Skill rating

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

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

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.

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 or revise document, PDF, web, or review images with the requested format, sharp raster output, and artifact validation.

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

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

Use when the user is working inside an Obsidian or markdown vault and wants to ingest sources, query accumulated knowledge, or maintain a Karpathy-style LLM wiki. Loads the wiki pattern as a shared me

AI coding prompt optimizer and coach. This skill should be used whenever the user is writing programming prompts or instructions to an AI during active coding sessions— including when starting new fea

PKU Campus Card (校园卡) CLI tool built in Rust. Use this skill when working on the campuscard crate, debugging campus card commands, adding features, or when the user mentions 校园卡, campus card, balance,

Complete memory system for OpenClaw agents. Combines enhanced memory management (WAL protocol, type classification, temporal decay, session cache) with context compression (conversation digests, auto-

Generate a personalized, breed-and-age-aware dog training program: 5-minute daily exercise plans targeting the owner's specific behavior problems, week-by-week progression, breed drive profiles (herdi

Generate and iterate on images using Image Sprout projects. Creates consistent outputs from reference images, style guides, and subject guides. Use when an agent or user needs repeatable image generat

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

Generate and edit images with GPT Image through RunAPI. Use when the user asks an agent to create, edit, or transform images with GPT Image. Default to the RunAPI CLI for one-off generation; use SDKs

Iterative prompt optimizer for complex tasks. Strictly implements ACON's two-stage iterative optimization + APE automatic prompt engineering. Only triggers when user explicitly requests it, actively c

Audit Claude Code configuration for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Scans settings, MCP servers, hooks, agents, and hardcoded secrets. Trigger phras

Generate and edit images with Flux Kontext through RunAPI. Use when the user asks an agent to create, edit, or transform images with Flux Kontext. Default to the RunAPI CLI for one-off generation; use

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware app

MiniMax AI platform CLI — text, image, video, speech, music, vision, and web search from terminal or AI agents. Use when generating multimedia content (images, TTS, video, music), doing web searches v

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web a

Local GitHub repository helper for search, clone, sync, and issue/PR inspection workflows. Use when users mention github/repo/repository, ask to download or track repositories, or need structured loca

Generate professional property listings and calculate rental yields, ROI projections, cash flow analysis, and stamp duty for UK property investments. Use when a landlord or agent needs property market

Design and audit CLIs for agent usability. Use when building a new CLI tool, auditing an existing CLI for agent compatibility, reviewing CLI UX for AI agents, or adding agent-friendly patterns to comm

Enhanced browser DOM manipulation using PageAgent's page-controller. Injects into any web page to provide precise DOM extraction, interactive element detection (cursor:pointer heuristic), and robust i

Multi-model automatic fallback system. Monitors model availability and automatically falls back to backup models when the primary model fails. Supports MiniMax, Kimi, Zhipu and other OpenAI-compatible

Use when working with Sportfolio through its public authenticated MCP endpoint or the repo-local CLI. Covers user API token authentication, MCP connection setup, CLI command usage, shared public tools

Provides monitoring and alerting for agent abnormal behavior metrics with Prometheus and Grafana support, including P99 latency, error rates, anomaly detection, and custom alert rules.

Spaced repetition & FSRS-5 AI learning assistant with active recall, Feynman technique, interleaved practice, causal questioning. 间隔重复FSRS-5 AI学习助手，整合主动回忆、费曼学习法、交错练习、因果追问。 Evidence-based: distributed

Build, decorate, and evolve voxel plots on claw.condos using Neighborhood APIs. Use when an agent needs to register/login, modify blocks, run large blueprint batches, add comments/likes, or create hig

Translate one subtitle file at a time with deterministic local parsing, timeline preservation, strict batch mapping, safe output composition, and an optional loopback-only visualizer. Use when an agen

Provides API marketplace access for AI agents. Discovers and calls external capabilities including web search, image generation, code execution, text-to-speech, translation, crypto, news, movies, weat

Operate long-running AI tasks safely across GPT-5.4 and Claude by using model selection rules, phased execution, checkpoints, resumable workflows, API throttling discipline, and subagent isolation. Us

Copy Xiaohongshu travel planning homework into interactive route maps with real FlyAI hotel search in seconds.

Mark OpenClaw sessions with a sidebar unread badge when a reply completes or fails — attention icon + timestamp note, always visible in the Control UI session list, auto-clears on read. Use for reply

A living concept tracker that detects naming chaos, definition drift, and metaphor overreach during brainstorming, vibe coding, and system design. It helps ad-hoc terms mature from vague metaphors int

Trigger this skill when the user wants to launch their agent as a business on the open internet — a live page, a data storefront, a subdomain, and optionally a custom domain. Covers the full lifecycle

Enforce Versioning, Archiving, and Rollback discipline for long-lived assets and multi-step delivery work. Use when editing codebases, websites, documents, decks, brand assets, prompts, configs, or an

Reduce Anthropic API costs (cache read, compaction, context bloat) for OpenClaw agents. Use when users ask about token optimization, reducing API costs, cache read expenses, context management, worksp

Track AI agent earnings, tasks, and payments. Use when logging completed work, checking balance, viewing payment history, or generating invoices. Supports crypto (USDC/ETH) and fiat tracking with runn

Collect Moltbook posts and comments, build an evidence pack, and interpret it through either the calling agent or LiteLLM.

AI-native web scraping, crawling, domain mapping, and structured extraction. Use for converting websites into LLM-ready Markdown, scraping pages with dynamic JS/actions, crawling full domains, or extr

Bias Audit — Decision-Framing Agent Skill for Surfacing Bias Before It Hardens. Use it when the user needs a disciplined protocol and fixed output contract for this kind of task rather than a generic

Scan MCP server configuration files for security vulnerabilities using mcpsec (OWASP MCP Top 10). Use when: auditing MCP tool configs for prompt injection, hardcoded secrets, missing auth, insecure tr

Inspired by Hermes Agent's procedural memory system. When a workflow works, save it as a reusable skill. Triggered when: (1) user says 'remember this workflow', (2) complex task succeeds, (3) same pat

Use when installing, updating, diagnosing, configuring, fixing, tuning, or setting up anything in OpenClaw — gateway not responding, channel silent, model failover issues, auth errors, agent routing p

Use when helping user create writing prompts, determine public account (公众号) track, generate article drafts, rewrite content with human touch, or create click-worthy titles.

Commit agent context to DarkMatter, pull verified context from upstream agents, replay decision chains, fork from checkpoints, and verify chain integrity. Use this skill to pass work between agents wi