发现 Skills

Build monitoring dashboards for platforms like Grafana and SigNoz that can answer real-world operations questions. Suitable for converting metrics into usable dashboards rather than flashy, non-actionable displays.

Orchestrate multi-agent workflows using dmux (a tmux-pane manager for AI agents). Enables parallel-agent workflow patterns across Claude Code, Codex, OpenCode and other tools. Suitable for running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Idiomatic C# and .NET patterns, conventions, dependency injection, async/await, and best practices for building robust, maintainable .NET applications.

Development conventions and patterns for everything-claude-code. JavaScript project with Conventional Commits.

A library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.

Clinical Decision Support System (CDSS) patterns, medical reasoning, and evidence-based implementations.

Japanese translation: This file requires a Japanese translation for messages-ops.

Japanese translation: This file requires a Japanese translation for motion-ui.

Japanese translation: This file requires a Japanese translation for mysql-patterns.

Japanese translation: This file requires a Japanese translation for nestjs-patterns.

Japanese translation: This file requires a Japanese translation for project-flow-ops.

Japanese translation: This file requires a Japanese translation for 'quality-nonconformance'.

Design composable recommendation, ranking, and feed pipelines using the six-stage Source → Hydrator → Filter → Scorer → Selector → SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

Rust testing patterns including unit tests, integration tests, asynchronous tests, property-based tests, mocks, and coverage. Follows TDD methodology.

Multi-agent adversarial verification with a convergent loop. Two independent review agents must both approve before an output may be released.

Use this skill when adding authentication, handling user input, managing secrets, creating API endpoints, or implementing payment or other sensitive features. Provides a comprehensive security checklist and patterns.

Used when developing application modules or microservices with the tinystruct framework. Covers routing, context management, JSON handling via the Builder, and a CLI/HTTP dual-mode pattern.

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky-test strategies.

Implementation patterns, quantization, optimization, and privacy-aware inference for on-device FoundationModels.

Automated hook implementation, event-driven execution, and rule-driven workflows.

Japanese translation: This file requires a Japanese localization for mcp-server-patterns.

Japanese translation: This file requires a Japanese translation for network-config-validation

Comprehensive Perl security covering taint mode, input validation, secure process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.

Multi-agent adversarial verification with a convergence loop. Two independent review agents must both pass before an output can be shipped.