI's identity commands when a service requests a Link Agent Attestation Token (AAT) or signed user claims such as email. Covers acquiring and managing attestations, obtaining identity credentials, and presenting selected claims to a verifier through an HTTP client or browser automation.
Operational controls for long-lived or cloud-hosted agent systems — runtime lifecycle (start, pause, stop, restart), observability (logs, metrics, traces), least-privilege safety scopes and kill switches, and rollout/rollback change management with audit logs and success/cost metrics. Use when running production agent fleets on PM2, systemd, or containers that need monitoring, incident response, or deployment gates.
Decompose complex tasks, design dependency graphs, and coordinate multi-agent work with proper task descriptions and workload balancing. Use this skill when breaking down work for agent teams, managing task dependencies, or monitoring team progress.
Split an RFC into a multi-agent execution DAG—decompose it into work units with dependencies and acceptance tests, run research, planning, implementation, testing, and review for each unit, then merge through a queue with re-based branches and perform final system verification. Use when a feature is too large for a single agent pass, orchestrating RFC-driven multi-agent execution, or managing merge queues across agent-built units.
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.
Operate and extend NanoClaw, ECC's zero-dependency session-aware REPL, with persistent markdown-backed sessions and slash commands for model switching, skill loading, session branching, cross-session search, history compaction, and export. Use when running or extending scripts/claw.js, or when resuming, branching, compacting, searching, or exporting a NanoClaw session.
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing communication norms for a newly spawned team, when deciding whether to send a direct message or a broadcast, when a team-lead needs to review and approve an implementer's plan before work begins, when orchestrating a graceful team shutdown after all tasks are complete, or when debugging why teammates are not coordinating correctly at integration points.
Interactive picker that discovers available agent personas via the claude agents command and agents/ markdown globs, groups them into domains, has the user select up to five, dispatches them in parallel on one task, and synthesizes agreements and conflicts into a unified report. Use when composing a team of agents, browsing available agent personas, or running several specialist agents in parallel.
Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit.
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
Enforces completion discipline for substantial autonomous work by writing acceptance gates before execution, decomposing work with the Depth Tree, running approved checks, and re-verifying evidence before reporting. Use when an agent faces a long or multi-part task, work that has returned half-done, an exhaustive audit or build, parallel leaves or pipelines, or explicit triggers such as /unlazy, $unlazy, "tree N", "gates", and "do not stop until it is done".
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when checking whether agents actually follow the skills, rules, and definitions they were given, rather than assuming they do.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when the user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to set up Claude Code for a project for the first time, or wants to know which Claude Code features they should use.
Multi-agent adversarial verification: two independent reviewers using the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and a human escalation cap. Use when gating publishing, production deploys, compliance or brand-sensitive content, or hallucination-prone claims before they ship.
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.