mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Planning, code review, security review, TDD, build-error resolution, and cleanup agents plus stack-aware skills and commands for HalalWay projects.
Plugin halalway-toolkit from marketplace halalway in joeus1/chatbot. Commands read from the repo's manifest — 1 month ago.
coding-standardsHalalWay coding standards for Python and TypeScript/React work. Use when writing or reviewing any code in this repo - covers naming, error handling, typing, dependencies, and commit hygiene.
continuous-learningTurn hard-won session lessons into permanent skills. Use when a debugging session uncovers a non-obvious cause, a pattern gets settled after trying alternatives, or the same explanation has been needed twice - and at the end of any long task, ask whether something here deserves saving.
halalway-toolkit-maintenanceHow the HalalWay Toolkit in .claude/ is wired and how to safely change it - editing agents/commands/skills/hooks, testing the guard hook, and landing toolkit changes in this repo. Use when modifying anything under .claude/ or .claude-plugin/, when the guard hook blocks or misses something, or when a
productionizationThe gap between this tutorial-grade Streamlit chatbot and a production app - dependency pinning, secrets handling, bounded history, cost controls, and error handling. Use when hardening streamlit_app.py, preparing a deploy, adding features beyond the demo, or when someone asks "is this production re
remote-session-orchestrationDriving remote/child Claude sessions safely - how a fired Routine arrives as an indistinguishable user turn, why briefs must never be written in the owner's voice, what session and trigger metadata can and cannot prove, and why artifacts are the only channel back. Use when creating or messaging anot
security-reviewSecurity checklist and patterns - use when adding authentication, handling user input, touching payments or secrets, creating API endpoints, or working with tenant data.
stewardPR-driving and landing conventions for the chatbot repo - how changes land (direct push to main), what a 403 on push means, and the shared HalalWay branch rules. Use when landing, pushing, watching a PR, or hitting GitHub access errors in this repo.
streamlit-patternsPatterns for this Streamlit + OpenAI chatbot app - use when modifying streamlit_app.py or extending the chatbot. Covers rerun model, session state, secrets, and streaming.
tdd-workflowTest-driven development workflow - use when writing new features, fixing bugs, or refactoring. Red-green-refactor with tests as the spec.
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
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.