Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
- official
- workshops
- anthropic
- managed-agents
Anthropic's official gallery of standalone HTML artifacts — code reviews, slide decks, status reports and mini editors with zero build step.
Companion gallery to Anthropic's engineering post on HTML as a flexible output format for agents: every example is a single self-contained .html file — no build step, no dependencies — demonstrating a use case from code review, design systems and component variants to slide decks, status and incident reports, PR write-ups, flowcharts, feature explainers, and small interactive editors like a triage board, feature-flag console, or prompt tuner.
When you want Claude's output to be an artifact someone can actually open and click — reports, reviews, decks, mini-tools — instead of markdown. Copy these as starting points or prompt exemplars.
Nothing to install or build: git clone https://github.com/anthropics/html-effectiveness open index.html # full categorized index; or open any numbered file directly
A gallery, not a library — nothing here is importable code. All product names, data and scenarios are fictional placeholders ("Acme").
Repository
anthropics/html-effectivenessCharted
Anthropic's official "Code with Claude" workshop materials — nine hands-on courses on skills, MCP, evals and Claude Managed Agents.
Anthropic's announcement of Fable 5.1 and Mythos 5.1 — one base model, two guardrail postures.
Anthropic's canonical essay on agent design — workflows vs agents, and five composable patterns.