The /Handoff Skill
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 /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 …
Matt Pocock's new skill, /to-questionnaire, turns open questions into a Markdown questionnaire document that can be sent to a specific person for async or meeting-based completion. The skill, installa…
Matt Pocock's /wizard skill generates an interactive bash script that walks a human through manual setup procedures, such as wiring third-party services or running one-off migrations, by opening URLs,…
Matt Pocock released the /wait-what skill for coding agents, a three-line prompt that re-pitches a confusing message in plain English using the project's CONTEXT.md vocabulary. The skill, installable …
A developer's deterministic tool adoption CLI scored mattpocock/skills, a collection of Claude Code agent skills, at 64/100, yielding a TRIAL verdict. The system evaluates candidates on five gates—mat…
Matt Pocock, a TypeScript educator, open-sourced his personal .claude directory as the repo mattpocock/skills, which has amassed over 160,000 GitHub stars. The repository contains around 36 Claude Cod…
Matt Pocock's /writing-for-agents skill, renamed from /writing-great-skills in v1.1, provides a reference for writing agent-facing documents such as skills, AGENTS.md, CLAUDE.md, specs, and READMEs, e…
Matt Pocock's /resolving-merge-conflicts skill, available via npx skills@latest add mattpocock/skills, resolves git merge or rebase conflicts hunk by hunk by tracing each side to its primary source (c…
A new analysis warns that large language model context windows degrade significantly beyond 100k tokens, making advertised sizes of 200k to 2M tokens misleading for practical use. Studies like RULER a…