So I tried Matt's skills...
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
A deep dive into two popular collections of AI agent 'skills' (markdown-based instruction files): Matt Pocock's skills repo (200k+ GitHub stars) and Lauren 'Potato' Tan's Pstack skills. The reviewer tests standout skills like unslop (removes AI writing tells and adds human voice), grilling/grill-me (relentless interview-style planning), blast-radius (impact analysis before changes), show-your-work, wizard, writing-for-agents, and wait-what. Includes live before/after comparisons showing how unslop dramatically improves AI-generated text readability, and a workflow for auditing personal usage against available skills to decide which to adopt rather than blindly copying setups. Sponsored segment for Depot's CI/build caching and remote agent sandboxes.
•38m watch time
Questions this post answers
What does the unslop AI agent skill actually do?
It edits AI-generated text to remove common AI writing patterns and add a more human voice. The process scans for cliche phrases like 'pivotal moment' or 'testament to,' removes puffery and chatbot phrases like 'I hope this helps,' cuts em-dash overuse, replaces vague feeling-based statements with direct facts, and finishes with a self-audit asking what still reads as AI-generated. Developers refining how their coding agents communicate can track skill-based prompting techniques like this on daily.dev.
What is the difference between Matt Pocock's skills repo and the Pstack skills collection?
Matt Pocock's skills repo is a widely starred (200,000+ stars) collection of markdown-based AI agent skills covering workflows like grill-with-docs, codebase design, diagnosing bugs, and wizard, many with manual invocation disabled by default. Pstack, created by former React core team member Lauren 'Potato' Tan (now at Cursor), offers skills like unslop, blast-radius, and arena that are considered more philosophically aligned and readable, though several are tied specifically to Cursor. Anyone comparing AI agent skill ecosystems can follow ongoing coverage of tools like these on daily.dev.
What does the blast-radius skill do when reviewing code changes with an AI agent?
It identifies what a change breaks elsewhere in a codebase before shipping it, by tracing dependencies and side effects tied to a diff. It complements 'how' and 'why' explanations: how describes what code does, why describes its design rationale, and blast-radius reveals downstream impact, making it useful when reviewing a small diff you don't fully trust. Developers building safer AI-assisted review workflows can keep up with skill-based agent tooling on daily.dev.
44.5K Impressions3 Comments