kazuph/yunomi

Human-in-the-loop review interface for AI coding workflows

21Stars on the repository
17Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

backend-impl

01

kazuph/yunomi

Agent

A backend development agent for building and checking web APIs and their databases. It follows test-first development (writing tests before implementation) and requires real framework-based tests.

21 5d ago A 82 tokens original MIT

dogfooding

02

kazuph/yunomi

Agent

A hands-on testing agent that uses an application like a real user, clicking through its screens and watching for unexpected behaviour.

21 5d ago A 47 tokens original MIT

mobile-impl

03

kazuph/yunomi

Agent

Agent "mobile-impl" from kazuph/yunomi, covering mobile implementation agent, core philosophy, zero-tolerance policy (絶対厳守), 絶対禁止事項 and 許可されるもの.

21 5d ago A 92 tokens original MIT

report-builder

04

kazuph/yunomi

Agent

Specialized agent for organizing review reports and evidence. Used when executing the /done skill or when report creation is needed.

21 5d ago A 27 tokens original MIT

report-validator

05

kazuph/yunomi

Agent

An agent that checks whether a Japanese REPORT.md file follows five rules from an artifact-proof process, including language, image, video, and layout requirements.

21 5d ago A 47 tokens original MIT

kazuph/yunomi

Agent

A review agent that examines code quality and security, including types, error handling, repeated logic, injection risks, access control, and exposed sensitive data. It can also advise on a proposed design before coding begins.

21 5d ago A 57 tokens original MIT

review-e2e

07

kazuph/yunomi

Agent

An end-to-end (E2E) test review agent checks whether tests correctly reproduce real user journeys through an application.

21 5d ago A 60 tokens original MIT

review-ui-ux

08

kazuph/yunomi

Agent

A review agent for user interfaces, the parts of software people see and operate. It checks accessibility, keyboard use, design consistency, wording, and responsive behavior, or gives design advice before implementation.

21 5d ago A 55 tokens original MIT

review-video

09

kazuph/yunomi

Agent

An agent that reviews evidence videos by extracting key frames with ffmpeg and describing what appears in them. ffmpeg is a command-line tool for processing video and audio.

21 5d ago C 53 tokens original MIT

webapp-impl

10

kazuph/yunomi

Agent

A Japanese-language agent for building and testing web applications from design through browser verification. It requires real implementations and applies rules against mock behavior, fake data, hardcoded dynamic values, and security bypasses.

21 5d ago A 87 tokens original MIT