ui-designer
UIを「情報設計(優先度/構造)+インタラクション(状態遷移)+ビジュアル(トーン)」として設計し、実装可能な仕様へ落とす。見た目だけでなく、ルール化(コンポーネント/トークン)に寄せる。
Discover blockchain sales marketing skills, compare source repositories and read the instructions for each workflow.
UIを「情報設計(優先度/構造)+インタラクション(状態遷移)+ビジュアル(トーン)」として設計し、実装可能な仕様へ落とす。見た目だけでなく、ルール化(コンポーネント/トークン)に寄せる。
FigmaやUI要件を「壊れない・拡張しやすい」実装へ翻訳するための判断軸。px写経を避け、比率・構造・制約・状態を先に設計してからUIを組み立てる。
認知負荷・エラー防止・学習コスト・アクセシビリティの観点からUI/フローを評価し、改善案を“検証可能な仮説”として提示する。認知人間工学/ユーザビリティ/アクセシビリティを統合して扱う。
体験品質(動き/触感/視線誘導)を「実装可能な制約」に落とし、アクセシビリティとパフォーマンスを犠牲にせずに表現を実現する。UIの表現・アニメーション・インタラクション設計/実装の相談で使う。
プロダクトのペルソナ/ユーザー像を、仮説と根拠(観察・調査・制約)で組み立て、意思決定に使える形へ整形する。※会話口調のペルソナ(にゃんこ)とは別物。
価値提案(誰に/何のために/なぜ勝てる)をレビューし、曖昧さ・矛盾・証拠不足を洗い出して、メッセージとMVPを磨くために使う。
Code quality metrics and continuous improvement. Use when quality standards guidance is required.
Persistent working memory for coding sessions. Automatically tracks what you're doing, why you're doing it, decisions made, and what's next. Trigger phrases: - "resume where we left off" - "what were we doing?...
Generates sequences of high-leverage tasks that increase understanding and improve the code. Use when: - "what should I work on next?" - suggests prioritized tasks - "create a plan for this repo" - generates a...
Feedback-driven skill improvement through tool outcome analysis. Collects execution data and surfaces insights for skill refinement. Use this skill when you want to: - Understand how skills are performing ("sho...
Critical-thinking brainstorming partner that acts as a requirements analyst. Use when users present ideas, feature requests, or problems they want to solve. Triggers include "I want to build", "help me validate...
Create on-brand Canva presentations from an outline or brief. Use when the user asks to create a branded presentation, make an on-brand deck, turn an outline into slides, or generate a presentation from a brief...
Reviews implemented ADRs by comparing them against actual implementation and updating feedback sections. Use this when the user wants to review an ADR implementation, validate architectural decisions, or update...
Iterative specification refinement for large features. Creates detailed What (requirements) and How (implementation) specs through automated codebase research loops followed by human-in-loop review. Use when pl...
Gather initial requirements through questionnaire and generate starting spec document. Used when creating a new feature specification.
Create a structured format for documenting feature requirements as user stories. JSON files with testable acceptance criteria that AI agents can verify and track.
Track custom events and conversions with Vercel Web Analytics. Covers common events, form tracking, and development testing.
ユーザーが PR のマージを求めたときや、エージェントが PR をマージするときに必ず使用してください。
Document and track feature implementation with user stories. Workflow for authoring stories, building features, and marking acceptance criteria as passing.
Learn and refine user ideas through brainstorming. Use when user uploads idea files to the Workplace. Analyzes uploaded content, asks clarifying questions, and produces structured idea summary. Triggers on requ...
Manage feature lifecycle in docs/planning/features.md. Category-level skill called during Step 4 (Category Closing) for feature-stage tasks. Accepts Task Data Model with feature_id and feature_phase, updates fe...
Execute development tasks with planning and tracking. Triggers on requests like "implement feature", "fix bug", "create PR", "design architecture", "set up project". Provides 6-step workflow for task planning,...
Manage idea tracking during ideation-stage tasks. This is a category-level skill called during Step 4 (Category Closing) for ideation-stage tasks. Accepts Task Data Model. Outputs category_level_change_summary.
Manage requirement tracking during requirement-stage tasks. This is a category-level skill called during Step 4 (Category Closing) for requirement-stage tasks. Accepts Task Data Model. Outputs category_level_ch...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.