Prompt-Me Skill
A developer has created an open-source agentic skill called 'prompt-me' that flips the typical AI writing workflow: instead of the user prompting an AI to write text, the AI prompts the user to write,…
A developer has created an open-source agentic skill called 'prompt-me' that flips the typical AI writing workflow: instead of the user prompting an AI to write text, the AI prompts the user to write,…
A developer's controlled comparison of two AI debugging workflows found that an agent using the Superpowers systematic-debugging skill missed a real bug despite following a structured method, while Ex…
Anthropic's Claude Code introduced a real-time multiplayer, agentic planning environment called Chopin, which aims to address limitations in current AI planning tools by enabling interactivity, team c…
Matt Pocock, a developer and educator, has released a set of AI coding agent skills designed to help engineers use tools like Claude Code and Codex for real engineering work, addressing common failure…
A new community-maintained open directory is tracking spec-driven development frameworks and real-world projects to evaluate their effectiveness, featuring Matt Pocock's composable agent skills built …
A developer presented a planning workflow for building software with generative AI, combining agent skills from Matt Pocock and Ryan Singer to generate a PRD and implementation plan. The developer fou…
Matt Pocock introduced Sandcastle, an AI agent orchestration tool that uses Git worktrees to run multiple AI agents in parallel without version control conflicts. The tool, available on GitHub and ins…
Matt Pocock's coding workflow has been turned into a coding-agent workbench, as announced in a Show HN post. The workbench is designed to integrate with Pocock's development practices, offering a spec…
A developer proposed a new skill for the to-architecture workflow that converts accepted specs into concrete implementation architectures. The skill instructs agents to read issue-tracker tickets, use…
Matt Pocock, creator of the AI Skills for Real Engineers project with over 220,000 GitHub stars, released a new skill called /wayfinder to help developers and AI agents navigate projects where the end…
Anthropic's Claude Code, a terminal-based agentic coding harness that understands whole codebases and handles git workflows, tops a new index of the best vibe coding tools. The index, which is ranked …
Matt Pocock released 'AI Skills for Real Engineers,' a suite of AI skills for AI harnesses like Claude Code, designed to improve AI tooling effectiveness for software engineers. The skills include /gr…
A developer shares a workflow using Matt Pocock's AI coding skills to improve agentic coding quality. The skills, including /grill-with-docs, /to-spec, /to-tickets, /implement, and /handoff, help deve…
Matt Pocock's skills repository offers reusable, context-rich engineering prompts designed to improve the quality of AI-assisted coding. The project addresses common gaps in 'vibe coding' workflows, s…
Matt Pocock's new AI Coding Crash Course teaches developers how to maintain control over AI coding agents by understanding large language models, harnesses like Claude Code and Codex, and applying Rea…
Working with AI agents feels like leadership, not coding, according to a note by an unnamed author, which clarifies that leadership sets direction and creates alignment, while supervision and manageme…
Matt Pocock's /handoff skill for coding agents compacts a conversation into a markdown file written to the OS temporary directory, enabling portability across harnesses, directories, or colleagues. Th…
Matt Pocock's public 'skills' repository, which contains his .agents directory, offers a structured approach to configuring AI coding agents. The developer behind the post analyzed the repo and found …
Developer Matt Pocock shares five agent skills he uses daily to enhance AI coding assistants like Codex, covering research, design review, React best practices, code simplification, and end-to-end tes…
RudVlad473 released iluvatar, a Claude Code skill that classifies an app idea into computer-science terms before any technology is named, emitting a schema-validated HIGH-LEVEL-ARCHITECTURE.md file th…