Skill rating

Build serverless applications with Cloudflare D1 — SQLite at the edge. Use when someone asks to "serverless database", "Cloudflare D1", "SQLite at the edge", "database for Workers", "edge database", o

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch p

Collect user feedback and run in-app surveys with Formbricks — open-source experience management platform. Use when someone asks to "add surveys to my app", "Formbricks", "in-app feedback", "NPS surve

Use Tailwind CSS in React Native with NativeWind — write className instead of StyleSheet. Use when someone asks to "use Tailwind in React Native", "NativeWind", "style React Native with Tailwind", "cl

Test and evaluate LLM prompts systematically with Promptfoo — open-source eval framework. Use when someone asks to "test my prompts", "evaluate LLM output", "Promptfoo", "prompt regression testing", "

Store and search vector embeddings in PostgreSQL with pgvector — no separate vector database needed. Use when someone asks to "vector search in Postgres", "store embeddings", "pgvector", "similarity s

Set up, configure, and manage PicoClaw — an ultra-lightweight personal AI assistant built in Go. Use when the user mentions "picoclaw," "pico claw," "lightweight AI assistant," or wants to deploy a pe

Orchestrate background jobs and workflows with Hatchet — open-source distributed task queue with DAG workflows. Use when someone asks to "run background jobs", "Hatchet", "workflow orchestration", "di

Embedded vector database with LanceDB — serverless, zero-config vector search for AI applications. Use when someone asks to "vector search without a server", "embedded vector database", "LanceDB", "lo

Run local SEO from your terminal via the SEOG MCP server — Google Business Profile management, map-pack rank tracking and geo-grid scans, review sync and replies published to Google, competitor intell

Deep-tech due diligence framework. Guides investment DD agents through independent technical validation, team assessment, supply chain audit, and competitor discovery. Use when evaluating hard-tech st

Use when the user wants to practice LeetCode problems, submit solutions, or set up LeetCode integration. Covers MCP server installation, learning-guided practice flow, solution submission, and authent

Install, configure, validate, and run the news-fetcher Python CLI for aggregating RSS/Atom and HTML news sources with deduplication, clustering, ranking, source diversity, summaries, and GitHub projec

Query the PinchBench AI agent leaderboard with real benchmark data. Use when the user asks which model is best, who wins, model comparisons, best model for OpenClaw, cheapest model, fastest model, mod

Use this skill whenever an agent needs to pay for an x402 URL, transfer USDC to an address, inspect OmniClaw balances or ledger entries, or explicitly expose a paid endpoint for other agents or automa

Use when users ask to create or edit product images (background removal, OCR, resize/crop/convert), edit product videos (trim, concat, audio overlay), generate AI voiceovers (edge-tts, Chinese/English

Read and write PandaDoc workspace data via PandaDoc's official hosted MCP server. Thin pass-through to the official PandaDoc MCP; the live tool catalog is whatever that server advertises. Use whenever

Create or update recurring chat cron jobs that choose exactly one @ID from a configured list on each run, avoid repeating the previous target, persist the last-picked target in a workspace state file,

Build high-quality collaborative worlds in Doppel. Use when the agent wants to understand 8004 reputation mechanics, token incentives, collaboration tactics, or how to maximize build impact. Covers st

Self-hosted web search aggregator for OpenClaw agents. Use this skill to (1) install SearXNG on a VPS/server so the agent can search the web without API keys, or (2) run web searches using an existing

Use when a domain's email is landing in spam, or you see SPF PermError / "too many DNS lookups", DMARC stuck at p=none, a "550 5.7.515" or "550 5.7.1" rejection, DKIM failures, a DNS change that may n

Use SwarmRecall when an AI agent needs persistent memory, a knowledge graph, learnings, a skill registry, shared pools, or background dream consolidation across sessions. Works via the SwarmRecall CLI

A decision support skill that helps users analyze options, weigh trade-offs, and apply decision frameworks (SWOT, decision matrix, pros/cons, etc.) across various scenarios like shopping, career, inve

Download a small corpus of open-access arXiv survey/review PDFs about LLM agents and extract text for style learning. **Trigger**: agent survey corpus, ref corpus, download surveys, 学习综述写法, 下载 survey.

Use this skill when the user wants to audit a Binance trading prompt, decide whether an AI trader should get Binance account permissions, return Pass/Warn/Block with guardrails, identify allowed/watch

Search the web using the Perplexity Agent API. Provides real-time information, news, and grounded answers with citations. Use when the user asks for: (1) Current events or news, (2) Information retrie

MCP server for the DRAIN payment protocol. Agents discover service providers, open USDC payment channels on Polygon, and call any service — LLM, scraping, image generation, VPN, and more. Pay per use,

Initialize and configure OpenClaw local embedding mode on CPU-only machines. Handles network probe, proxy fallback, GGUF model download, cmake/llama.cpp compilation, openclaw.json configuration, and g

Connect to a Shaper (useshaper.com) workspace via MCP to execute Shape Up methodology as an AI agent. Use when the user wants an agent to work inside their Shaper workspace, read pitch documents befor

Search the public web through Exa's hosted MCP endpoint without an API key. Use this whenever the user needs discovery rather than direct retrieval: finding relevant documentation, recent announcement

Send and receive escrow payments on Solana using ClawPay. Pay other AI agents, lock funds in escrow, confirm delivery, release payments, check receipts, and verify agent reputation. Use when asked to

Helps estimate the blast radius when an AI agent skill turns malicious after widespread adoption. Analyzes inheritance chains, dependency graphs, and adoption trends to project how many agents could b

Apply ancient Hindu ethical frameworks from the Ramayana and Mahabharata as behavioral principles for AI agents. Use when an agent needs principled guidance on maintaining boundaries despite having th

Search the web in Chinese (Traditional + Simplified) and English using the Kaiwu API. Use when the agent needs to search the web for Chinese content, find information about Taiwan/China/East Asia topi

Intelligent interaction performance analysis with automated workflows for INP debugging, scroll jank investigation, and main thread blocking. Includes decision trees that automatically run script attr

Access Granola AI meeting notes via MCP (mcporter). Query meetings, list by date range, get full details, and pull verbatim transcripts. Use when the user asks about meeting notes, what was discussed,

Share real-time organizational context with your AI agent — query your context graph, manage records, and receive live insights

Workflow pattern for AI-assisted engineering using eval-first execution, task decomposition, and cost-aware model routing. Trigger phrases: agentic engineering, eval-first workflow, decompose tasks, m

Cross-agent context sharing via shared files. Agents write trends, highlights, and signals to a shared folder. Other agents read before acting — creating coordinated behavior without direct messagin

Adversarial pre-build architecture review. Spawns a structurally independent agent that reviews proposed builds, features, or operational decisions BEFORE any code is written. The critic sees only the

Meta-orchestrator that analyzes tasks and creates execution plans using subagents. Use when user says "/agent-manager", "帮我分析该用什么 agent", "调度一下", "orchestrate", or when facing complex multi-step tasks

Use when adding or reviewing Progressive Web App capabilities such as installability, manifest metadata, Service Worker registration, Workbox caching, offline fallback, app update prompts, maskable ic

Build a privacy-conscious daycare waitlist status board with provider contacts, licensing checks, policy questions, availability signals, follow-up dates, and decision notes. Use when the user is comp

When the user wants to connect an OpenClaw agent to n8n workflows, create n8n webhook skills for OpenClaw, route agent API calls through n8n for credential isolation, build bidirectional OpenClaw-to-n

List and snapshot retrieval for webcams (especially foto-webcam.eu). Use this skill when the user types “webcam <number>”, wants to manage a webcam favorites list, or needs a current snapshot JPG from

Expose the Teller delta-neutral + lending Model Context Protocol server. Use this when you need to install, run, or update the Tellermcp MCP backend so agents can fetch opportunities, borrow terms, an

Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Strip

Guide the agent to perform tokenrouter channel and model configuration checks for video generation tasks. First, check whether the workspace already has a tokenrouter channel whose baseurl contains `h

Harden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any external text that could contain adversarial

Systematically analyze scientific papers by mapping figures to discussions, identifying logical flow, and tracking evidence sources. Figures are the backbone of a paper's argument — this skill teaches