skill▌

Comprehensive guide for creating modular skills that extend Claude's capabilities with specialized knowledge and workflows. \n \n Skills consist of a required SKILL.md file with YAML metadata and markdown instructions, plus optional bundled resources (scripts, references, and assets) organized in a three-level loading system to manage context efficiently \n Follow a six-step creation process: understand concrete usage examples, plan reusable contents, initialize with the provided script, edit SK

Fetch and analyze real-time news from 28 global, AI, finance, and podcast sources with deep Chinese-language reports. \n \n Supports 28 sources across six categories: global news (Hacker News, GitHub, Weibo), AI/tech (Hugging Face Papers, newsletters), finance (WallStreetCN), podcasts, and essays \n Three-step universal workflow: fetch data with keyword filtering, generate unified markdown reports in Simplified Chinese, and save to timestamped directories \n Pre-configured daily briefing profile

Custom Playwright scripts for any browser automation task, with auto-detected dev servers and visible browser execution. \n \n Auto-detects running localhost dev servers; writes test scripts to /tmp to avoid project clutter \n Supports responsive design testing, login flows, form filling, link validation, and screenshot capture across multiple viewports \n Includes helper utilities for safe clicks, typed input, cookie banner handling, and table data extraction \n Configurable custom HTTP headers

Create hybrid agent skills for Microsoft technologies with local knowledge and dynamic Learn MCP lookups. \n \n Generates modular skill packages with frontmatter, reference documentation, and working code examples for any Microsoft technology (Azure, .NET, M365, Semantic Kernel, etc.) \n Uses three-phase investigation workflow: scope discovery via search, core content fetching, and depth exploration for best practices and troubleshooting \n Balances local storage of foundational concepts and com

Validate and standardize SKILL.md files against the Agent Skills specification. \n \n Validates frontmatter fields (name, description, allowed-tools, metadata) and enforces naming conventions, length constraints, and format rules \n Converts legacy skill formats to standard structure, including section heading normalization and directory layout alignment \n Provides templates and step-by-step guidance for creating new skills, improving descriptions for reliable triggering, and batch-validating s

Pre-install security vetting for OpenClaw skills using a structured red-flag checklist. \n \n Evaluates metadata, permission scope, and content against critical, warning, and informational risk categories \n Detects typosquatting, credential file references, obfuscated content, and command injection patterns \n Flags high-risk permission combinations like network + shell that enable data exfiltration \n Produces a standardized vetting report with verdict (Safe/Warning/Danger/Block) and install r

$22

Version: 2.1.0 | Last Updated: 2025-01-27

$23

Use this skill when you need to create a new skill under skills/, or when an existing skill needs a material authoring refresh instead of a small copy edit.