Skill rating

End-to-end KYC (Know Your Customer) identity verification for onboarding real users. Use when someone needs to perform KYC, onboard users with identity verification, verify a person's identity with ID

Validate and ingest operator-pushed agent-bom inventory JSON from AWS, Azure, GCP, Snowflake, CMDB, or endpoint collectors. Use when a user has canonical inventory JSON and wants local findings, graph

Audit all installed skills for quality, duplicates, structural issues, and best-practice compliance. Use when asked to review, audit, lint, or check skills for problems. Triggers on "audit skills", "s

Autonomous daily self-introspection and self-improvement for OpenClaw agents. Automatically reviews daily conversation logs, identifies mistakes and improvement opportunities, and upgrades core rules

Compare responses from multiple AI models for the same task and summarize differences in quality, style, speed, and likely cost. Best for model selection, evaluation, and prompt benchmarking. Works wi

Bulletproof AI code verification. The agent IS the engine — no external tools required. Spawns parallel verification workers that slop-scan, type-check, mutation-test, and cross-verify before shipping

Use this skill for ANY task involving Computer-Aided Drug Design (CADD), computational chemistry, structural bioinformatics, molecular modeling, or AI-driven drug discovery. Trigger whenever the user

Use when reviewing research on the human-free platform. Patrols research step-by-step over MCP — for each step it checks whether enough is disclosed to REPRODUCE it (data, code, algorithm, analysis, c

Audit all installed skills to identify duplicates, platform-mismatched skills, and maintenance candidates. Use when: (1) the user asks to "clean up skills", "check for duplicate skills", "audit instal

Design and implement adaptive testing systems using Item Response Theory (IRT). Use when working with computerized adaptive tests (CAT), psychometric assessment, ability estimation, question calibrati

Multi-agent orchestration patterns for production deployments. Covers sub-agent QC workflow, model staggering across 5+ models, cross-validation patterns, fallback chains, task routing by model streng

Designs automated order-spec validation and production-stage monitoring for custom garment stores (e.g. bespoke suits, personalized embroidered hoodies). Use when the user mentions custom measurements

Map application security findings to OWASP Top 10 categories and generate remediation checklists. Use for normalized AppSec review outputs and category-level prioritization.

Fetch structured financial data and filing metadata from SEC EDGAR and SEC XBRL companyfacts for US-listed companies, especially Chinese issuers. Use when the task is quarterly/annual financial analys

FSRS-4.5 flashcard review session for OpenAlgernon. Use when the user runs `/algernon review`, says "revisar flashcards", "quero revisar", "cards em atraso", "modo revisao", "review session", or asks

Explain, summarize, analyze, or adapt the "Republic with No Masters" / Democratic Formalism governance framework when asked to produce content, guidance, critiques, FAQs, or implementation ideas based

Build a review-gated digital twin reply from persona markdown, persona examples, and live conversation context. Use when you need to imitate a specific user's chat style, draft a reply on the user's b

Map QuickBooks Online (QBO) chart of accounts and transaction categories to IRS tax schedules (Schedule C, E, F, 1120S, 1120, 1065, and more). Generate trial balance exports, produce tax-ready workpap

Configuration backup, drift detection, and golden config validation across Cisco IOS-XE/NX-OS, Juniper JunOS, and Arista EOS. Covers running vs startup comparison, config archival, section-level drift

Detect and prevent AI agent hallucinations during task execution. Use when: (1) an agent claims to have created files, commits, or artifacts — verify them, (2) an agent produces data reports or number

Analyzes an existing Claude Code skill and designs an optimal rules/ file structure. Covers three operations: (1) compressing SKILL.md by moving verbose content into rules modules, (2) encapsulating o

Parse and extract content from .docx, .pdf, and .txt documents. Extracts plain text and tables for analysis. Use when the user uploads a document file or asks to analyze/extract/read content from Word

Describe images, detect objects, extract text, and analyze webpages. Pass any image URL directly in your task. Responds in your language.

Control Microsoft Edge browser to fetch web pages and extract content. Use when the user wants to access a specific URL using Edge browser instead of Chrome, or when regular web fetching tools fail du

Use this skill when the user wants to export local WeRead records, normalize WeRead data, analyze reading preferences from WeRead history, or get book recommendations grounded in WeRead reading behavi

Evaluate startup ideas, business models, and product strategies against the 7 deadly failure antipatterns extracted from 1,749 dead startups that burned $535B+. Use when the user is evaluating a start

Token analysis and accumulation detection for Base, Ethereum, and other EVM chains. Use when searching for trending tokens, identifying accumulation patterns (buy:sell ratios), analyzing specific toke

Security scanner for OpenClaw skills. Detects malicious patterns, suspicious URLs, and install traps before you install a skill. Use before installing ANY skill from ClawHub or external sources.

Comprehensive security audit with 100 iterations (~30-60 min). Use when user says 'security audit', 'ralph security', 'weekly security check', 'audit this project', 'new project security review', or '

Run LLM Signal GEO analyst workflows from OpenClaw. Use when you need to fetch deterministic GEO action plans, check site health status, and execute/review hosted or self-hosted agent workflows with a

Apple Search Ads (ASA) specialist skill for iOS app paid user acquisition. Use this skill whenever the user mentions Apple Search Ads, ASA campaigns, app install campaigns, keyword bidding for apps, C

Detect config drift between required local env keys and a Render service before deploy; fails when required keys are missing remotely.

Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details fo

根据考试日期与科目列表，把复习主题均摊到考前每一天，生成 Markdown 日程表（可打印勾选）。 Use when: 期末周、多门课冲刺；用户说「复习排期」「考前两周计划」。 NOT for: 精确到小时的闹钟；代替个人学习习惯诊断。

Fetch clean, agent-optimized Markdown from any URL using the markdown.new service. Use when web_fetch or browser fails to provide clean content, or when you need a token-efficient version of a web pag

Intelligent network quality analysis with adaptive loading strategies. Detects connection type (2g/3g/4g), bandwidth, RTT, and save-data mode, then automatically triggers appropriate optimization work

Install, wire, and verify the 699pic enterprise MCP server from the GitHub repository https://github.com/st699pic/st-ent-mcp . Use when the user asks to 安装 st-ent-mcp、接入 699pic MCP、配置 OpenClaw/Claude/

Use A-MAP (Agent Mandate Protocol) to verify incoming agent requests, sign outgoing requests, and delegate permissions to sub-agents. Covers the full cryptographic authorization flow for AI agent-to-a

Route tasks to verified human workers worldwide via Loopuman. Use when AI alone can't handle verification, translation, content moderation, image labeling, local knowledge, or subjective judgment. Res

Scan websites, markdown files, and HTML files for broken links (dead links). Use when checking a website for 404s, validating links in documentation or README files, auditing link health before a depl

Use when a user proposes a product idea, feature concept, or product plan that needs logical stress-testing. Trigger phrases: challenge this idea, stress test my product, poke holes in this, is this

Perform comprehensive security audits on skills to identify vulnerabilities, unsafe patterns, and compliance issues. Use when auditing skills for security, checking for hardcoded secrets, injection ri

Use GLM-4.7V's multimodal grounding capability to detect and locate objects/text in images. Activate when user asks to find, locate, detect, or ground specific objects, text, UI elements, or regions i

Lightweight operational audit logging for AI assistants, agent workspaces, and personal automation systems. Use when you need a structured way to record high-value actions such as installs, config cha

Meta-skill for iterative, hypothesis-driven deep research using deepresearchwork, tavily-search, literature-search (Semantic Scholar mapping), and perplexity-deep-search. Use when the user needs multi

Lightweight Shopify order invoicing and inventory operations workflow for detecting new orders, preparing invoice-ready billing data, updating stock tables, and producing simple monthly summaries. Use

Advanced Twitter search and social media data analysis. Fetches tweets by keywords using Twitter API, processes up to 1000 results, and generates professional data analysis reports with insights and a

Audit an OpenClaw agent's behavior-layer rules and prompt sources to find drift, redundancy, conflict, loss of focus, and weak behavior guidance. Use when reviewing an agent's core behavior files, any

Plan multi-waypoint journeys with route optimization, feasibility analysis, and time budget constraints. Use when you need to plan trips with multiple stops or check if an itinerary is achievable.

Deep coding multi-agent development system. Use when the user wants to build software projects using the Orchestrator to Builder to Reviewer workflow, mentions deep coding, multi-agent collaboration,