obsidian-vault
Low Risk 79Organize and Search Your Obsidian Vault
by mattpocock
Managing a large Obsidian vault with hundreds of notes becomes hard without consistent structure. This skill teaches Claude and Codex the naming, linking, and search conventions to keep your vault organized and discoverable.
migrate-to-shoehorn
Low Risk 79Migrate TypeScript Tests to Shoehorn
by mattpocock
TypeScript tests often use unsafe `as` assertions to fake large objects. This skill migrates them to type-safe shoehorn helpers, keeping autocomplete and type checking working.
improve-codebase-architecture
Safe 76Improve Codebase Architecture
by mattpocock
Codebases accumulate shallow modules that are hard to test and navigate. This skill finds deepening opportunities by analyzing module depth and seams, then guides you through refactoring decisions to make your architecture more maintainable.
handoff
Low Risk 78Handoff - Seamlessly Transfer Work Between AI Agents
by mattpocock
Developers lose valuable context every time they start a new AI coding session. This skill generates a compact handoff document that summarizes the current conversation, key artifacts, and next steps so a fresh agent can pick up the work immediately.
grill-with-docs
Safe 81Stress-test plans with domain-driven documentation
by mattpocock
Planning discussions drift into ambiguity. This skill runs structured grilling sessions that force clarity on domain terminology, then updates CONTEXT.md and ADRs inline as understanding crystallizes.
grilling
Safe 80Stress-test any plan before you build it
by mattpocock
Plans often fail because hidden assumptions go unchallenged. This skill makes the AI relentlessly interview you about every aspect of your design, surfacing gaps and resolving dependencies one question at a time.
grill-me
Safe 82Stress-test your plans with relentless interview questions
by mattpocock
Uncritical planning leads to overlooked flaws and failed implementations. This skill rigorously interviews your designs, exposing hidden dependencies and weak points before they become costly mistakes.
git-guardrails-claude-code
Low Risk 75Block Dangerous Git Commands in Claude Code
by mattpocock
Claude can accidentally run destructive git operations like force push or hard reset. This skill installs hooks that block these commands before they execute, protecting your work from accidental data loss.
edit-article
Safe 81Edit and Improve Article Drafts with Structured Revision
by mattpocock
Editing an article draft can feel overwhelming when sections, flow, and clarity all need attention. This skill provides a clear, section-by-section revision process that tightens prose and improves coherence.
domain-modeling
Safe 80Build Precise Domain Models with Active Vocabulary
by mattpocock
Software projects suffer when teams use inconsistent terminology or lose track of why decisions were made. This skill helps you actively build and sharpen your domain model by challenging terms, inventing edge cases, and capturing decisions in CONTEXT.md and ADRs.
diagnosing-bugs
Low Risk 76Diagnose and Fix Tough Software Bugs
by mattpocock
Debugging complex bugs often leads to wasted time with unstructured trial and error. This skill provides a systematic phased methodology to build feedback loops, reproduce issues, and fix problems efficiently.
design-an-interface
Safe 81Design Better Interfaces Using Parallel Sub-Agents
by mattpocock
Designers often settle on the first interface idea without exploring alternatives. This skill applies the 'Design It Twice' methodology, using parallel sub-agents to generate radically different interface designs for comparison and synthesis.
diagnose
Safe 78Debug Complex Issues with a Structured Diagnosis Loop
by mattpocock
When bugs resist diagnosis or performance mysteriously degrades, use a disciplined six-phase loop: reproduce, minimise, hypothesise, instrument, fix, and regression-test. This skill provides the exact methodology to avoid guesswork and solve hard problems systematically.
codebase-design
Safe 80Design deep modules with clear interfaces
by mattpocock
Most codebases suffer from shallow modules with large interfaces and thin implementations. This skill provides a shared vocabulary and methodology for designing deep modules, deciding where seams go, and making code more testable and maintainable.
caveman
Safe 77Cut token usage by 75% with ultra-brief responses
by mattpocock
Verbose AI responses consume excessive tokens and slow workflows. This skill compresses communication to essential content only while preserving technical accuracy, enabling faster and cheaper interactions with Claude, Codex, or Claude Code.
ask-matt
Safe 80Route any engineering situation to the right skill
by mattpocock
When you cannot remember which skill to use, this router maps your situation to the correct flow. It describes the main path from idea to ship and the available on-ramps.
mastra
Safe 79Build AI Apps with Mastra Framework
by mastra-ai
Mastra is a TypeScript framework for building AI agents and workflows. This skill provides comprehensive documentation lookup strategies and code patterns to ensure you use current APIs and avoid common errors.
using-email-templates
Safe 80Send Mailtrap emails with template UUIDs and Handlebars variables
by mailtrap
Email teams waste time switching between docs and code to assemble template UUIDs and variable payloads. This skill gives Claude and Codex the exact Mailtrap API patterns so they generate correct send requests on the first try.
testing-with-sandbox
Low Risk 76Test emails safely with Mailtrap Sandbox
by mailtrap
Developers need to verify outbound email without sending to real recipients. This skill guides Claude and Codex to configure and use the Mailtrap Email Sandbox for safe, automated email testing in development and CI environments.
setting-up-sending-domain
Low Risk 77Set Up and Verify Mailtrap Sending Domains
by mailtrap
Configuring DNS records for email sending is complex and error-prone. This skill provides clear guidance for adding, verifying, and troubleshooting Mailtrap sending domains across major DNS providers.