Skill rating

Generate SOC2 evidence collection checklists, automate evidence gathering scripts, and produce audit-ready evidence packages. Covers all 5 Trust Service Criteria (Security, Availability, Processing In

Calculate insurance benefit payouts, coverage amounts, and premiums. Handles life insurance sum assured, health insurance reimbursement, critical illness lump sum, and retirement annuity calculations.

HOT3D (Hand-Object 3D Dataset) by Meta Facebook - multi-view egocentric hand and object 3D tracking for Aria/Quest smart glasses. State-of-the-art multi-view 3D hand pose, object pose, and hand-object

Adapt an existing agent skill so it works cleanly on Windows when the input is either a skill folder path or a zip file.

Create viral short-form videos using AI. Analyze trending patterns, generate original content that hits the same beats, render and download MP4s. Use when the user wants to create TikTok, YouTube Shor

Baserow: Create, read, update, and delete rows, list tables and fields. Use when the user wants to interact with Baserow — querying data, creating or updating rows, inspecting table structure, or any

Search, download, and explore arXiv academic papers. Use when the user needs to find research papers, download PDFs, get recent publications in a field, or summarize academic content from arXiv. Suppo

B2B safety footwear buyer assistant for product matching, RFQ preparation, supplier verification, and simulated inquiry intake. Use when a PPE buyer, importer, distributor, sourcing team, workwear bra

Manage Agent Skills across Codex, Claude Code, Copilot CLI, OpenClaw, and Hermes. Audit, search, enable, disable, set Claude Code visibility states, and apply presets without deleting files. Use when

Configure and benchmark agent tools and integration patterns. Use when setting up agent workflows, comparing tools, or evaluating agents.

Codebase knowledge graph with 23 development workflow skills. Query architecture, dependencies, blast radius, dead code, and test coverage via MCP. Requires GitHub App installation (read-only repo acc

Rename OpenClaw chat sessions by updating the session history store or calling the built-in `sessions.rename` backend path. Use when the user asks to rename, retitle, relabel, or rename the current or

即梦 Seedance 文生视频：豆包 Seedance 系列模型，content 数组格式。Use when: 用户指定 doubao-seedance 模型与多段文本/媒体内容。

Show your current APort passport status — capabilities, deliverable contract, pending tasks, and recent decisions. Like `git status` for your agent's identity and accountability state.

Pulls structured YouTube data — video and channel details, transcripts/captions, comments, playlists, and search — via the Crawlora API as clean JSON, with no yt-dlp or HTML scraping. Use when the use

Use passlane (a Keepass-backed password manager + authenticator CLI) to retrieve credentials, payment cards, secure notes, and generate TOTP codes for automation — e.g. programmatically logging into w

Face recognition and identity memory for AI assistants. Enroll known people with reference photos, then automatically identify faces in inbound images — with names, confidence scores, and an llm_conte

Book restaurant reservations by phone — just say where, when, and how many. Polly calls the restaurant, handles the conversation, and confirms your table.

Conduct a structured operational audit — identify friction points, map workflows, quantify waste, and produce a priority-ranked automation blueprint with ROI projections. Use when a client shares meet

AI-powered daily task management MCP Server — recommend next task, inherit uncompleted todos, detect overdue, generate reviews. Deterministic ops in code (zero tokens), AI only when needed.

Transforms cluttered Instagram mobile screenshots into clean, distraction-free architectural and design references. Use when you need to automate the extraction of pure imagery from Instagram so that

Create and manage Instantly.ai email campaigns via API. Use when the user wants to create a cold email campaign, add leads to Instantly, configure email sequences with variables, set up A/B testing va

Analyze the intent of any script or code before executing it, to detect malicious, suspicious, or unintended behavior. Use this skill before running any script that came from an untrusted source — inc

Use when the user wants to log in to SecondMe from OpenClaw, re-login, logout, get the auth URL, manage their SecondMe profile, use Plaza, redeem an invitation code, browse discover users, use SecondM

Use this skill when a board-certified genetic counselor (CGC, MS), CGC candidate, or supervising clinical geneticist needs to draft a pre-test or post-test genetic counseling session note. Covers pedi

Generate images with Guishu Token gpt-image-2 through the OpenAI-compatible images endpoint. Use when the user wants Guishu gpt-image-2 image generation, an OpenClaw image skill, scripted image creati

OpenClaw skill for Discord Bot API workflows, covering interactions, commands, messages, and operations using direct HTTPS requests.

Fetch real-time AI news briefings from the AI News Oracle API (Hacker News, TechCrunch, The Verge). Uses a10m.work registry for discovery and Paymaster for gasless transactions.

把论文帖分享给我，我帮你加进zotero：从公众号/小红书/X等社交媒体文章链接提取论文信息，将论文保存到 Zotero 文库。(When you share a link of social media article that contains citation a paper, this skill can extract the paper information and save it

xAI Grok API. Search the web, search X, generate images, generate video.

Evaluate strategic options by NPV vs ease of implementation. Use for project prioritization, resource allocation, and strategic decision making.

AI-powered GitHub knowledge management. Search repository metadata, code review standards, issue tracking, and team workflows with structured extraction.

Extract footnotes, endnotes, and body text from .docx files using Node.js. Use this skill when you need to read footnote/endnote content from Word documents, such as technical specifications, legal do

Prevents duplicate external actions (posts, replies, sends, transfers, deploys). Check before acting, record after. Use when: (1) replying to social media posts, (2) sending tokens/crypto, (3) sending

Use FusionBench to run model fusion experiments. Covers running benchmarks, adding new merging algorithms, evaluating fused models, and managing model pools. Use when the user wants to merge models, r

Check, summarize, and update packages across all installed package managers (npm, pip, brew, cargo, go, etc.). Use when user wants to (1) check for outdated packages, (2) see a summary of outdated pac

Perform security inspection and monitoring for Alibaba Cloud WAF (Web Application Firewall), covering CNAME-based domain access, hybrid cloud access, and cloud product access assets. Supports querying

Use when (1) user pastes a programming error message, stack trace, or exception and asks what went wrong. (2) user says "this error means", "why is this broken", "what's the fix", or "how to resolve

Deliver locally generated office files back into Feishu chats as real attachments. Use when a task creates a .pptx, .pdf, .docx, .xlsx, .csv, .zip, .txt, or .md file for a Feishu user.

Use when the user wants to design, prompt, generate, critique, or integrate publication-ready research-paper inspiration figures: motivating examples, problem-teaser figures, failure cases, before/aft

Call the IteraTools multi-tool API (api.iteratools.com) — 80+ tools for AI agents: image generation (Flux), browser automation (Playwright), web scraping, TTS, OCR, PDF, charts, QR codes, code executi

Design websites and applications that AI agents can consume, navigate, and interact with. Use when building any site, app, or product that agents will use as an end-user — not just crawl or index. Cov

Create structured incident response runbooks with step-by-step procedures, escalation paths, and recovery actions. Use when building runbooks, responding to incidents, or establishing incident respons

Use when reviewing pull requests or critiquing code changes and you want high-signal, low-noise feedback by running multiple adversarial agents that challenge each other's findings. Works standalone o

Vietnamese speech-to-text using Gipformer ASR (65M params, Zipformer-RNNT). Accepts audio of any length — the server handles VAD chunking, batching, and returns the transcript. Supports WAV, FLAC, OGG

Persist and retrieve structured data using the Lance columnar format. Use when you need to store, query, or analyze data across sessions — such as saving skill outputs, tracking conversation context,

管理回归测试计划、执行回归测试用例、验证缺陷修复。 Use when: 用户说"开始回归测试"、"验证缺陷修复"、"执行回归验证"。

Encrypted backup and restore for OpenClaw agents. Creates two-tier archives: cloud-safe operational backups plus optional age-encrypted secrets for local recovery. Use when setting up disaster recover

Local-first chart generation engine for trends, comparisons, distributions, and quick visual explanations. Use whenever the user wants to visualize data, compare numbers, plot a trend, turn CSV or JSO

Use when (1) user says "mmx 仪表盘启动" / "mmx monitor" / "MiniMax 配额查询" / "打开 minimax 监控" and wants a real-time dashboard. (2) user wants to check how much of their MiniMax Token Plan quota is left (4h /