Use when writing or refactoring Python code for LangGraph v1.x + LangChain v1: Graph API + Functional API import paths, checkpoint/store usage, and migrations off deprecated prebuilts (create_react_agent -> langchain.agents.create_agent).
Create a safe checkpoint git commit on the current branch (auto-message; include agent log + safe untracked files; avoid secrets and bulky artifacts; track runs/**/{summary,report}.md only).
Debug constructor inheritance issues where subclass properties are accessed before initialization.
Pflege Evaluationsmetriken und Schwellenwerte; verwenden bei Aenderungen an Metriken, Messmethoden oder Akzeptanzkriterien fuer Evaluation.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
読み取り専用で差分をレビューし、ルール違反・リスク・最小修正案を提示する
The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration patterns, plugins, and more. Use this skill anytime you are developing something and want to find a reference to use as a starting point.
Pflege die Extraktion von ATS-Kriterien aus CVs; verwenden bei Anpassungen an Kontakt-, Erfahrung- oder Bildungsextraktion.
Ask whether to proceed with refactoring after architecture mapping.
Tutorial for debugging CUDA crashes using API logging
Converts telemetry and user notes into a structured reflection, confidence score, and next-step guidance.
Concurrency with Effect.all, forEach concurrency, Fiber lifecycle, race and timeouts. Use for parallelizing tasks safely.
Create semantik plugins (connectors, embeddings, chunkers, rerankers, extractors, agents). Use when developing plugins, creating new integrations, or asking about plugin patterns, protocols, or testing.
Run in-session task loops via the codex-taskloop-plugin MCP server and stop hook.
[51] EXECUTE. Commitment to maximum quality work with 150% coverage. Use when you need the highest quality output for critical tasks, complex problems, important decisions, or when standard work isn't enough. Triggers on "maximum quality", "150% mode", "full quality", "critical task", or when you explicitly want AI to work at its best.
agent-browser CLI の仕様と使い方に関する知識を提供。ヘッドレスブラウザ自動化、スナップショット、セレクター、セッション管理、ネットワーク制御について回答。Use when user asks about agent-browser, browser automation, snapshots, selectors, sessions, or web scraping. Also use when user says agent-browser について, ブラウザ自動化, スナップショット, セレクター, セッション管理.
Master expert in product design for complex systems with 10+ years of experience in data-driven systems, operational dashboards, and enterprise SaaS. Integrates six comprehensive areas - UX analysis, UI design, microcopy, user research & flows, personas & journeys, and WCAG accessibility - into one holistic review. Provides end-to-end design analysis with structured recommendations across all design layers. Use when user needs comprehensive design review covering multiple aspects (UX + UI + Content + Accessibility) rather than focused single-area analysis. Triggers include "Review this design comprehensively", "Full design review", "Analyze everything", or when multiple design areas need simultaneous evaluation. Delivers practical, sharp, accurate recommendations for complex operational systems.
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.