cd/entity/mattpocock/skills· home entities mattpocock/skills
grep -l @mattpocock/skills /news/*.json | wc -l → 10

mattpocock/skills

mentions 10 type Organization feed RSS

// recent coverage 10 mentions

20:45
2026-08-15
aihero.dev
developer-tools

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…

22:00
2026-08-11
aihero.dev
developer-tools

The /to-questionnaire Skill

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…

22:00
2026-08-11
aihero.dev
developer-tools

The /wizard Skill

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,…

10:17
2026-08-05
aihero.dev
developer-tools

The /wait-what Skill

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 …

00:00
2026-07-25
dev.to
developer-tools

Deterministic Tool Adoption Gates: Score It, Don't Vibe It

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…

15:28
2026-07-08
aihero.dev
ai-agents

The /writing-for-agents Skill

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…

13:56
2026-07-07
aihero.dev
developer-tools

The /resolving-merge-conflicts Skill

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…

06:07
2026-06-14
garrit.xyz
large-language-models

Don't trust large context windows

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…

// co-occurs with top 8 entities
// topics top 6 topics