EasyGlobe Skills
Meta & Tools Skills Hub
A shared meta & tools category page for Claude Skills, Codex Skills, Gemini Skills, Kimi Skills, GLM Skills, and team workflows.
How to choose
Review the agents and workflows covered by this category, then open a skill detail page to check task boundaries, README notes, setup requirements, and expected outputs.
How To Use This Skill
Use this category to organize agent-ready skills for skill creation, prompt libraries, agent routing, tool evaluation, and reusable workflow systems. Each page follows the same skills template so teams can compare categories quickly and adapt the workflow to Claude, Codex, Gemini, Kimi, GLM, or internal SOPs.
Usable AI Agents and Models
Works well as
Meta & Tools Skills
Popular Meta & Tools Skills
Start with the skills in this Meta & Tools category that are easiest to evaluate first. Each detail page includes a download link, the original Skill URL, and notes for adapting the workflow to Claude, Codex, Gemini, Kimi, GLM, or a team SOP.
Handoff Skill
Compresses a session into a markdown doc to continue in a fresh session or hand off to a different agent.
Use for Handoff, Markdown, Session tasks that should become a reusable agent workflow.
Skill Creator Skill
Builds new skills interactively so you can extend Claude yourself.
Use for Skill authoring, Meta tool tasks that should become a reusable agent workflow.
Caveman Skill
Cuts output tokens by stripping narration while keeping every technical fact intact.
Use for Token saving, Communication tasks that should become a reusable agent workflow.
Curated Skill Resources
Useful Skill, MCP, Agent, and finance API resources imported from the FynnZhang designer tool library and manual curation.
Compresses a session into a markdown doc to continue in a fresh session or hand off to a different agent.
Builds new skills interactively so you can extend Claude yourself.
Cuts output tokens by stripping narration while keeping every technical fact intact.
Create, edit, and analyze Word documents
Create, edit, and analyze PowerPoint presentations
Create, edit, and analyze Excel spreadsheets
Design visual art in PNG and PDF formats
Frontend design and UI/UX development tools
Build complex claude.ai HTML artifacts with React and Tailwind
Create MCP servers to integrate external APIs and services
Test local web applications using Playwright
Guide for creating skills that extend Claude's capabilities
Architecture and usage patterns for agents, workflows, memory, and servers
PostgreSQL best practices for Supabase
Developing Gemini-powered apps on Google Cloud Vertex AI using the Gen AI SDK
Best practices for building Stripe integrations
Performance optimization for React Native apps from Callstack
GitHub workflow patterns for PRs, code review, branching
Set up Firecrawl credentials and SDK in a project for the first integration
Integrate Firecrawl `/search` for query-first discovery with optional content hydration
Programmatic video creation with React
Next.js best practices and recommended patterns
Build sandboxed applications for secure, isolated code execution on Workers
Build UI components with shadcn/ui
Iterative design-to-code feedback loop
Search and extract data from Burp Suite project files
Security-focused diff review with git history analysis
Static analysis toolkit with CodeQL, Semgrep, and SARIF
Find similar vulnerabilities via pattern-based analysis
Deploy apps to Cloudflare using Workers, Pages, and platform services
Build and test web games iteratively using Playwright with time-stepping
Read, create, and edit .docx documents with formatting and layout fidelity
Generate and edit images using OpenAI's Image API for projects
Manage issues, projects, and team workflows in Linear
Convert conversations into structured, searchable Notion wiki entries
Prep meetings by pulling Notion context and tailoring agendas
Research Notion content and synthesize findings into structured briefs
Convert Notion specs into linked implementation plans and tasks
Provide authoritative guidance from OpenAI developer documentation
Read, create, and review PDFs with layout and visual formatting integrity
Automate real browser interactions for navigation, forms, and scraping
Generate repo-specific threat models identifying trust boundaries
Generate, remix, and manage short video clips via OpenAI's Sora API
Create, edit, analyze, and visualize spreadsheets with formulas
Transcribe audio files to text with optional speaker diarization
Stage, commit, push code, and open a GitHub pull request via CLI
Build, scaffold, and troubleshoot ChatGPT Apps SDK apps with MCP server and widget UI
Use the Figma MCP server to fetch design context and translate nodes into production code
Translate Figma designs into production-ready code with 1:1 visual fidelity
Prerequisite skill for every use_figma tool call — write/read actions in Figma context
Create visually strong landing pages, websites, and app UIs with restrained composition
Persistent browser and Electron interaction via js_repl for iterative UI debugging
Create and edit .pptx presentation decks with PptxGenJS
Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights.
Core Workflows
Context and input setup
Define the source material, constraints, goal, expected output, and quality bar for meta & tools work.
Agent execution workflow
Run the task through Claude Skills, Codex Skills, Gemini Skills, Kimi Skills, GLM Skills, or another agent with clear checkpoints.
Review and reusable handoff
Package the result into a checklist, reusable prompt, operating note, or implementation handoff.
Typical Outputs
Frequently Asked Questions
Can Meta & Tools skills be used with Claude, Codex, Gemini, Kimi, and GLM?
Yes. The category is written as a model-flexible skills hub entry, so the same workflow can become a Claude Skill, Codex Skill, Gemini Skill, Kimi Skill, GLM Skill, or team SOP.
Why use one template for every category page?
A shared template makes the directory easier to scan: every category shows supported agents, core workflow steps, expected outputs, and FAQs in the same structure.