Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
When the user wants to build or improve an automated sales bot's ability to recognize prospect intent—whether they're interested, objecting, asking questions, or ready to buy. Also use when the user mentions "detecting intent," "classifying responses," "understanding prospect replies," "bot understanding," or "NLP for sales."
When the user wants to build or improve a sales bot's ability to detect prospect language and respond appropriately or route to the right team. Also use when the user mentions "language detection," "multilingual," "non-English," "translation," "language routing," or "international prospects."
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when the user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks
When the user wants to build or improve a sales bot's ability to rate conversation quality. Also use when the user mentions "conversation scoring," "quality scoring," "exchange rating," "conversation metrics," or "performance scoring."
One-time project initializer for Inertia Rails skills. Detects the stack and frontend framework (React/Vue/Svelte) from Gemfile and package.json, offers to install recommended dependencies (alba-inertia, js-routes, pagy, shadcn), and generates a CLAUDE.md section configuring which skill patterns apply. Use when first installing these skills, bootstrapping a new Inertia Rails project, or when the stack changes.
When the user wants to build or improve a sales bot's ability to respect prospect time zones for outreach. Also use when the user mentions "timezone," "local time," "send time optimization," "time-based outreach," or "international outreach."
Build and deploy AI agents with Cloudbase Agent (TypeScript), a TypeScript SDK implementing the AG-UI protocol. Use when: (1) deploying agent servers with @cloudbase/agent-server, (2) using LangGraph adapter with ClientStateAnnotation, (3) using LangChain adapter with clientTools(), (4) building custom adapters that implement AbstractAgent, (5) understanding AG-UI protocol events, (6) building web UI clients with @ag-ui/client, (7) building WeChat Mini Program UIs with @cloudbase/agent-ui-miniprogram.
Use when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts, approval gates, loops), authoring editor_info, publishing, unpublishing or renaming, importing an exported workflow JSON, migrating a graph built in Weavy, ComfyUI, or another node tool, copying a workflow, or turning a prompt chain into an app. Running or pricing a workflow is scenario-workflows. Keywords: node graph, editor_info, CEL.
Use when the user wants to build or improve a sales bot's ability to identify decision-makers versus gatekeepers. Also use when the user mentions “decision maker,” “buyer identification,” “gatekeeper detection,” “authority detection,” or “economic buyer.”
Create a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X", or build a new sentry-<platform>-sdk skill bundle with wizard flow and feature reference files.
Writes turn-level tests for a LiveKit agent in the user's normal test suite: pytest (Python) or Vitest (Node.js). Use when the user asks to "write tests for my agent", "add a test for this tool", "test the handoff", "pin this bug", "why does my agent test fail", or after building or changing agent behavior that needs regression coverage. Covers the SDK's test session harness, assertions on messages, tool calls and handoffs, LLM judging of a reply against an intent, mocking tools, multi-turn tests, and judging whole conversations with the built-in judges. For interactive poking use debugging-livekit-agents. For grading whole conversations at scale use running-livekit-simulations.
Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example, “get it to 8 out of 10” or “bring everything under 6 up to 6+”). Covers anchored rubrics, measurable criteria, independent or blind judging, before/after scorecards, and honest reporting of anything still short. Use whenever the user asks to score, rate, grade, or judge something out of 10, names a target score, or asks “what would make this a 9?”
Analyze Claude Code and Claude Desktop Code token usage, cost, quota burn, model mix, cache read/write, and 5-hour block consumption using ccusage evidence. Use when the user asks why Claude quota was exhausted, whether a model such as fable/opus/sonnet is unusually expensive, how many tokens were spent today or historically, or needs a human-friendly explanation of local Claude Code CLI/Desktop usage.
Manage scheduled tasks using the openclaw cron CLI. Trigger when the user needs recurring reminders, scheduled tasks, background checks, or scheduled agent tasks. Keywords: schedule, daily/weekly/hourly/every minute/every second, reminder, schedule, remind, every, cron, scheduled task, run later, delayed execution, reservation, plan, alarm, countdown, in X minutes, in X seconds, at what time
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
When the user wants to build or improve a sales bot's ability to generate personalized scripts on the fly. Also use when the user mentions "dynamic scripts," "script generation," "personalized messaging," "adaptive scripts," or "real-time content generation."
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and set up scheduled reports on an evaluation. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, inspect sentiment classifications, or manage the evaluation lifecycle.
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with a plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
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.