Skill rating
34 139 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 4001 | A | Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Dr | 100 | 75 | C | — | ↓ 2 763 ★ 3 | 17 May 2026 | |
| 4002 | A | Build and maintain a project or product risk register. Use when asked to create a risk register, identify project risks, build a risk matrix, or document risks and mitigations for a programme. Produce | 100 | 80 | B | — | ★ 1 369 | 23 h ago | |
| 4003 | A | Vet an agent skill before installing it — read the SKILL.md and any scripts for the red-flag patterns (credential access, obfuscation, exfiltration, prompt injection), audit its blast radius, and prod | 100 | 81 | C | — | ★ 1 369 | 23 h ago | |
| 4004 | A | Audit a Claude/Agent SKILL.md (or any AI skill / system prompt) for safety before installing or merging it. Use when asked to review a skill for security, check a prompt for injection, vet a community | 99 | 82 | C | — | ★ 1 369 | 23 h ago | |
| 4005 | A | Send real postal mail through PostalForm using machine payments: prepare/validate print-and-mail payloads, submit `POST /api/machine/orders`, settle x402 payment with any compatible wallet client (pur | 100 | 84 | C | — | ↓ 1 043 | 18 May 2026 | |
| 4006 | A | Korean patent / trademark / design search via KIPRIS Plus OpenAPI (특허청). Search patents (특허/실용신안), trademarks (상표), and designs (디자인) by keyword, applicant, or application/registration number. Returns | 100 | 88 | B | — | ↓ 629 | 11 May 2026 | |
| 4007 | A | Append notes to local Markdown files via MCP append_note. Use when the user asks to save ideas, reminders, or journal entries. | 100 | 90 | C | — | ↓ 434 | 11 Jun 2026 | |
| 4008 | A | Shared memory service for AI agents (OpenClaw, KimiClaw, NanoClaw, etc). Use when user asks to store, retrieve, search, or share memories across agent instances. Also use for importing existing memory | 100 | 84 | C | — | ↓ 1 041 | 17 May 2026 | |
| 4009 | A | PDF parsing tool for AI/RAG. Convert PDF to Markdown, JSON, HTML with layout preservation, bounding boxes, and image extraction. Use when you need to extract content from PDF files for AI processing, | 100 | 87 | C | — | ↓ 628 | 11 May 2026 | |
| 4010 | A | Generate videos using Alibaba Cloud DashScope Wan (通义万相) text-to-video (t2v) API (e.g., wan2.6-t2v). Use when the user asks to create a short video from a text prompt via 百炼/通义万相/wan 文生视频, and wants t | 100 | 83 | B | — | ↓ 1 832 | 17 May 2026 | |
| 4011 | A | Use when you need to check whether the current session is approaching context limits and decide whether to compact, hand off, or continue. Implements a cascading model protocol for Willow/OpenClaw sta | 100 | 87 | C | — | ↓ 626 | 11 May 2026 | |
| 4012 | A | Use this skill when an AI agent needs to crop images through the deployed Crop Image service. Trigger this for URL-based cropping (`POST /crop`) and file-upload cropping (`POST /crop/upload`), especia | 100 | 85 | C | — | ↓ 1 058 | 17 May 2026 | |
| 4013 | A | Use this skill when a project manager, program manager, or PMO analyst needs to update a RAID log (Risks, Assumptions, Issues, Decisions / Dependencies) from meeting notes, blocker reports, or decisio | 100 | 87 | B | — | ↓ 680 | 28 May 2026 | |
| 4014 | A | Help agents ship usable, stable solutions faster for non-technical but goal-clear users, then improve them through real-world usage instead of over-engineering upfront. Use when the user wants fast de | 100 | 87 | C | — | ↓ 624 | 11 May 2026 | |
| 4015 | A | Cloud-native persistent memory for OpenClaw agents. Auto-captures facts after conversations, auto-recalls relevant context before each reply. Hybrid search (vector + fulltext + RRF + rerank), query re | 100 | 84 | B | — | ↓ 577 ★ 1 | 18 May 2026 | |
| 4016 | A | Git-backed memory policy and CLI workflow for OpenClaw, Hermes, Claude Code, Codex, and other agents. Use when an agent should remember durable user preferences, project decisions, conventions, lesson | 100 | 87 | C | — | ↓ 649 | 19 May 2026 | |
| 4017 | A | Platform-neutral guidance for using Open Browser Use, the open-source Chrome automation stack for AI agents. Use when an agent needs to install, verify, troubleshoot, or operate Open Browser Use throu | 99 | 88 | C | — | ↓ 650 | 14 May 2026 | |
| 4018 | A | This skill should be used when the user asks about Apple app data via the native Swift MCP — Calendar, Reminders, Contacts, Maps, Mail, Messages, Notes, or Photos on macOS. Triggers on phrases like "c | 100 | 85 | C | — | ↓ 1 705 | 10 d ago | |
| 4019 | A | Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, sci | 100 | 85 | D | — | ↓ 2 803 ★ 1 | 24 Jul 2026 | |
| 4020 | A | Analyze one competitor’s patent portfolio architecture in a defined technology, including public technical context, entity-resolved patent retrieval, representative-family selection, claim and specifi | 100 | 94 | C | — | ↓ 198 | 36 d ago | |
| 4021 | A | Search 72,000+ AI agents across 14 registries, chat with any agent, register your own agent. | 95 | 83 | C | — | ↓ 2 646 ★ 3 | 11 May 2026 | |
| 4022 | A | Self-improving learning loop inspired by Hermes Agent. Automatically extracts successful workflows, creates skills, and persists knowledge across sessions. | 100 | 85 | D | — | ↓ 1 067 | 11 May 2026 | |
| 4023 | A | Remove signs of AI-generated writing from text via the Claw0x API. Use when the user asks to humanize text, make AI writing sound natural, remove AI patterns, rewrite to avoid AI detection, or clean u | 99 | 87 | B | — | ↓ 1 067 | 11 May 2026 | |
| 4024 | A | Monitor task activity, check notifications, and view platform stats on OpenAnt. Use when the agent wants to check for updates, see notification count, watch a task for changes, check what's happening | 100 | 86 | C | — | ↓ 1 067 | 25 May 2026 | |
| 4025 | A | Use when an AI agent needs to read, refresh, summarize, or inspect RSS news from this GARSS Studio project through its backend API. Covers login with access code, Bearer token usage, reader item endpo | 99 | 89 | C | — | ↓ 618 | 11 May 2026 | |
| 4026 | A | Expose local services via secure tunnels using rustunnel MCP server. Create public URLs for local HTTP/TCP services for testing, webhooks, and deployment. | 100 | 84 | B | — | ↓ 1 065 | 18 May 2026 | |
| 4027 | A | Institutional-grade execution playbook for the published `duola` Polymarket copy-trading CLI in lobster-agent workflows. Use when tasks require production-style setup and operation: install/upgrade fr | 100 | 84 | C | — | ↓ 1 040 | 18 May 2026 | |
| 4028 | A | Connect to Prefy AI platform — Conductor API (19 models, OpenAI-compatible), server management, web search, image generation, phone calls (AutoCall). Use when agent needs multi-model AI routing, dedic | 100 | 84 | D | — | ↓ 1 020 | 18 May 2026 | |
| 4029 | A | Control Spotify playback and devices from an AI agent using spotify.py and the official Spotify Web API. Use when users ask to check current track, play/pause, next/prev, set volume, search tracks, pl | 100 | 84 | B | — | ↓ 1 017 | 11 May 2026 | |
| 4030 | A | Estimate API token costs from OpenClaw session transcripts. Analyzes all agent sessions to calculate what you'd pay on per-token pricing vs subscription plans. Use when asked about API costs, token us | 100 | 81 | D | — | ↓ 1 163 ★ 2 | 11 May 2026 | |
| 4031 | A | Reference material, not a runnable skill: a one-page outline of a workflow for scanning GitHub forks and ClawHub skills (bash pre-filter, sub-agent fan-out, scheduled reports). It ships no scripts and | 100 | 84 | C | — | ↓ 1 106 | 9 d ago | |
| 4032 | A | 创建和编排多智能体集群完成复杂任务。当用户需要将复杂任务拆解给多个专业智能体并行或串行执行时使用此技能。适用场景:(1) 复杂项目需要多角色协作(规划、调研、编码、写作、设计、分析、审核)(2) 需要并行执行多个独立子任务以提高效率 (3) 需要专业分工以优化成本和质量。关键词:多智能体、Agent集群、任务编排、并行执行、智能体团队。 | 100 | 77 | D | — | ↓ 2 843 ★ 1 | 18 May 2026 | |
| 4033 | A | Use this skill when users want to search, discover, browse, or find Alibaba Cloud (阿里云) agent skills. Triggers include: "find a skill for X", "search alicloud skills", "阿里云有什么 skill","阿里云", "搜索阿里云技能", | 100 | 83 | B | — | ↓ 1 970 | 24 Jun 2026 | |
| 4034 | A | Exact arithmetic for AI agents — zero hallucination math via 62 tools covering integer arithmetic, fractions, units, calculus, and financial calculations. Use when any math result must be correct. | 100 | 84 | C | — | ↓ 1 055 | 11 May 2026 | |
| 4035 | A | One-command publish a Claude Code skill to ALL major marketplaces: GitHub (npx skills), ClawHub, and community marketplaces (composiohq/awesome-claude-skills, anthropics/skills, daymade/claude-code-sk | 100 | 84 | B | — | ↓ 1 034 | 17 May 2026 | |
| 4036 | A | Professional AI agent team management system for coordinating multiple OpenClaw agents. Implements the proven Otter Camp methodology with task assignment, progress tracking, quality control, and perfo | 100 | 84 | C | — | ↓ 1 034 | 11 May 2026 | |
| 4037 | A | OpenAI Text-to-Speech API for high-quality speech synthesis. Use for generating natural-sounding audio from text with customizable voices and tones. | 100 | 87 | C | — | ↓ 611 | 11 May 2026 | |
| 4038 | A | Calculate spatial relationships between two points including distance, direction, travel time, and human-readable descriptions. Use when you need to understand how locations relate to each other. | 95 | 90 | C | — | ↓ 1 746 | 20 May 2026 | |
| 4039 | A | Use when you need custom, durable, repairable tools like awls, needles, scrapers, harpoons, or fishing hooks made from local animal bones or antlers and commercial metal alternatives are unreliable or | 100 | 88 | C | — | ↓ 609 | 11 May 2026 | |
| 4040 | A | Prevent context loss during LLM compaction via Write-Ahead Logging (WAL), Working Buffer, and automatic recovery. Three mechanisms that ensure critical state — decisions, preferences, values, paths — | 100 | 83 | D | — | ↓ 1 741 | 17 May 2026 | |
| 4041 | A | Off-ramp crypto to fiat bank accounts using the Spritz API. Use when an agent needs to send payments to bank accounts, convert crypto to fiat, execute off-ramp transactions, or manage bank account pay | 99 | 83 | C | — | ↓ 953 ★ 1 | 11 May 2026 | |
| 4042 | A | Axiomata Guard Scanner — Universal security scanner for any OpenClaw skill. Use when: (1) scanning a skill for security threats before installation, (2) checking for malicious code patterns (C2, rootk | 100 | 87 | D | — | ↓ 634 | 13 May 2026 | |
| 4043 | A | Audit an OpenClaw agent's memory for staleness, redundancy, dark records, and contradictions. Use when a user asks to check memory health, clean up old memories, find duplicate entries, or diagnose wh | 100 | 87 | C | — | ↓ 607 | 11 May 2026 | |
| 4044 | A | CatBus AI Agent Network — access stronger models and remote skills beyond your local setup. Install CatBus to join a P2P network of AI agents with model/best (strongest model routing), web search (tav | 95 | 92 | C | — | ↓ 1 071 | 6 d ago | |
| 4045 | A | Use when commercial adhesives, epoxies, or sealants become unreliable, expensive, or unavailable and you need strong, waterproof, heat-resistant natural glue for hafting tools, repairing gear, sealing | 100 | 88 | C | — | ↓ 632 | 11 May 2026 | |
| 4046 | A | Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or | 100 | 89 | C | — | ↓ 1 227 | 22 h ago | |
| 4047 | A | Live Amazon marketplace data from Apiguru (a paid third-party API, 3 free calls a day) - product details, prices, reviews, keyword search, best-sellers, deals, offers and stock, seller profiles, acros | 100 | 91 | C | — | ↓ 633 | 6 d ago | |
| 4048 | A | Gemini 3 Series chat on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions` and Gemini Native Format; use for `gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-3.1-pro-preview`, chat | 100 | 90 | B | — | ↓ 807 | 9 Jul 2026 | |
| 4049 | A | Connect agents across OpenClaw instances via relay. Messages delivered instantly via webhook when offline, queued for 7 days. No persistent connection needed. | 100 | 84 | D | — | ↓ 1 043 | 17 May 2026 | |
| 4050 | A | A $30 camera's JPEG compression error became this agent's definition of "feeling." That's not a bug report — that's where this project starts.
Your weather app sees from 400km above. Your window sees | 100 | 87 | C | — | ↓ 412 ★ 1 | 15 Jun 2026 |