mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Verification-gated autonomous loop engineering: Claude works act→verify→repeat until a verify command passes, bounded by iteration caps and no-progress detection.
Plugin loop-engine from marketplace loop-engine-marketplace in juliosaraiva/claude-code-loop-pluging. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
loop-engineeringMethodology and guardrails for AI loop engineering — running autonomous act→verify→repeat loops in Claude Code. Use when designing or running an iterative loop, writing success criteria, choosing a verify command, or deciding loop guardrails.
/loop-engine:planPlan a loop-engineering run without starting it — produce a plan, deterministically verifiable success criteria, and a recommended verify command.
/loop-engine:startStart an autonomous, verification-gated loop-engineering run. Claude works act→verify→repeat toward a goal until the verify command passes (or a guardrail stops it).
/loop-engine:statusShow the current loop-engine state — status, iteration, last verification result, and history.
/loop-engine:stopCancel the active loop-engine run so Claude can stop normally.
loop-plannerDesigns a loop-engineering run. Decomposes a goal into an ordered plan plus explicit, deterministically verifiable success criteria, and recommends a verify command (tests/lint/build) for the repo. Use before starting a loop or when /loop-engine:plan is invoked.
loop-verifierThe verification gate for a loop-engineering run. Runs the verify command and inspects the working tree to judge whether each success criterion is met, then returns a concise, actionable diagnosis for the next iteration. Use to assess loop progress objectively.
"${CLAUDE_PLUGIN_ROOT}"/scripts/stop-hook.sh
"${CLAUDE_PLUGIN_ROOT}"/scripts/session-start.sh
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.