Agent skills from experts worth learning from.
Independent guides to Matt Pocock’s focused engineering loop, Addy Osmani’s production lifecycle, Emil Kowalski’s design-and-motion craft, Jesse Vincent’s Superpowers methodology, and Poteto’s rigor-first pstack. Learn what each skill changes, when it helps, and where its opinions add friction.
Expert collections
Five different ways to work with agents
Choose a focused engineering loop, a full production lifecycle, a specialist design-and-motion toolkit, a plan-first methodology, or a rigor-first Cursor workflow.
Matt Pocock Skills
A focused daily engineering loop built around alignment, domain language, feedback, and codebase design.
Best for: Experienced individual developers and small teams that want a sharp daily workflow, especially for requirements interrogation, domain modeling, TDD, debugging, deep module boundaries, and explicit human control over when larger workflows begin.
Read complete guideAddy Osmani Agent Skills
A production engineering system spanning definition, planning, building, verification, review, and launch.
Best for: Engineering teams and production applications that need a shared lifecycle vocabulary, broad cross-agent support, review gates, and operational checks beyond the inner coding loop.
Read complete guideEmil Kowalski Design Skills
A design-engineering toolkit for purposeful motion, interface polish, animation critique, and visual exploration.
Best for: Frontend and mobile teams that already ship functional interfaces but want stronger motion judgment, more deliberate micro-interactions, practical critique, and a repeatable way to explore alternatives without accepting generic AI styling.
Read complete guideJesse Vincent Superpowers
A complete agent development methodology that plans before it codes and verifies before it claims success.
Best for: Developers and teams who want an agent that plans before coding, keeps changes small and reviewed, and refuses to call work done without fresh evidence, especially in Claude Code, Codex, Cursor, and other harnesses with plugin or skill support.
Read complete guidePoteto Pstack
Rigorous, opinionated engineering skills that trade output volume for verified, high-quality code.
Best for: Experienced engineers working in Cursor who want rigorous agents for bug fixes, performance chases, refactors, migrations, and long autonomous runs, and who value deletion, typed boundaries, and evidence over output volume.
Read complete guideChoose by work
Engineering workflow guides
Start with the problem you need to solve, then choose the smallest useful skill set.
Requirements and Specs
Agent skills for turning vague intent into explicit, reviewable engineering work.
Compare 7 skillsTest-Driven Development
Choose a test-first discipline that makes agent feedback visible before implementation.
Compare 6 skillsSystematic Debugging
Replace speculative edits with reproducible signals, hypotheses, and regression evidence.
Compare 6 skillsCode Review
Review agent changes against intent, repository standards, and production quality risks.
Compare 9 skillsCodebase Architecture
Create deeper module boundaries and durable domain language for agent-maintained systems.
Compare 7 skillsProduction Readiness
Cover the security, performance, observability, automation, and rollback work after code functions.
Compare 10 skillsBuilding Interface Motion
Choose and implement purposeful web or native motion with the right physical and platform constraints.
Compare 5 skillsAnimation Review and Audit
Evaluate one motion change or improve animation quality systematically across an existing product.
Compare 4 skillsAgent Orchestration
Delegate independent work to isolated subagents and keep verification with the coordinator.
Compare 6 skillsWriting That Does Not Read Like AI
Strip AI tells from replies, docs, pull request descriptions, and commit messages.
Compare 4 skillsInterface Design and Prototyping
Improve interface taste, compare divergent component directions, and choose proven UI building blocks.
Compare 4 skillsEditor’s picks
Start with these reviewed skills
Original analysis of the highest-value entry points, including limitations and concrete tasks.
Grill Me
The clearest reason to install Matt’s collection. Grill Me turns vague intent into a visible decision tree and refuses to let the agent silently fill gaps, which directly addresses the most expensive failure in agentic coding: building the wrong thing quickly.
Grill With Docs
Grill With Docs improves on a normal requirements interview by turning resolved language and architectural choices into durable project context. That makes later sessions shorter and reduces inconsistent naming across both code and agent explanations.
TDD
A pragmatic, seam-oriented TDD guide that insists on observing the failure before implementation and favors tests through public behavior. It is especially useful when coding agents otherwise add tests after the fact to bless what they already wrote.
Diagnosing Bugs
This skill makes debugging a sequence of evidence-producing gates: reproduce, minimize, hypothesize, instrument, fix, and regression-test. It is a strong antidote to agents editing the first suspicious line and declaring victory.
Codebase Design
Codebase Design gives agents a compact architectural vocabulary centered on deep modules, narrow interfaces, locality, and testable seams. It improves design conversations without pretending that a generic architecture pattern fits every repository.
Interview Me
Interview Me is Addy’s strongest entry point for vague work. It asks one question at a time until underlying intent is clear, creating a measured human checkpoint before the broader lifecycle begins.
Historical repository index
Previously crawled skills remain available as a secondary reference. Indexed means discovered, not recommended.