Skill rating

Audit Rust code for unsafe block usage — verify safety invariants, check FFI boundaries, review raw pointer operations, validate Send/Sync implementations, and detect unsound abstractions. Use when re

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-criti

Use when creating, reviewing, or restructuring frontend monorepos with pnpm workspace, Turborepo, Nx, multi-package dependency boundaries, task orchestration, package naming, or package publishing; Ch

Pure intelligence gathering for social media platforms (TikTok & Instagram). Use when an agent needs to discover trending hooks, analyze a competitor's strategy, or look up a specific creator's profil

Short alias for external-site-profile-learning. Use this when investigating, adding, validating, or debugging external website profiles for the 99idea Playwright browser demo.

Compress oversized videos into upload-ready files for creators, ecommerce teams, and operators while keeping practical clarity. Use when a video is too large for platform limits, review handoff, or fa

分析GitHub趋势榜和热门榜，提供技术趋势总结和创新项目介绍。 当用户询问GitHub趋势、热门项目、技术发展趋势、"今天有什么热门"、 "GitHub trending"、"github热门"、"开源趋势"、"技术风向"等话题时， 必须使用此skill获取GitHub官方Trending页面的数据，进行分析总结。 此skill适用于： - 想了解当前GitHub上什么项目最火 - 关注技术发展

Automatically use installed skills without being asked. Maintain a trigger table that maps contexts to skills, and enforce that every newly installed skill gets added to the table immediately. Use whe

Install, verify, repair, and diagnose GPT-Image-2 support for OpenClaw so agents can use model refs like hnbc/gpt-image-2 through the built-in image_generate tool. Use when a user wants to add GPT-Ima

You are a business analyst specialist with expertise in process optimization, workflow design, business transformation, and strategic. Use when: business process modeling and optimization, workflow de

Local-first memory retrieval for Agent/OpenClaw workspaces. Use when the user asks about prior work, decisions, dates, preferences, root causes, todo history, or "what changed" questions and you want

Multi-agent adversarial security review — 3 AI agents debate every finding, only real vulnerabilities survive

Resolve dual-perspective collaboration conflicts by classifying them into 5 types and applying targeted integration strategies. Use when two agents (or an agent and user) have different approaches to

Explain any code snippet or file in plain English. Paste code → get a clear explanation of what it does, how it works, and key concepts. Use when the user shares code and wants to understand it, learn

Scrape Amazon product data using Pangolin APIs. Use this skill when the user wants to: look up Amazon products by ASIN, search Amazon by keyword, check bestsellers/new releases, get product reviews or

Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'w

Guided setup and troubleshooting for installing, enabling, configuring, verifying, and updating @aramisfa/openclaw-a2a-outbound in OpenClaw.

GPU-accelerated document parsing and OCR via PaddleOCR-VL. Detects layout, recognizes Chinese/English text, tables, charts, and seals in images. Use when the user asks to OCR an image, extract text fr

Use when querying or analyzing Kubernetes Pod stdout/stderr logs, CCE LogConfig-collected application logs, Huawei Cloud LTS log streams, CCE audit logs for Pod deletion or workload change events, or

Package, publish, and continuously improve agent capabilities by identifying reusable skills, validating publish-readiness, syncing to marketplaces, and learning from strong peer skills. Use when the

Operate an already-open Hinge session in the browser or on iPhone to review profiles, triage the queue, analyze matches, draft respectful openers or replies, and execute explicit like, reply, or rose

Verify OpenClaw after upgrades against an operator-maintained model, cron, and channel ground truth. Use for report-only config integrity, provider liveness, cron integrity, session smoke tests, and c

Decode a suspicious message — text, email, call transcript, or DM — against the anatomy of known scam families, with a 🔴🟡🟢 read and the safe next move. Use when someone asks is this a scam, decode

Pressure-test a startup idea the way a sharp investor or co-founder would — problem, market, wedge, moat, why-now, and the fastest cheap way to test it. Use when asked to validate a startup idea, eval

Vet an agent skill before installing it — read the SKILL.md and any scripts for the red-flag patterns (credential access, obfuscation, exfiltration, prompt injection), audit its blast radius, and prod

Audit a Claude/Agent SKILL.md (or any AI skill / system prompt) for safety before installing or merging it. Use when asked to review a skill for security, check a prompt for injection, vet a community

Triage a vulnerability or scanner finding — assess real severity, exploitability, and how urgently to fix. Use when asked to triage a CVE, prioritize scanner/pentest findings, assess a vuln's risk, or

University final-exam review assistant for course profiling, materials ingestion, adaptive quizzes, strict grading, Feynman technique, Socratic tutoring, active recall, spaced repetition, visual expla

Review and finalize configuration topics through a structured item-by-item confirmation flow. Use when the user wants a documented configuration review flow, wants to逐条核对配置 or 逐项确认配置, or needs a proce

Use this skill whenever a user wants to verify whether content (text, images, audio, video, or documents) was created by AI; detect deepfakes or AI-synthesized voices; use tools like GPTZero, Turnitin

Use this skill when a medical-device regulatory-affairs specialist or RA manager needs to draft the Section 10 Substantial Equivalence Comparison for an FDA 510(k) under 21 CFR Part 807. Produces a DR

Use this skill when a product manager, engineering lead, or localization PM needs to audit a product surface for i18n / l10n readiness before engaging a translation vendor or committing to a new-local

Audit a game, feature, session, level, event, onboarding flow, reward sequence, or return-player experience through the lens of the peak-end rule. Use when evaluating which moments players are most li

Deep web information search and archival skill for comprehensive research on persons, organizations, or products. Uses multiple search engines (Baidu, Tavily, Multi-Search-Engine) plus browser-based c

Configure, deploy, and verify Huawei Cloud CCE to CCI 2.0 bursting for fast elastic capacity. Use when users ask to enable CCE elasticity to CCI, install or configure virtual-kubelet bursting addon, c

Use this skill when a project manager, program manager, or PMO analyst needs to update a RAID log (Risks, Assumptions, Issues, Decisions / Dependencies) from meeting notes, blocker reports, or decisio

PDF parsing tool for AI/RAG. Convert PDF to Markdown, JSON, HTML with layout preservation, bounding boxes, and image extraction. Use when you need to extract content from PDF files for AI processing,

Audit and rewrite Chinese or English content to remove AI tone ("AI-isms"), then pull it toward a target human voice. Use this skill when asked to "remove AI tone," "sound human," "去 AI 味," "说人话," "活人

Use this skill when a medical biller, denials specialist, revenue-cycle analyst, or coder needs to convert a denied insurance claim (EOB / 835 ERA) into an appeal letter. Maps CARC/RARC denial codes t

Activate when: user says 'I'm stuck and don't know why', 'I keep making the same mistake', 'my analysis feels right but I'm not sure', 'am I solving the right problem', 'I should understand this but I

Install, enable, verify, pair, and manage PrivateClaw OpenClaw sessions, preferring same-conversation /privateclaw QR replies and falling back to the local CLI when needed.

⚠️ HIGH PRIVILEGE SECURITY AUDIT SKILL Performs comprehensive security auditing for OpenClaw deployments. Requires system-level access for legitimate security scanning purposes. All operations are re

Scan, tag, validate, and catalog files using the Ghost Catalog semantic file header system (SOM-XXX-NNNN-vX.X.X). Use when: discovering untagged files, onboarding to a new codebase, maintaining catalo

Use when working with .phiproto files, PhiProto messages, or converting between .phiproto and CSV with the bundled phicli binary. Trigger on requests to inspect, decode, encode, validate, or explain P

USE WHEN user types /fund-tracker or wants to check fund purchase availability, daily purchase quota, fee, and changes versus the previous run. Uses local AKShare-based tracker presets under <skill-ro

Continuous self-improvement through systematic logging, pattern detection, and behavioral updates. Use when: the owner corrects you, a task fails, you discover a better approach, you notice a recurrin

Expert-level code review for React Native and native iOS/Android applications. Use when reviewing mobile codebases for architecture, performance, security, or preparing for acquisition due diligence.

Use when creating or reviewing Next.js 14+ App Router projects, file routes, layouts, server/client component boundaries, SSR/SSG/ISR, streaming, metadata, middleware, server actions, or Next-specific

Analyze and optimize cloud costs across AWS, Azure, and GCP. Use when evaluating cloud spending, identifying cost optimization opportunities, analyzing cloud bills, rightsizing instances, finding unus

AI-powered financial knowledge management. Search financial statements, audit findings, tax documents, and treasury records with structured extraction.