Plan and execute large refactors with shadow mode and rollback.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
When asked to commit the codebase, follow these guidelines
Integrate Dapr building blocks for event-driven microservices - Pub/Sub, State Management, Secrets, Service Invocation, and Jobs API. Use when implementing event-driven architecture for Phase 5. (project)
name: diff-doc-sync
Expert knowledge in Go clean architecture patterns and best practices
Load CSV/XLSX into DuckDB with validation and an ETL markdown report
Dokumentiere Architekturentscheidungen (ADRs) und Architektur-Updates; verwenden bei neuen Design-Entscheidungen oder Aenderungen am Architektur- oder Technologie-Stack.
Repo workflow for markdowntown CLI development and scans.
Converts telemetry and user notes into a structured reflection, confidence score, and next-step guidance.
Create semantik plugins (connectors, embeddings, chunkers, rerankers, extractors, agents). Use when developing plugins, creating new integrations, or asking about plugin patterns, protocols, or testing.
name: family-recipe-lore
Handle Restio support tickets when the user provides a ticket ID like XX-### (e.g., 'YYYYY-##: TASK - ...'). Use this skill to fetch the ticket via the restio-support MCP, prepare git branches, summarize the ticket, and request confirmation before making any code changes.
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.
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices). Use when choosing libraries, investigating solutions, understanding legal/technical questions, comparing approaches, or anytime you need comprehensive knowledge from both project context and world knowledge. Triggers on "research", "investigate", "find best approach", "what do others do", "compare options", or complex questions requiring multiple sources.
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.
Use when you need a detailed execution trace of a Python script using sys.monitoring, including logging every operation with include/exclude event controls.
Generates 14–21 day running plans tailored to onboarding data and recent performance.
Design and implement the Viet K-Connect visa assessment engine (DB-driven ruleset JSON schema + versioning + effective dates). No hardcoded rules in code. Use for building /api/visa/assess and admin ruleset management. (키워드= 비자 평가, 룰셋, 규칙 엔진, DB-driven, 버전/적용일, /api/visa/assess)