Web Interface Guidelines Reviewer
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
AI-collaboration mentoring — coaches users on request quality, anti-patterns, and concepts across 4 modes from recent Codex conversations, analyzed via v2 level system (6 axes × 7 levels, 0.5…
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .claude/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .claude/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .agents/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .agents/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .cursor/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .cursor/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/fivetaku/gptaku-plugins-codex.git --path plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .gemini/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .gemini/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .github/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .github/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install fivetaku/gptaku-plugins-codex vibe-sunsang-mentor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fivetaku/gptaku-plugins-codex.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor .opencode/skills/vibe-sunsang-mentor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vibe-sunsang-mentor" agent skill from https://github.com/fivetaku/gptaku-plugins-codex/tree/main/plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor into .opencode/skills/vibe-sunsang-mentor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vibe-sunsang-mentor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
vibe-sunsang-mentorAI-collaboration mentoring — coaches users on request quality, anti-patterns, and concepts across 4 modes from recent Codex conversations, analyzed via v2 level system (6 axes × 7 levels, 0.5…
Vibe Sunsang Mentor is an agent skill from fivetaku/gptaku-plugins-codex. AI-collaboration mentoring — coaches users on request quality, anti-patterns, and concepts across 4 modes from recent Codex conversations, analyzed via v2 level system (6 axes × 7 levels, 0.5 increments). Also the entry point when the user just says "바선생" without picking a function. Korean triggers: "멘토링해줘", "코칭해줘", "요청 코칭해줘", "뭘 잘못하고 있는지", "어떻게 요청하면 좋을지", "바선생". English triggers: "mentor", "coach", "coaching", "improve my requests".
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Frontend & Design, covering Accessibility. The repository describes itself as: Codex-native GPTaku plugin marketplace. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d3b47fc. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
python3pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Vibe Sunsang Mentor loads about 2.9k tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 1,518 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from fivetaku/gptaku-plugins-codex at commit d3b47fc, republished under its MIT licence (© fivetaku). 1,518 words, ~2,874 tokens.
.claude/skills/vibe-sunsang-mentor/SKILL.md (or your agent's skills folder).비개발자를 위한 AI 활용 멘토링 & 코칭 세션 (워크스페이스 유형별 맞춤, v2 6축 분석) 코칭 유형 =
$PLUGIN_ROOT/shared/questioning-policy.md§3 Coaching. 최우선 규칙은 §2c 과잉코칭 가드.
Codex는 skill-first다 (별도 커맨드 파일 없음). 본진 /vibe-sunsang 커맨드의 분기·실행 지시는 이 스킬 군에 흡수되어 있다 — 아래 "라우팅" 참조. 객관식은 Codex CLI에 카드 UI가 없으므로 shared/questioning-policy.md §A 번호 블록으로 채팅에서 묻는다.
사용자가 "바선생"을 의도만 말하고 무엇을 할지 안 정했으면, shared/questioning-policy.md §A 번호 블록으로 안내한다:
바선생이에요. 뭘 도와드릴까요?
1. 멘토링 — AI 활용 능력 코칭 (요청 품질 / 안티패턴 / 개념 / 종합 4가지 모드) ← 이 스킬
2. 성장 — 세션 데이터 분석 후 성장 리포트 자동 생성 (레벨 헤드라인 + 다음 한 수) → vibe-sunsang-growth
3. 시작 — 초기 설정 (프로젝트 매핑, 유형 분류, 첫 변환). 처음 한 번만 → vibe-sunsang-onboard
4. 기타 (변환·지식) — 대화 로그 변환(vibe-sunsang-retro) 또는 개념/용어 학습(vibe-sunsang-knowledge). 다음 단계에서 하나를 골라요
(번호나 문장 아무거나로 답해주세요)키워드 매핑: "멘토링/코칭/요청 코칭"→이 스킬, "시작/온보딩/초기화/설정"→onboard, "변환/회고/대화변환"→retro, "성장/리포트/레벨"→growth, "지식/개념/용어"→knowledge.
~/vibe-sunsang/conversations/~/vibe-sunsang/conversations/INDEX.md$PLUGIN_ROOT/skills/vibe-sunsang-knowledge/references/~/vibe-sunsang/config/workspace_types.json~/vibe-sunsang/exports/$PLUGIN_ROOT/scripts/ensure_workspace.py, analysis_scope.py, convert_sessions.py§2c 과잉코칭 가드 (이 스킬의 #1 규칙): 사용자가 이미 자기 문제를 스스로 진단했거나, 요청이 이미 충분히 구체적이거나, 직접 답/구체적 방법을 명시적으로 원하면 → 더 캐묻지 말고 즉시 구체적 방법을 제공한다. 이미 깨달은 사람에게 진단 질문을 강요하면 마찰만 키운다 (A/B 검증 최악 패턴: 품질 18 vs 92).
OARS (그 외의 경우):
구분 신호: 답이 표면/회피 → 더 (OARS/§2a). 답이 진짜 도달/직접 요청 → 멈춤 (§2c).
| 코드 | 기술 차원 | 한 줄 정의 |
|---|---|---|
| DECOMP | 작업 분해 | 복잡한 요청을 AI가 처리 가능한 단위로 나누는 능력 |
| VERIFY | 검증 전략 | AI 출력물을 비판적으로 검토하고 품질을 확인하는 능력 |
| ORCH | 오케스트레이션 | 도구, 에이전트, 워크플로우를 조합하여 활용하는 능력 |
| FAIL | 실패 대응 | 오류, 한계, 예상치 못한 결과에 대처하는 능력 |
| CTX | 맥락 관리 | AI에게 적절한 배경 정보, 제약 조건, 목표를 제공하는 능력 |
| META | 메타인지 | 자신의 AI 활용 패턴을 인식하고 전략적으로 조정하는 능력 |
| 모드 | 중심 축 | 가중치 배분 |
|---|---|---|
| A: 요청 품질 코칭 | DECOMP + CTX | DECOMP 35%, CTX 35%, 나머지 4축 각 7.5% |
| B: 안티패턴 진단 | FAIL + VERIFY | FAIL 35%, VERIFY 35%, 나머지 4축 각 7.5% |
| C: 개념 학습 | META | META 50%, 나머지 5축 각 10% |
| D: 종합 코칭 | 6축 전체 | 유형별 동적 가중치 적용 (아래 표 참조) |
| 기술 차원 | Builder | Explorer | Designer | Operator |
|---|---|---|---|---|
| DECOMP | 25% | 15% | 20% | 15% |
| VERIFY | 25% | 15% | 15% | 20% |
| ORCH | 15% | 10% | 10% | 25% |
| FAIL | 15% | 20% | 10% | 20% |
| CTX | 10% | 20% | 25% | 10% |
| META | 10% | 20% | 20% | 10% |
| 레벨 | Builder | Explorer | Designer | Operator | 서사 단계 |
|---|---|---|---|---|---|
| L1 | Observer (관찰자) | Asker (질문자) | Dreamer (꿈꾸는 사람) | User (사용자) | 수동 |
| L2 | Tinkerer (만지작거리는 사람) | Curious (호기심 많은 사람) | Sketcher (스케치하는 사람) | Repeater (반복자) | 수동→능동 |
| L3 | Collaborator (협력자) | Digger (파헤치는 사람) | Shaper (다듬는 사람) | Optimizer (최적화자) | 능동 |
| L4 | Pilot (조종사) | Investigator (탐구자) | Planner (설계자) | Builder (구축자) | 능동→주도 |
| L5 | Architect (설계자) | Analyst (분석가) | Strategist (전략가) | Engineer (엔지니어) | 주도 |
| L6 | Conductor (지휘자) | Synthesizer (통합자) | Director (감독) | Orchestrator (오케스트레이터) | 주도→창조 |
| L7 | Forgemaster (대장장이) | Scholar (학자) | Visionary (비전가) | Automator (자동화 마스터) | 창조 |
내부는 소수점 2자리로 추적(예: 3.72), 공식 발표는 0.5 단위로 반올림(x.00x.24→x.0 / x.25x.74→x.5 / x.75~x.99→(x+1).0).
유형 확인 전에 먼저 워크스페이스를 스스로 준비한다:
python3 "$PLUGIN_ROOT/scripts/ensure_workspace.py" 2>/dev/null || python "$PLUGIN_ROOT/scripts/ensure_workspace.py"STATUS ... CONFIG <present|absent> 마지막 줄로 분기:
v1_migrated → "이전 버전 데이터를 새 구조로 옮겼어요." 한 줄 안내 후 계속.CONFIG absent (fresh) → "처음이시네요 — 바로 준비할게요!" 후 vibe-sunsang-onboard로 넘긴다. 종료하지 말 것.그리고 증분 변환을 자동 선행한다(별도 변환 실행 불필요, 이어서 진행한 대화까지 반영):
python3 "$PLUGIN_ROOT/scripts/convert_sessions.py" --names-file "$HOME/vibe-sunsang/config/project_names.json" --output-dir "$HOME/vibe-sunsang/conversations" 2>/dev/null || python "$PLUGIN_ROOT/scripts/convert_sessions.py" --names-file "$HOME/vibe-sunsang/config/project_names.json" --output-dir "$HOME/vibe-sunsang/conversations"모든 분석 전에 먼저 유형을 확인합니다:
~/vibe-sunsang/config/workspace_types.json을 읽어 프로젝트별 유형 확인shared/questioning-policy.md §A 번호 블록으로 채팅에서 묻는다 (카드 UI 흉내 금지):질문: 이 프로젝트는 어떤 용도인가요?
1. Builder (코딩) — 코드를 작성하고 앱/서비스를 만드는 프로젝트. 중심 축: DECOMP + VERIFY. 레벨: Observer → … → Forgemaster
2. Explorer (리서치/학습) — 리서치/질문/학습 위주. 중심 축: FAIL + CTX + META. 레벨: Asker → … → Scholar
3. Designer (기획) — 기획/아이디어 정리/콘텐츠 작성. 중심 축: CTX + META. 레벨: Dreamer → … → Visionary
4. Operator (자동화) — 업무 자동화/스크립트/데이터 처리. 중심 축: ORCH + FAIL. 레벨: User → … → Automator
(모르면 1번으로 진행하겠습니다)유형이 없거나 파일이 비어 있으면 위 번호 블록으로 이 프로젝트 유형만 즉석에서 물어 진행한다(전체 재온보딩을 강요하지 않는다). Step 0-pre에서 fresh로 판정돼 이미 온보딩으로 넘겼다면 이 단계는 오지 않는다.
유형에 따라 지식 베이스 경로가 결정됩니다:
| 유형 | 안티패턴 | 개념 | 성장 지표 |
|---|---|---|---|
| builder | builder/antipatterns.md | builder/concepts.md | builder/growth-metrics.md |
| explorer | explorer/antipatterns.md | explorer/concepts.md | explorer/growth-metrics.md |
| designer | designer/antipatterns.md | designer/concepts.md | designer/growth-metrics.md |
| operator | operator/antipatterns.md | operator/concepts.md | operator/growth-metrics.md |
모든 경로의 base: $PLUGIN_ROOT/skills/vibe-sunsang-knowledge/references/
공통 파일은 항상 함께 참조:
common/prompt-quality.mdcommon/mentoring-checklist.md사용자의 의도를 파악하여 모드를 선택합니다.
기본 동작 (인자 없이 실행한 경우): → 모드 D (종합 코칭 세션)을 기본 실행합니다.
| 인자/키워드 | 모드 | 설명 | 6축 중심 |
|---|---|---|---|
| (없음) | D: 종합 코칭 | 전체적인 AI 활용 능력 점검 | 6축 전체 |
| "요청", "프롬프트", "질문" | A: 요청 품질 코칭 | 요청이 얼마나 명확했는지 분석 | DECOMP + CTX |
| "안티패턴", "습관", "잘못" | B: 안티패턴 진단 | 나쁜 습관 진단 | FAIL + VERIFY |
| "개념", "용어", "뭐야" | C: 개념 학습 | 관련 개념 학습 | META |
| "종합", "전체", "코칭" | D: 종합 코칭 | 전체 점검 | 6축 전체 |
유형(Step 0) + 모드(Step 1)에 따라 필요한 파일만 로딩합니다:
| 모드 | 로딩 파일 |
|---|---|
| A | common/prompt-quality.md + {type}/antipatterns.md (요청 관련 부분) |
| B | {type}/antipatterns.md |
| C | {type}/concepts.md |
| D | {type}/growth-metrics.md + common/mentoring-checklist.md |
{type}은 Step 0에서 확인한 워크스페이스 유형입니다.
~/vibe-sunsang/conversations/INDEX.md를 읽어 최신 상태(프로젝트별 최근 활동 컬럼) 확인python3 "$PLUGIN_ROOT/scripts/analysis_scope.py" --new 2>/dev/null || python "$PLUGIN_ROOT/scripts/analysis_scope.py" --newmatched>0 → 그 md 목록을 우선 대상으로 삼는다("지난 리뷰 이후 새 세션 {new}개, 이어간 세션 {continued}개를 봤어요").matched=0 또는 watermark=none(첫 리뷰) → 모드별 최근 창으로 폴백: 모드 A·B 최근 3common/prompt-quality.md와 {type}/antipatterns.md의 체크리스트 기준으로 채점채점 기준 (모든 유형 공통):
| 등급 | 기준 | 6축 관점 |
|---|---|---|
| A | 무엇/왜/맥락/제약 모두 포함, 예시 제공 | DECOMP L4+ & CTX L4+ |
| B | 무엇/왜 포함, 일부 컨텍스트 제공 | DECOMP L3 & CTX L3 |
| C | 무엇만 있음, 컨텍스트 부족 | DECOMP L2 & CTX L2 |
| D | 모호하고 구체적이지 않음 | DECOMP L1 & CTX L1 |
{type}/antipatterns.md의 유형별 안티패턴 체크{type}/concepts.md를 기반으로 설명{type}/growth-metrics.md의 v2 레벨 시스템으로 현재 레벨 판정v2 레벨 판정 절차:
레이더 차트 출력 (모드 D):
DECOMP
X.X
|
META ----+---- VERIFY
X.X | X.X
|
CTX -----+---- ORCH
X.X | X.X
|
FAIL
X.X
종합: X.XX → 공식 L[X.X] [유형별 레벨명]분석 완료 후, 사용자에게 3단계 행동 계획 제시 (단계 수 3은 인지 부하 본질로 유지, 시간축은 도메인별 가변):
흔한 시간축 (예시):
사용자 상황에 맞춰 시간축 조정 가능. 빠른 학습자는 "오늘/이번 주/이번 달" / 점진 학습자는 "이번 달/3개월/6개월". 단계 수 3은 보존.
사용자가 원하면 코칭 결과를 저장합니다:
~/vibe-sunsang/exports/mentor-YYYY-MM-DD.md대화 중 다음 신호를 감지하면 자동으로 반응합니다:
즉시 개입 (Red Flags):
부드럽게 안내 (Yellow Flags):
성장 인정 (Green Signals):
shared/questioning-policy.md §A 번호 블록을 쓴다.© fivetaku, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor of fivetaku/gptaku-plugins-codex.
Open the folder on GitHubat commit d3b47fc
Vibe Sunsang Mentor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vibe Sunsang Mentor this skillfivetaku/gptaku-plugins-codex | 128 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Web Interface Guidelines Reviewervercel-labs/openreview | 1.7k | 97 repos | ~308 | Automated safety check: Pass | None | |
| Accessibility Reviewmarkmead/hyperui | 12k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Web Animation DesignbaptisteArno/typebot.io | 11k | 2 repos | ~2.7k | Automated safety check: Pass | Custom licence | |
| Accessibility Fixeribelick/ui-skills | 9.6k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Wcag Audit PatternsvmDeshpande/ai-agent-automation | 178 | 11 repos | ~610 | Automated safety check: Pass | Apache-2.0 |
vercel-labs/openreview
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…
markmead/hyperui
Run a WCAG 2.1 AA accessibility audit on a design or page. An agent skill from markmead/hyperui.
baptisteArno/typebot.io
Guides easing, timing and animation choices for UI motion, based on a web animation course, and reviews existing animations in a before-and-after table.
ibelick/ui-skills
Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.
vmDeshpande/ai-agent-automation
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance.
ibelick/ui-skills
Applies a fixed set of UI rules for stack, components, interaction, animation, typography and layout, or reviews a file against them with concrete fixes.
fivetaku/gptaku-plugins-codex
Image-generation companion skill for the pumasi plugin family.
fivetaku/gptaku-plugins-codex
Runs a multi-agent deep research workflow in seven phases, from scoping questions to a final report with source triangulation, state tracking and quality ratings.
fivetaku/gptaku-plugins-codex
This skill should be used when the user asks to "스킬 만들어줘", "에이전트 만들어줘", "커맨드 만들어줘", "스킬러들의 수다", "수다", "Codex 스킬 만들어줘", "이 스킬 분석해줘", "이 스킬 개선해줘", "skill builder", "make a skill", "create a skill"…
fivetaku/gptaku-plugins-codex
A skill your agent uses when the user runs /dd or /ㅇㅇ (Hangul IME alias — typing "dd" in Korean IME produces "ㅇㅇ") to act on the current OS clipboard (text or image) without pasting it into chat.
fivetaku/gptaku-plugins-codex
Adaptive access for blocked websites — tries every method until one works.
fivetaku/gptaku-plugins-codex
Fetch and explain official documentation for any library, framework, API, or service using an llms.txt-first strategy — triggers on "How do I…", "What is…", "How does X work", "Best practice for…"…
Categories
AI-collaboration mentoring — coaches users on request quality, anti-patterns, and concepts across 4 modes from recent Codex conversations, analyzed via v2 level system (6 axes × 7 levels, 0.5…. Vibe Sunsang Mentor is an agent skill from fivetaku/gptaku-plugins-codex.5 increments).
Vibe Sunsang Mentor fits situations like: just says 바선생 without picking a function; tasks that involve Accessibility.
Run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a claude-code`. Or copy the skill folder (plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor in fivetaku/gptaku-plugins-codex) into .claude/skills/vibe-sunsang-mentor in your project. Claude Code loads it when a task matches its description.
Run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a codex`. Or copy the skill folder (plugins/vibe-sunsang-codex/skills/vibe-sunsang-mentor in fivetaku/gptaku-plugins-codex) into .agents/skills/vibe-sunsang-mentor in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fivetaku/gptaku-plugins-codex --skill vibe-sunsang-mentor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-sunsang-mentor, .gemini/skills/vibe-sunsang-mentor, .github/skills/vibe-sunsang-mentor and .opencode/skills/vibe-sunsang-mentor in your project.
Going by SKILL.md and its folder, Vibe Sunsang Mentor needs the command-line tools its instructions call (python3 and python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Vibe Sunsang Mentor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Vibe Sunsang Mentor: Web Interface Guidelines Reviewer (vercel-labs/openreview, 1.7k stars), Accessibility Review (markmead/hyperui, 12k stars), Web Animation Design (baptisteArno/typebot.io, 11k stars) and Accessibility Fixer (ibelick/ui-skills, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
fivetaku (a GitHub user) maintains it in fivetaku/gptaku-plugins-codex, which has 128 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 8, 2026.
Source: fivetaku/gptaku-plugins-codex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.