Language-neutral definition of done — the completion gate (build, tests, static analysis, standards, coverage, Sonar, no commit until asked), code hygiene (no needless comments, dead code or redundant tests) and the Sonar quality gate.
Plugin ai-toolkit-quality from marketplace ai-toolkit in oriddd/ai-toolkit. Commands read from the repo's manifest — yesterday.
code-hygieneKeep a diff minimal and self-explanatory — no comments restating code, no dead code, no speculative abstraction, no unrelated churn, no redundant tests. Use when reviewing your own diff before saying done, and before adding a comment, docstring or test.
completion-gateDefinition of done — never commit until asked; before saying done, prove build, full tests, static analysis, language standards, meaningful coverage, hygiene and Sonar with evidence. Use when finishing any code change, before reporting it done, and after every fix made during the check.
sonar-quality-gateDrive the SonarQube/SonarCloud new-code quality gate to green — bugs, vulnerabilities, smells, hotspots, duplication, coverage — without suppressing findings; report honestly if Sonar is unreachable. Use when the completion gate reaches Sonar or a pipeline's Sonar gate fails.
Java 21 / Spring Boot design phase — package structure, strategy/registry, ports and adapters, domain modeling, Spring conventions and REST API design. Ships the Java routing hook. Part of the `ai-toolkit-java` set — install that to get the whole language.
13 skills · hooks
Java 21 / Spring Boot implementation phase — exceptions, validation, permissions, persistence, messaging, external clients, resilience, security and privacy.
12 skills
Java task agents that compose the Java skills — new endpoint, feature, Kafka consumer, metric, client, validation, refactor, code review, repo scaffold, context update, and the parallel test-writer worker. Requires the java-* plugins.
10 agents
Java 21 / Spring Boot build-and-run phase — Jenkins and GitHub Actions CI, Helm CD, observability, request metrics, health indicators, graceful shutdown, local dev.
8 skills
Java 21 / Spring Boot quality phase — unit/component/integration/contract tests, static analysis, quality review and refactoring playbook.
8 skills
Experimental — Python task agents that compose the python-* skills — new endpoint, feature, refactor, code review and the parallel test-writer worker. Requires the python-* plugins.
5 agents
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
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · 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.