Skill search for "anthropic".

Create distinctive, production-grade frontend interfaces with high design quality. Use when building web components, pages, artifacts, posters, or applications. Generates creative, polished UI code that avoids generic AI aesthetics.

Read, write, split, merge, rotate, watermark, encrypt and OCR PDF files. Use whenever the user mentions a .pdf file or wants to produce one. Includes pypdf, pdfplumber, reportlab and command-line workflows.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Supports Python (FastMCP) and Node/TypeScript (MCP SDK).

Create new skills, modify existing skills, run evals, benchmark performance, and optimize a skill's description for better triggering accuracy. The meta-skill for building SKILL.md skills.

Create, edit and extract content from Microsoft Word (.docx) files. Use whenever the user works with .docx documents, asks to produce a Word file, or needs to manipulate document structure, styles, or tracked changes.

Read, write, and analyse Microsoft Excel (.xlsx) files. Use whenever the user mentions a .xlsx file, asks to produce a spreadsheet, or wants to read/write cells, formulas, sheets, or formatting.

Build self-contained interactive web artifacts (single-file HTML+CSS+JS apps) like calculators, visualisers, mini-tools and demos. Use when the user wants a runnable web artifact rather than a full project.

Use the Claude API effectively: messages endpoint, streaming, tool use, vision, prompt caching, batches, files. Use when the user is building against the Anthropic API or troubleshooting requests.

Create and edit PowerPoint (.pptx) presentations. Use when the user mentions a .pptx file, asks to build a slide deck, or needs to manipulate slides, layouts, or speaker notes.

Design visual canvases including posters, social cards, illustrations, and graphics using HTML/CSS/SVG. Use when the user asks for visual design output other than code-driven web UIs.

Generate algorithmic and generative art with HTML5 Canvas, SVG, p5.js patterns and shaders. Use when the user wants creative coding, generative visuals, or mathematical art.

Generate cohesive design themes (color palettes, typography, spacing scales) and apply them as design tokens across a codebase. Use when the user wants to rebrand, retheme, or unify styling.

Apply and enforce brand guidelines across designs and content: voice, tone, color, type, logo placement, and asset rules. Use when the user references a brand, style guide, or visual identity.

Author end-to-end and integration tests for web applications using Playwright, Cypress and the like. Use when the user wants to add tests, debug flaky behaviour, or set up CI test pipelines.

Collaboratively write, edit and structure long-form documents (specs, RFCs, papers, reports) with attention to clarity, tone and consistency. Use when the user is drafting or revising long-form prose.

Draft clear, well-structured internal communications: announcements, change docs, status updates, post-mortems. Use when the user is writing to colleagues, teams, or leadership.

Create small, looping animated GIFs suitable for Slack reactions and emoji using HTML/CSS animation captured to GIF. Use when the user wants a custom Slack reaction or emoji.