Tutorials
My Spec Session With to-Spec: No Interview, Just Synthesis
I ran Matt Pocock's to-spec skill on a half-baked feature and it refused to interview me: pure synthesis, one test seam pinned, then a ready-for-agent spec.
Resolve Git Merge Conflicts With AI: The 5-Step Workflow
A step-by-step guide to Matt Pocock's resolving-merge-conflicts skill, the five-step workflow that bans --abort, keeps both intents, and finishes every rebase.
Diagnosing Bugs Skill FAQ: The Feedback Loop Comes First
Straight answers on diagnosing-bugs: why the red-capable loop precedes hypotheses, how flaky bugs become debuggable, and when regression tests should wait.
Best AI Debugging Skills of 2026: A Roundup
5 AI skills that actually find bugs, compared from their source: diagnosing-bugs loop, TDD seams, code-review axes, prototype flow, and the regression trap.
Prototype vs TDD: When to Explore Throwaway and When to Go Test-First
The Matt Pocock skills offer two ways to build something new: Prototype throws code away to answer a question, TDD locks it down test-first. Pick right.
I Ran Matt Pocock’s Triage Skill on a Stale Backlog of Issues
I ran Matt Pocock's Triage skill (skills.sh #11) over a stale backlog, and its verification gate stalled me before a single issue moved.
Domain Modeling With AI: Build a CONTEXT.md Glossary
A step-by-step domain modeling walkthrough with Matt Pocock's skill — run the five moves, write a CONTEXT.md glossary, offer ADRs when all three tests pass.
Teach Skill FAQ: Personal AI Teaching With Claude Code
Practical answers on Matt Pocock's Teach skill: how the teaching workspace works, why lessons ship as HTML, and what learning records do for retention.
Best MCP Servers in 2026: A Data-Backed Roundup
13 MCP servers ranked with GitHub data pulled August 16, 2026: stars, maintenance signals, and the right pick for docs, search, coding, or browser control.
Best AI Agent Frameworks in 2026: A Data-Backed Roundup
12 AI agent frameworks, ranked with GitHub data from August 15, 2026: stars, maintenance signals, and the right pick for Python, TypeScript, or enterprise.
Copilot vs Cursor vs Claude Code: Best AI Coding Agent 2026?
GitHub Copilot vs Cursor vs Claude Code on 2026 pricing, agent power, model access, and terminal-vs-IDE fit, plus a practical pick for your stack.
I Installed a 9.4k-Star Business Skill Pack and Ran Its Diagnosis
I installed dbskill's 30 business skills on a live server and ran its diagnosis workflow — the CLI found 31 skills, and 2 of 73 agents rejected the install.