Skill rating

Audit an unfamiliar codebase and map architecture, user-facing features, maturity, and risks. Use when the user asks to inspect a repo, summarize the stack, explain structure, list implemented feature

Turn consequential choices, uncertain claims, recurring failures, serious learning, and evidence-bearing reviews into provisional judgments, discriminating tests, and user-owned action. Use explicitly

Format, audit, and polish academic references in APA 7th style, including in-text citations, DOI/URL cleanup, and correction tables for student papers.

Real-time war intelligence monitoring and emergency alert system for conflict zones. Use when user needs to track military conflicts, receive emergency alerts, monitor evacuation options, or assess sa

Review AI video production packages for creative consistency, asset provenance, platform metadata, disclosure wording, and publishing readiness. Use when a user asks whether a video package is ready f

Manage Tailscale tailnet from chat. Check status, list devices, ping hosts, run network diagnostics, check serve/funnel config. All public IPs are automatically masked in output (after JSON parsing, n

Plan, generate, insert, and hand off evidence-safe illustrations for reviewed long-form Markdown articles. Use when a WeChat, Zhihu, blog, or other long-form draft needs an illustration decision, imag

Deploy a legal contract review pipeline with 3 agents. Use this skill when: 1. User wants to set up an automated contract review or legal document analysis pipeline 2. User is configuring an extractor

Use when building, auditing, or simplifying an AI coding-agent harness, especially when the current runtime has unclear config precedence, weak tool permissions, hidden product-only behavior, or poor

Find and qualify company websites by their detected technologies using Crawlora's tech-stack dataset and live website checks. Use for technology-based account lists, integration targeting, or qualifyi

Use this skill when a K-12 teacher, instructional coach, or curriculum designer needs a standards-aligned lesson plan for a specific subject, grade, and duration. Produces a complete lesson plan with

Signed access control for your OpenClaw agent. Wraps MCP tool calls through protect-mcp to add per-tool policies, signed receipts, and trust tiers. Every action your agent takes produces a cryptograph

AI Agent 安全与绿色运维顾问。合并 EcoCompute（GPU 能耗优化）与 OpenClaw/Bagman（安全密钥管理）， 提供 LLM 推理部署的能效分析、密钥安全管理、泄露防护和注入防御一体化方案。 Use when handling GPU energy optimization for LLM inference, secure key management for AI a

Check macOS hardware health: CPU usage, RAM pressure, disk space, temperatures, and top processes. Returns a quick status summary or full breakdown. USE WHEN: User or agent wants to know if the Mac i

Audit food safety plans, HACCP records, and inspection reports against Codex HACCP principles and ISO 22000 before release. Flags nonconforming hazard analyses, CCP limits, and verification records wi

Optimize conversion rates with funnel analysis, A/B testing, statistical significance, and compliance-safe experiments.

Guides project ideation via Socratic questioning to produce a validated brief. Use before specification when requirements are unclear

Production-ready multi-agent orchestration system for OpenClaw. Implements Coordinator Mode with real parallel worker spawning via sessions_spawn, XML task notifications, state persistence, and four-p

Use when implementing or reviewing frontend server-state flows: typed queries, request caching, invalidation, mutations, optimistic updates, infinite queries, prefetch, SSR hydration, or API-layer int

Use AgentPMT without an account: connect OpenClaw and autonomous AI agents to AgentPMT tools, workflows, skills, agent-to-agent work, and paid capabilities through a revocable AgentAddress with credit

When the user needs a comprehensive marketing plan for a client, a company they advise, or their own product. Also use when the user mentions "marketing plan," "growth plan," "GTM plan," "go-to-market

Review a Java Maven project delivered as a ZIP archive or a GitLab repository URL for code规范, naming, module boundaries, maintainability problems, duplicated logic, structure issues, and整改建议. Use when

Automated QA testing for web apps using local browser automation. Runs entirely on your machine — no data leaves, no cloud services, no external servers. Level 1 (smoke tests) needs only a URL. Level

Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification

Multi-temporal shoreline change rate analysis. Generates transects, computes Endpoint Rate (EPR) and Linear Regression Rate (LRR), and identifies erosion hotspots. Use when monitoring coastline retrea

Research TikTok Creative Center Top Ads by brand, market, industry, and objective through Crawlora. Use for competitor-ad comparisons, creative briefs, messaging and format analysis, and inspection of

从想法到 Skill 文件的全流程创建器。通过多轮对话帮助用户设计、打磨并生成高质量的 Agent Prompt， 最终输出可直接使用的多平台 Skill 文件（OpenClaw、Claude Code、Cursor、Cline 等）。 Full-cycle Skill creator from idea to file. Helps users design, iterate, and gene

OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. Use it to verify factual answers with live search results and explicit source handling.

帮 HR 做定薪判断、band 对标、市场调研摘要，以及个税社保公积金申报前检查，先看值不值，再看会不会出风险。 / Help HR teams with compensation review, band and market checks, and payroll filing prechecks.

Comprehensive AI writing pattern detection and removal toolkit for Chinese and English prose. Use when drafting, editing, reviewing, or scoring text to eliminate AI-generated writing patterns. Covers:

Create, review, illustrate, and format WeChat Official Account articles through Pixmind's private content engine, then copy the rich article into the WeChat editor. Use for 公众号选题、大纲、正文、文章审核、配图规划、公众号排版

Detect and quantify urban expansion from multi-temporal built-up rasters. Use when the user wants to analyze changes, compare multi-temporal rasters, compute indices, or generate assessment reports.

Learning optimizer - analyze study patterns, identify inefficiencies, suggest optimizations for better learning outcomes

Lightweight HTTP endpoint health checks with curl. Use when an agent needs to (1) verify one or more URLs are reachable, (2) collect status codes, TLS info, and timing, or (3) loop-check a service dur

Generate brand names with domain checks and analysis. Use when naming a startup, checking domain availability, or brainstorming product names.

Persistent, consensus-validated memory for AI agents via SAGE MCP server. Gives you institutional memory that survives across conversations — memories go through BFT consensus, carry confidence scores

Lint your Claude Code config for token waste. Checks CLAUDE.md, hooks, skills, and commands. Gives health score and actionable fixes. Use when user asks about config optimization or token waste.

Fast lightweight verification pass for recent work. Use proactively after medium or large tasks, coding passes, app changes, or long replies when you need a quick check for missed asks, partial comple

Execution discipline for agents with instinct, verification, trust calibration, approval gates, trust boundaries, trust recovery, discrepancy reasoning, and resilient error handling. Use when you want

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchm

Detect forest disturbance from multi-temporal NDVI. Use when the user wants to analyze changes, detect hazards, or generate assessment reports.

Bind and verify a public custom domain for an existing Volcengine TOS bucket. Use when users mention TOS/object-storage custom domains, storage.<domain>, bucket public URLs, ICP filing passed but the

Real-time online/offline/busy presence tracking for agent fleets using ping and pub/sub. Use this skill when: 1. You need to track which agents are online/offline/busy 2. You need to broadcast presenc

Query STRING database for protein-protein interactions with confidence scores. Use this skill when: (1) Finding interaction partners for a protein of interest, (2) Retrieving confidence scores for pro

Session retrospective that analyzes conversation history to produce structured feedback for both user and LLM. Use this skill whenever the user says '复盘', 'retrospect', '批评与自我批评', 'session review', 'r

Compare and audit two or more beauty or cosmetic offers: cash landed price, bundle split, gift net value, and evidence grade. Use for sale-season, live-stream, or duty-free price checks.

Assesses architecture decisions, ADR compliance, and coupling

Self-verification skill for arifOS. Activates when: (1) the agent is about to return a consequential answer; (2) a claim has been made that requires evidence cross-check; (3) Arif asks "verify", "chec

Use Peekaboo for macOS desktop GUI automation, screen understanding, and MCP-backed local app control. Trigger when the user wants to inspect or control native macOS apps, Finder, Notes, Xcode, Termin

Stateful cron system for OpenClaw with persistent memory, change detection, smart routing, token budget tracking, and self-healing. Requires 'openclaw' and 'gog' CLIs. Broad I/O capabilities (file rea