Discover Databases skills, compare source repositories and read the instructions for each workflow.
Guides creation of new skills following dsmj-ai-toolkit v2.0 format with validation. Trigger: When creating new skills, when user says "create skill", when adding domain knowledge, when documenting patterns, wh...
Type-safe APIs with tRPC - End-to-end typesafe APIs without code generation. Covers routers, procedures, context, middleware, and React Query integration. Trigger: When creating tRPC routers, when implementing...
Tailwind CSS patterns for utility-first styling, responsive design, and component composition. Trigger: When styling with Tailwind CSS, when implementing responsive designs, when building UI components, when co...
Error handling patterns for try-catch, error boundaries, structured logging, and exception strategies. Trigger: When implementing error handling, when building error boundaries, when setting up logging, when de...
Orchestrate V2 transaction MDX documentation coverage and quality tracking
Review individual V2 transaction MDX documentation for coverage and accuracy
Orchestrate V2 transaction documentation by tracking all endpoints and delegating analysis to /analyze-transaction
Parse decoded V2 transaction CBORs from Atlas API and create/update documentation YAML files
実装計画の続きから作業を再開。doc/plans/ の計画ファイルを読み込み、「8. 現在の進捗」セクションから次のタスクを把握して実装を継続する。セッション開始時やコンテキスト圧縮後の復帰に使用。トリガー - 「計画を再開」...
機能実装後のドキュメント更新をサポート。新機能追加、API変更、画面追加、スキーマ変更時に doc/ARCHITECTURE.md、doc/INDEX.md、doc/features/*.md を更新する手順と判断基準を提供。
GitHubにPull Requestを作成するスキル。コミット・プッシュ済みの状態で、現在のブランチの変更内容を分析し、適切なタイトルと説明文でPRを作成する。「PRを作成して」「プルリクエストを作って」「PR作って」などのトリガー...
実装計画をファイルに保存する。実装計画、タスク計画、作業計画を立てた後に使用。コンテキスト圧縮後も参照可能にするため doc/plans/ に保存する。トリガーキーワード: 実装計画, 計画保存, plan, 作業計画
Unified Specification-Driven Development (SDD) workflow. Auto-detects user intent and routes to correct phase. Handles the complete development lifecycle from product definition to implementation. Triggers on:...
Best-practice prompt engineering using research-backed patterns. Handles: transforming rough prompts into production-ready, debugging prompt issues, creating new prompts from scratch. ALWAYS researches via suba...
Comprehensive Next.js project setup from scratch following industry best practices. Use when creating new Next.js projects, requiring template selection, design system ideation, specifications, wireframes, impl...
Debug bugs and errors using intel-first approach with systematic root cause analysis. Use proactively when errors occur, tests fail, or unexpected behavior appears. MUST trace from symptom to root cause with Co...
Execute end-to-end tests for Nikita using Telegram MCP, Gmail MCP, Supabase MCP, Chrome DevTools MCP, and gcloud CLI. Use when verifying implementations, testing user journeys, validating integrations, performi...
Create detailed implementation plans from feature specs or bug reports with testable acceptance criteria. Use proactively when planning features, refactors, or fixes. Every task MUST have minimum 2 testable ACs...
Intelligence-first code analysis for bugs, architecture, performance, and security. Use proactively when investigating code issues, tracing dependencies, or understanding system behavior. MUST query project-int...
Audit and optimize website for AI search engines like ChatGPT, Perplexity, Google AI Overviews, and Claude. Use when discussing GEO (Generative Engine Optimization), SEO for AI, llms.txt, AI crawlers, structure...
Helps with OSD JSON configuration files and schema. Use when editing config.json, modifying widget settings, changing fonts, or working with the JSON schema.
Helps with WASM compilation, building, and packaging. Use when discussing build targets, Makefile commands, build modes, or WASM compilation issues.
Helps with deploying OSD packages to sych.local. Use when discussing deployment, hot-reload, frontend updates, or gallery updates.
Helps with protobuf messages, updating proto submodules, and understanding the JonGUIState structure. Use when working with proto files, message fields, or state data.
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.