Delegated browser QA operator: plan, run, monitor, triage, and optionally repair acceptance checks from requirements with evidence dashboards
Plugin qa-operator from marketplace donghyuns-agent-tools in edonghyun/donghyuns-agent-tools. Commands read from the repo's manifest — 20 days ago.
monitorServe or open the qa-operator live dashboard. Use when the user wants to monitor QA progress, see a dashboard, watch run status, view screenshots as they appear, or continue an existing QA dashboard; triggers include "monitor 켜줘", "대시보드 열어줘", "진행상황 보여줘", "QA dashboard", "live monitor", "실시간으로 보고싶어".
planConvert requirements into a qa-operator plan. Use when the user provides a spreadsheet, issue list, PR, current diff, feature checklist, staging URL, or range and wants browser QA planned before execution; triggers include "QA 계획", "qa-plan.json", "요구사항 정리", "시트 범위 QA", "테스트 케이스로 바꿔줘", "plan QA", "a
repairFix scoped, verifiable local defects found by qa-operator and rerun affected QA items. Use when the user explicitly allows repair, asks to "고치고 재검증", "명백한 버그는 수정", "auto repair local bugs", "fix failed QA", or "repair and retest". May modify application code only for narrow defects, writes repair-lo
runExecute browser QA from an existing qa-plan.json and update evidence incrementally. Use when the user wants server access, login, feature checks, validation, screenshots, traces, console/network logs, UI/UX risk scanning, or retry of failed items; triggers include "브라우저로 QA 실행", "직접 확인해줘", "QA run",
startDefault delegated QA entry for qa-operator. Use when the user wants to hand off QA from a requirement source, spreadsheet, issue, PR, feature list, current diff, or staging URL; triggers include "QA 맡겨줘", "완전 QA 돌려줘", "브라우저로 직접 확인해줘", "제대로 구현됐는지 확인해줘", "UI/UX 문제까지 찾아줘", "monitor 켜고 진행상황 보여줘", "실패 항목
triageAnalyze qa-operator FAIL, PARTIAL, BLOCKED, and UX risk findings. Use when the user wants root-cause analysis, issue reports, failure screenshots, console/network/API/server-log interpretation, or next actions after a QA run; triggers include "실패 항목 분석", "원인 분석", "UX 리스크 리포트", "triage QA", "왜 실패했는지"
Screenshot-backed product intake for external PoCs, demos, prototypes, and VoC experiments before product integration, with page-walk, control-reaction, PoC fidelity, implementation specs, and static web reports
9 skills
Six-skill safety net: generate, drift-check, lint, test-stub, coverage-audit, and scope-walk E2E specs against the current implementation
6 skills
Evidence-backed UI iteration operator for baseline/current web, mobile web, native mobile, local session, and requirement parity comparisons during product UI changes
6 skills
Branch a conversation point into a capsule another session continues from, merge results back, and always show where you are
4 skills
Evidence-driven development discipline for strict RED-GREEN-REFACTOR TDD with co-located executable specifications and contract tests for fakes
2 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
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
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
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.