- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add jdubois/boot-ui --skill bootui-rubber-duck -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add jdubois/boot-ui --skill bootui-rubber-duck -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add jdubois/boot-ui --skill bootui-rubber-duck -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add jdubois/boot-ui --skill bootui-rubber-duck -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/jdubois/boot-ui/tree/HEAD/.github/skills/bootui-rubber-duck게시자 제공
Get three independent, high-signal critiques of a proposal from three different powerful models, then reconcile them. This develops BootUI itself and supplements repository instructions and the relevant path-scoped instructions.
Pick one target and state it precisely:
git status, git diff, plus the intent behind it).git diff against the base (or gh pr diff), changed tests,
and CI state.Collect only what a reviewer needs: goal, constraints, files changed, tests run, and open doubts. Read the docs
that govern the area (docs/SPECIFICATION.md, docs/features/, docs/WEBFLUX-SUPPORT.md,
docs/QUARKUS-SUPPORT.md, PRODUCT.md/DESIGN.md for UI) so the brief names the invariants at stake.
Reviewers are stateless and must not see each other's output. The brief contains:
Launch three rubber-duck agents (use the task tool, agent_type: rubber-duck, background mode) at the same time,
each with a different model from the strongest available. Prefer one per model family, for example:
gpt-6-sol (or gpt-6.1-sol)claude-sonnet-5.5 (or claude-sonnet-5 at high/max effort)gemini-4-argon (or grok-4.7)Use the highest reasoning effort offered, and fall back to the next-best model if one is unavailable. Keep the same brief for all three. Respect the repository's limit on parallel sub-agents (3 fits within it). While they run, do independent work such as reproducing the riskiest claim yourself; do not poll.
Read all three results, then produce a single list:
Classify accepted items as blocking or follow-up. Do not accept a claim you have not verified.
Finish by telling the user which models were used, what was accepted, rejected, and still open.
Use to rubber duck a proposed BootUI design, plan, or implementation, either in the current agent session or in a pull request, by getting independent critiques from three different powerful models an
---name: bootui-rubber-duckdescription: Use to rubber duck a proposed BootUI design, plan, or implementation, either in the current agent session or…---# .github/skills/bootui-rubber-duck/SKILL.md개요
Use to rubber duck a proposed BootUI design, plan, or implementation, either in the current agent session or in a pull request, by getting independent critiques from three different powerful models and synthesizing them. Not for routine reviews of trivial changes.
FAQ
게시자에게서 .github/skills/bootui-rubber-duck/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/jdubois/boot-ui에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.