Matt Pocock's Engineering Skills
Complete workflow system for shipping code, from idea through deployment
What You Can Do
This is a comprehensive engineering workflow system designed to guide you from an initial idea all the way to shipped code. It includes a main flow (idea → grill → spec → tickets → implement → review → ship), specialized skills for handling bugs, triage, and large architectural challenges, and foundational vocabulary skills for domain modeling and codebase design. Each skill works independently or as part of the larger workflow, giving you flexibility to adapt to your project's needs.
Features
Guided path from initial concept through grilling, spec writing, ticketing, implementation with TDD, and code review
Entry point that identifies which skill fits your current situation and when to branch or merge flows
Structured approach to intermittent bugs and regressions using tight feedback loops and minimal reproduction cases
Parallel review of Standards (project conventions) and Spec (requirements) to catch issues one axis might miss
Vocabulary and principles for designing modules with large behavior behind small interfaces and clean seams
Process for moving incoming bugs and feature requests through triage roles into agent-ready work
Clear decision tree for when to continue, clear context, handoff, spawn subagents, or compact context
Design-question answering through throwaway code that feeds into real implementations and architecture
Example Output
Routing to the right skill
Which skill should I use? I have an intermittent bug that fails every few hours.
The ask-matt skill identifies that diagnosing-bugs is the right tool, explains why, and guides you to build a tight feedback loop (failing test, curl script, or minimal harness) that reliably reproduces the bug before investigation begins.
Code review on two axes
Review my changes since main. I implemented the search feature from issue #42.
The code-review skill runs Standards and Spec reviews in parallel, then reports both findings side-by-side so you see exactly where code follows project conventions and where it matches (or diverges from) the original requirement.
Starting large architectural work
I need to redesign the data layer. It's become a bottleneck and I'm not sure where to start.
You begin with grill-with-docs to sharpen the problem, explore alternatives using codebase-design or improve-codebase-architecture, prototype solutions with diagrams and throwaway code, then hand back to the main flow to spec and ticket the work.
What's Included
- ask-matt: Entry point router that helps you identify which skill fits any situation
- Complete idea-to-ship workflow: grill-with-docs, to-spec, to-tickets, implement (with TDD), code-review, and handoff tools
- Bug diagnosis system: diagnosing-bugs skill with structured approach to hard bugs, regressions, and performance issues
- Design vocabulary and principles: codebase-design and domain-modeling skills for shared language around modules, interfaces, seams, and domains
- Triage and issue management: Process for moving incoming bugs and feature requests into agent-ready work items
- Supporting skills: Prototype, research, teach, resolving-merge-conflicts, to-questionnaire, and phase-boundary decision trees
Who It's For
- Software engineers and architects
- Engineering leads managing complex projects
- Teams building multi-session features with Claude
- Developers focused on code quality and standards
- Engineers diagnosing hard bugs and regressions
Best For
- Feature development workflows
- Debugging intermittent or hard-to-reproduce bugs
- Code review and standards enforcement
- Architecture and module design
- Managing large, multi-phase projects
You might also like
Present users with an adaptive 24-question personality assessment that uses Bayesian active learning to efficiently map their psychological profile. The skill automatically maps user responses (1-7 scales or natural language) to archetype classifications based on a 5-color psychological model, tracks probability distributions in real-time, and delivers detailed personality insights including core strengths, weaknesses, and top archetype matches.
The Lark CLI is the official command-line interface for Lark (飞书), packed with 35+ AI agent skills and 200+ commands. Automate workflows across your entire Lark workspace: manage approvals and attendance, develop custom applications with Miaoda, query and analyze multi-dimensional base tables, handle documents and sheets, schedule meetings, send messages, manage mail and tasks, and integrate with external APIs. Built for both humans and AI agents with comprehensive business domain coverage.
Generate batches of proven viral hooks across named-creator frameworks (MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway). Write and audit short-form scripts with platform-specific pacing. Optimize Instagram Reels for sends-per-reach using Trial Reels testing. Craft captions and CTAs that match video payoff. Diagnose why openings flop and rewrite weak hooks against anti-patterns. The skills encode what patterns tend to lift retention in the first 1 to 3 seconds, then repurpose across platforms.
RigorPilot is a comprehensive skill suite for deep learning research, providing auditable repository analysis, README-first reproducibility workflows, bounded exploration with evidence-based ranking, and publication-ready scientific documentation. Each skill enforces rigor through documented assumptions, comparability tracking, and explicit decision checkpoints. Use these skills to understand ML repository internals, faithfully reproduce published results, systematically explore novel ideas with proper baselines, and generate standardized research artifacts.
This comprehensive collection includes 79 dedicated agent skills for all major Azure services and operations. You can automate Azure resource deployment and management, query infrastructure and logs with natural language using Kusto Graph and IRQL, analyze security events and detect threats, configure identity and access management through Entra ID, monitor application performance with Application Insights, manage storage and messaging services, execute cloud migration workflows, validate compliance policies, and query Azure resources by metadata or properties.
Access 29 production-ready Claude agent skills that wrap RunComfy's AI models for image generation, video creation, audio synthesis, and avatar videos. Skills include music generation (ACE Step with inpaint/outpaint), AI avatars and lip-sync (OmniHuman, Seedance, HappyHorse), image editing (inpainting, outpainting, face-swap, relight), video generation and extension, and upscaling. All skills are CLI-driven via the runcomfy command, with built-in schema validation, error handling, and examples for each model.
Elevate your interface design from strategy to pixel-perfect execution. Shape layouts and user flows before coding, critique designs against established heuristics, audit for accessibility and performance gaps, and polish for production. Enhance with purposeful animation, strategic color, harmonious spacing, and delightful moments. Includes comprehensive guidance for websites, dashboards, apps, components, forms, onboarding, and design systems across web and native platforms.
by pbakausDesign and build animations using a proven decision sequence covering when to animate, which tools to use (CSS, WAAPI, Motion.dev), property selection, easing curves, and accessibility. Review existing animations and audit codebases for quality issues. Understand and name motion effects using a comprehensive vocabulary glossary. Learn from Emil Kowalski's opinionated motion design philosophy built on decades of interface engineering experience.