True LLMs / REGISTRY

Skills

AI agent skills, sourced from their real repositories. No fabricated scores, no claimed test results — see the scope note below.

Data verified Aug 24, 2026

Scope: compatibility below is what each skill's own source states, not an independent test — True LLMs hasn't run these against live agents yet. Marked confirmed by source where the repo says so, untested everywhere else.

Agent tool2 agents confirmed

MCP Builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

by AnthropicView →
Testing2 agents confirmed

Web Application Testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

by AnthropicView →
Utility2 agents confirmed

Skill Creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

by AnthropicView →
Coding2 agents confirmed

Frontend Design

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

by AnthropicView →
Coding2 agents confirmed

Claude API

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

by AnthropicView →
Data processing2 agents confirmed

PDF

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable.

by AnthropicView →
Documentation2 agents confirmed

Academy Guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub.

by AnthropicView →
Utility2 agents confirmed

Algorithmic Art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.

by AnthropicView →
Utility2 agents confirmed

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

by AnthropicView →
Utility2 agents confirmed

Canvas Design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece.

by AnthropicView →
Utility2 agents confirmed

Discernment Nudge

After a substantive answer or draft the user may act on — advice, drafted artifacts, estimates, analysis, factual claims, or a multi-step argument — invoke this before finalizing the reply and append 2-3 short follow-up questions that help the user check key facts, probe reasoning, and notice missing context.

by AnthropicView →
Documentation2 agents confirmed

Doc Co-Authoring

Guide users through a structured workflow for co-authoring documentation. Use when a user wants to write documentation, proposals, technical specs, decision docs, or similar structured content — context gathering, refinement and structure, then reader testing.

by AnthropicView →
Data processing2 agents confirmed

DOCX

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx) — tables of contents, headings, page numbers, letterheads, tracked changes, comments, and find-and-replace.

by AnthropicView →
Documentation2 agents confirmed

Internal Comms

A set of resources to help write internal communications using common company formats — status reports, leadership updates, newsletters, FAQs, incident reports, and project updates.

by AnthropicView →
Data processing2 agents confirmed

PPTX

Use this skill any time a .pptx or .potx file is involved — creating slide decks, pitch decks, or presentations; reading, editing, or combining existing presentations; working with templates, layouts, speaker notes, or comments.

by AnthropicView →
Utility2 agents confirmed

Slack GIF Creator

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts for requests like "make me a GIF of X doing Y for Slack."

by AnthropicView →
Utility2 agents confirmed

Theme Factory

Toolkit for styling artifacts with a theme — slides, docs, reports, HTML landing pages, etc. Ships 10 pre-set themes with colors and fonts, or can generate a new theme on the fly.

by AnthropicView →
Coding2 agents confirmed

Web Artifacts Builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). For complex artifacts requiring state management, routing, or shadcn/ui components.

by AnthropicView →
Data processing2 agents confirmed

XLSX

Use this skill any time a spreadsheet file is the primary input or output — opening, reading, editing, or fixing .xlsx/.xlsm/.xltx/.csv/.tsv files, creating a new spreadsheet, or cleaning messy tabular data into a proper spreadsheet.

by AnthropicView →