Matt Pocock ships /teach agent skill

// 1h agoTUTORIAL

Matt Pocock ships /teach agent skill

Matt Pocock shared a step-by-step guide for developers seeking to transition from junior to senior using coding agents like Claude Code. The process involves installing his custom /teach skill, setting up a dedicated workspace directory, and running the terminal-based AI agent.

// ANALYSIS

Modular, instruction-based "skills" are the new IDE configuration files, shifting developer productivity from raw syntax writing to orchestrating agentic behavior.

* The `/teach` skill targets the critical learning curve of junior developers by embedding structured mentorship directly inside terminal-based agents.

* Standardizing agent guardrails through commands like `/teach` or `/tdd` prevents "vibe coding" and enforces software engineering discipline.

* Leveraging a dedicated CLI (`npx skills`) makes prompt injection and agent setup easily shareable, composable, and version-controlled.

// TAGS

agentdevtoolclaude-codeprompt-engineeringsoftware-engineeringopen-source

DISCOVERED

1h ago

2026-06-10

PUBLISHED

2h ago

2026-06-10

RELEVANCE

8/ 10

AUTHOR

mattpocockuk

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE51m ago

OpenMed 1.5.5 adds batch PII processing

OpenMed version 1.5.5 introduces batch PII extraction and de-identification alongside REST model unload and keep-alive controls. The update also improves Swift-based on-device acceleration and clinical OCR document handling on Apple Silicon.

OPEN SOURCE58m ago

A new open-source repository, train-llm-from-scratch, provides a step-by-step guide to building and training a transformer model from raw data on a single GPU.

The train-llm-from-scratch repository by Fareed Khan provides an end-to-end, open-source guide to building a transformer model from scratch. Unlike typical tutorials that focus solely on the neural network architecture, this project walks developers through the entire pipeline: downloading and parsing raw text data, implementing tokenization, structuring the transformer layers, training the model on a single GPU, and running inference. It aims to make the underlying mechanics of modern LLMs accessible and practical for individual developers.

NEWS1h ago

Claude Code creator highlights shift to agentic loops

Boris Cherny, the creator of Anthropic's Claude Code, shared that his engineering workflow has shifted from writing traditional prompts to building autonomous loops. Developers now build agentic systems that run continuously to discover, execute, and verify tasks independent of constant user input.

Matt Pocock ships /teach agent skill