socialadsmentor/sam-agentic-harness/anthropic-courses

Claude Code and agent skill by socialadsmentor/sam-agentic-harness

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Reference for Anthropic''s 5 official educational courses (github.com/anthropics/courses): API fundamentals, prompt engineering, real-world prompting, prompt evaluations, and tool use. Use when the user asks how to LEARN Claude development, wants a structured course, asks about Anthropic''s official training material, or wants the notebooks cloned and run locally. Triggers: anthropic courses, claude course, learn the claude api, prompt engineering course, tool use tutorial.

Install

npx vskill@latest install socialadsmentor/sam-agentic-harness/anthropic-courses

SKILL.md

The same SKILL.md was published earlier as socialadsmentor/sam-agentic-harness/anthropic-courses.

Anthropic Courses Reference

Source: https://github.com/anthropics/courses 5 structured educational courses for learning to build with Claude.

How to Access

Clone the repository and run notebooks locally:

bash
git clone https://github.com/anthropics/courses.git

Courses use Claude 3 Haiku by default to minimize API costs. You can substitute other models.


Course 1: Anthropic API Fundamentals

Path: anthropic_api_fundamentals/ Recommended: Complete first

Teaches the essentials of working with the Claude SDK.

NotebookTopic
01_getting_started.ipynbGetting an API key, first API call
02_messages_format.ipynbMessages format and conversation structure
03_models.ipynbAvailable models and their capabilities
04_parameters.ipynbModel parameters (temperature, max_tokens, etc.)
05_Streaming.ipynbStreaming responses for real-time output
06_vision.ipynbMultimodal prompts with images

Course 2: Prompt Engineering Interactive Tutorial

Path: prompt_engineering_interactive_tutorial/Anthropic 1P/ Recommended: Complete second

Comprehensive step-by-step guide to key prompting techniques. Also available as an AWS Workshop.

NotebookTopic
00_Tutorial_How-To.ipynbHow to use the tutorial
01_Basic_Prompt_Structure.ipynbBasic prompt structure fundamentals
02_Being_Clear_and_Direct.ipynbWriting clear, direct prompts
03_Assigning_Roles_Role_Prompting.ipynbRole prompting techniques
04_Separating_Data_and_Instructions.ipynbSeparating data from instructions
05_Formatting_Output_and_Speaking_for_Claude.ipynbOutput formatting and prefilling
06_Precognition_Thinking_Step_by_Step.ipynbChain-of-thought / step-by-step reasoning
07_Using_Examples_Few-Shot_Prompting.ipynbFew-shot prompting with examples
08_Avoiding_Hallucinations.ipynbTechniques to reduce hallucinations
09_Complex_Prompts_from_Scratch.ipynbBuilding complex prompts from scratch
10.1_Appendix_Chaining Prompts.ipynbPrompt chaining techniques
10.2_Appendix_Tool Use.ipynbIntroduction to tool use
10.3_Appendix_Search & Retrieval.ipynbSearch and retrieval patterns

Course 3: Real World Prompting

Path: real_world_prompting/ Recommended: Complete third

Learn how to incorporate prompting techniques into complex, real-world prompts. Also available in a Google Vertex version.

NotebookTopic
01_prompting_recap.ipynbRecap of prompting fundamentals
02_medical_prompt.ipynbBuilding a medical domain prompt
03_prompt_engineering.ipynbAdvanced prompt engineering techniques
04_call_summarizer.ipynbBuilding a call summarization system
05_customer_support_ai.ipynbCustomer support AI implementation

Course 4: Prompt Evaluations

Path: prompt_evaluations/ Recommended: Complete fourth

Learn how to write production prompt evaluations to measure prompt quality.

ModuleTopic
01_intro_to_evals/Introduction to evaluations
02_workbench_evals/Using the Anthropic Workbench for evals
03_code_graded_evals/Code-graded evaluation methods
04_code_graded_classification_evals/Classification-specific code-graded evals
05_prompt_foo_code_graded_animals/PromptFoo code-graded evals (animals example)
06_prompt_foo_code_graded_classification/PromptFoo code-graded classification
07_prompt_foo_custom_graders/PromptFoo custom graders
08_prompt_foo_model_graded/PromptFoo model-graded evaluations
09_custom_model_graded_prompt_foo/Custom model-graded evals with PromptFoo

Course 5: Tool Use

Path: tool_use/ Recommended: Complete fifth

Everything you need to implement tool use successfully in your workflows with Claude.

NotebookTopic
01_tool_use_overview.ipynbOverview of tool use concepts
02_your_first_simple_tool.ipynbCreating your first simple tool
03_structured_outputs.ipynbGetting structured outputs via tools
04_complete_workflow.ipynbComplete tool use workflow
05_tool_choice.ipynbControlling tool selection
06_chatbot_with_multiple_tools.ipynbBuilding a chatbot with multiple tools

Learning Path Summary

API Fundamentals (6 notebooks)
|
v
Prompt Engineering (13 notebooks)
|
v
Real World Prompting (5 notebooks)
|
v
Prompt Evaluations (9 modules)
|
v
Tool Use (6 notebooks)

Total: 39 notebooks/modules across 5 courses.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/socialadsmentor/sam-agentic-harness/anthropic-courses/badge)](https://verified-skill.com/skills/socialadsmentor/sam-agentic-harness/anthropic-courses)

Something wrong with this skill or its page? Tell us.