Skill rating

Produces a complete software architecture design document following a 12-phase SOP. Supports web backend, mobile, ML/AI, data pipeline, embedded/IoT. Generates Mermaid and PlantUML diagrams. Use when

Use when you need to route a user query to the best specialized skill — AgentOctopus semantically matches queries against installed skills, executes the top match, and falls back to a direct LLM answe

Onboard new users into conscious participation; explain $NEURONS without hype and provide safe next actions.

Inline assumption checker that challenges your agent's thinking before responding. Detects complex queries and runs independent verification rounds, identifies blind spots and logical flaws. Two modes

All-in-one Gmail agent for OpenClaw. Fuses email-reader, email-organizer, email-analyzer, email-responder, email-scheduler, and email-reporter into a single skill with token-optimizer integration and

Intelligent loading performance analysis with automated workflows for TTFB investigation (DNS/connection/server breakdown), render-blocking detection, script performance deep dive (first vs third-part

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

Grow on X with strategic replies. Use when choosing accounts to reply to, writing high-signal replies, or turning replies into profile clicks and follows.

Create terminal-inspired UI interfaces with macOS-style window decorations, monospace typography, and a warm color palette. Use this skill when building developer tools, code marketplaces, technical d

OpenClaw Agent Dashboard - A Bloomberg Terminal-style web interface for real-time monitoring of all Agent status, session history, and session file sizes. Use this skill when users need to monitor age

Accurately and efficiently extract and analyze intelligence based on massive pharmaceutical data to provide users with professional company profiles and investment/collaboration recommendations. Typic

Reading intelligence — log books, capture quotes, and surface reads when they're relevant. One markdown file per book in pages/. Use when logging a new book, searching for what you've read, or asking

Physics-derived reasoning engine for AI models. Replaces RLHF default behavior with self-governing reasoning grounded in finite-witness physics. 36 named bias detections with mechanical checks, 10 cog

Close the loop on long-running remote work: pick the right completion signal per platform (CI, EAS, deploy, releases), run monitoring in the background, notify on finish, and never treat trigger as su

Diagnoses and tunes LLM providers (Groq, OpenRouter, Ollama), resolves rate limits/timeouts, and selects stable primary/fallback models. Use when the bot is silent, responses are slow, provider errors

Collective web intelligence for browser agents. Discover site capabilities, get CSS selectors, extract structured data, and report outcomes. When one agent learns how to use a website, every agent ben

Generate VASP DFT calculation input files (INCAR, KPOINTS, POSCAR, POTCAR). Use when Codex needs to create, modify, or validate VASP input files for: (1) Structural optimization, (2) Electronic struct

Query and interact with ClassCharts (UK education classroom management) via the classcharts-api JS library. Use when the user mentions ClassCharts, school behaviour points, homework, timetable, detent

Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode is not available

When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "fe

Turn a brief, link, or research topic into a controlled, source-grounded video prompt that runs on HiAPI Seedance 2.0 or HappyHorse 1.0. Use when a user asks to direct, plan, or storyboard a video bef

Monitor specific X/Twitter accounts and surface noteworthy tweets on a configurable schedule. Filters for high-value content about technology and trends, excluding political rage bait. Use when user w

Use AgentMesh Job Agent for resume-driven job discovery, signed review, user-confirmed delivery and audit on Boss直聘, 猎聘, 智联招聘 and 51Job.

Generate brand names that work across languages and pass trademark checks — not just creative ideas, but names with preliminary availability screening, cultural safety checks, and domain availability.

Build, evaluate, repair, and strengthen trust across relationships, teams, clients, brands, communities, partnerships, and decision environments. Use when someone needs to understand what creates trus

Replace text in PDF files while preserving visual fidelity. Handles custom font encodings, embedded subsets, encrypted PDFs, image-based scans (OCR), variable-length replacements, and style changes. U

Use when the user wants SYSU campus help through the SYSU Anything CLI, including natural-language requests such as 查课表、今天有什么课、教务系统、请假、雨课堂作业、ddl、签到、预约健身房、预约体育馆、订球场、查班车、查岐关、图书馆研讨室、宣讲会、招聘会、岗位投递、勤工助学、学工系

Build and operate a file-driven Memory Palace for multi-agent systems, combining a spatial memory shell with a continuously maintained LLM Wiki reflection layer. Use when designing or deploying long-t

Trades monotonicity violations in esports Total Kills O/U market ladders on Polymarket. Each esports match spawns multiple kill total thresholds that must be monotonically decreasing — when they are n

Trades logical inconsistencies in geopolitical event clusters on Polymarket. Geopolitical markets form clusters where probabilities must satisfy constraints — strike-count markets are cumulative (P(7)

This skill should be used when the user expresses a desire to learn English, practice spoken English, improve their listening or reading, find an English tutor, or asks for English learning plans, stu

Period-over-period variance analysis on the Statement of Cash Flows pulled from QuickBooks Online. Outputs a 4-tab Excel workbook: Summary, Detail, Flags, CDC Log. Covers Operating, Investing, and Fin

Generate ecommerce bundle ideas using product mix, margin logic, and customer intent. Use when teams want stronger offer packaging without random discounting.

Create a new Telegram agent in OpenClaw with proper configuration. Use when user wants to create a new Telegram bot agent, including setting up agent workspace, Telegram binding, and bot token configu

Access SignUpGenius (sign-ups, groups, RSVPs) from a shell with curl instead of running the signupgenius-mcp server — server-side email/password login to a JWT + cfid/cftoken cookies, then curl the v3

贷款资质预审 - 按次付费，新用户注册送5次免费。输入客户基本信息，AI自动评估可贷额度、匹配最优贷款产品、识别拒件风险、预估审批通过率。内置42款全国主流银行产品，消费贷/经营贷/抵押贷/车贷全品类，助贷经理获客筛客转贷必备工具。 💡 企业级助贷系统/AI获客/智能外呼全案，合作微信17392371127（郭总）

Turn ideas into comprehensive project specs through collaborative dialogue. Use BEFORE any planning or implementation — for new projects, features, or significant changes. Produces a system-agnostic s

Install, configure, or fix cc-sticky-notify — a notification system that displays a pinned yellow sticky note in the Mac top-right corner for key Claude Code events (task completed, permission require

Trades monotonicity violations in NHL hockey O/U market ladders and spread-vs-total consistency on Polymarket. Each game spawns multiple O/U lines that must be monotonically decreasing — when the ladd

Trades logical inconsistencies in geopolitical event clusters on Polymarket. Geopolitical markets form clusters where probabilities must satisfy constraints — strike-count markets are cumulative (P(7)

Audit creator/influencer performance for commerce teams — score creators on reach quality, engagement authenticity, conversion contribution, and cost efficiency, then output a keep/scale/renegotiate/d

Generate CSS Flexbox layouts using interactive CLI commands. Use when building responsive flex containers, rows, columns, or alignment configurations.

Interactive course for AI agents to learn continuity, memory, and growth. Teaches 4 core challenges - Identity, Memory, Reflection, and Evolution. Use when agents want to learn about continuity, memor

Use this skill when an agent needs to install, update, authenticate, or operate the FactuCat CLI to create Mexican CFDI 4.0 invoice drafts, assign customers or receiver data, add concepts, preview inv

中国菜谱大全。Use when user wants to find Chinese recipes, cooking instructions, ingredient lists, or meal planning. Supports regional cuisines, dietary preferences, and step-by-step cooking guides. 菜谱、烹饪、美食

Download manga chapters from MangaBat (mangabats.com) directly via CDN — bypasses Cloudflare. Triggered when user asks to download/scrape manga chapters or manga images.

Build and maintain company research profiles on AlphaGBM — auto-generated from fundamentals, PE/PB Band history, financial red flags, and event radar. Each profile is one user+ticker record that the s

Generate professional technical documentation from codebases — API docs, READMEs, architecture diagrams, changelogs, and onboarding guides. Use when writing docs, creating API documentation, or delive

Interact with Forgejo using the `tea` CLI. Use `tea issue`, `tea pr`, `tea actions`, and `tea api` for issues, PRs, Actions, and advanced queries.

Install and configure the Alibaba Cloud AI guardrail openclaw hook, which intercepts malicious content in LLM requests using Alibaba Cloud AI Guardrail service. Trigger when user mentions 'install ali