# anthropics/cwc-workshops

Repository: https://github.com/anthropics/cwc-workshops
Canonical: https://ross.abutalabs.com/products/cwc-workshops
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-20T21:44:46+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 35, longevity 8
- inputs: {"age_days": 119, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2026, forks 587 (observed 2026-08-28T04:06:06.861835+00:00)

## What it is
Workshop materials from Anthropic's 'Code with Claude' events, covering building and evaluating agents with Claude Managed Agents, Skills, and MCP. It includes hands-on exercises like multi-agent decomposition, memory persistence, eval-driven development, and agent competitions.

## Use cases
- learn to build agents with Claude Managed Agents
- hands-on workshop for MCP and Claude skills
- learn eval-driven LLM agent development
- practice decomposing a monolithic prompt into multi-agent systems
- learn to add cross-session memory to an AI agent
- find the best model and inference parameters for quality per dollar
- build an SRE agent that greps logs and calls local tools

## When to choose
- you want structured, hands-on exercises for Claude agent development
- you're running a workshop or self-study on Skills, MCP, and Managed Agents
- you want practical patterns for LLM evals and multi-agent architectures

## When to avoid
- you need a maintained, production-ready library or framework
- you expect community contributions or bug fixes - the repo explicitly accepts none
- you use non-Anthropic LLMs exclusively, since materials are Claude-centric

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: agent-framework, mcp, prompt-engineering, rag, llm-inference
- domain: artificial-intelligence, large-language-models, tutorials, developer-tools
- platform: python, cross-platform
- tags: claude, claude-code, workshops, managed-agents, llm-evals, multi-agent-systems, anthropic, educational-materials, ai-agents, nodejs

## Member repositories
- anthropics/cwc-workshops (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.861835+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:59:43.602305+00:00, confidence not recorded.
  - readme: https://github.com/anthropics/cwc-workshops (fetched 2026-08-28T04:06:06.861835+00:00, sha 21dc7dd6957e)
- Data as of 2026-08-30T08:39:29.467469+00:00.