持續整合/部署

This skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Comprehensive Nix validation: treefmt-nix integration, statix/deadnix linting, flake checks, khanelinix-specific patterns. Use when validating Nix code or setting up linting infrastructure.

khanelinix theme system patterns. Use when configuring themes, working with Stylix or Catppuccin, or implementing theme-aware module configuration.

khanelinix directory structure and module placement. Use when creating new modules, deciding where files belong, or understanding the modules/ organization. Covers platform separation (nixos/darwin/home/common) and auto-discovery.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Nix library usage patterns: with, inherit, and inline lib. prefixes. Use when deciding how to access lib functions, avoiding the with lib anti-pattern, or writing analysis-friendly Nix code.

khanelinix 7-level configuration hierarchy and customization strategy. Use when deciding where to put customizations, understanding override precedence, or working with host/user specific configs.

khanelinix option namespacing and design patterns. Use when defining module options, accessing configuration values, or understanding the khanelinix.* namespace convention.

Automates the release process for the ts-oauth2-server project.

Analyze spring-data-relational version changes and identify required updates for the current project. Use when upgrading spring-data-relational versions or syncing with upstream changes.

Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.

Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

Create optimized llm-context rules for specific tasks by analyzing codebase content and generating minimal file selection patterns

This skill should be used when the user mentions GitHub PRs, issues, workflows, releases, or repository management. Triggers on keywords like "github", "gh", "pr", "pull request", "issue", "workflow", "actions", "release", "merge", "review", "ci", "check", or PR/issue number patterns like "#123".

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Patterns for testing code effectively. Use when breaking dependencies for testability, adding tests to existing code, understanding unfamiliar code through characterization tests, or deciding how to structure tests. Covers seams, dependency injection, test doubles, and safe refactoring techniques from Michael Feathers.

Implicit feedback scoring, confidence decay, and anti-pattern detection. Use when understanding how the swarm plugin learns from outcomes, implementing learning loops, or debugging why patterns are being promoted or deprecated. Unique to opencode-swarm-plugin.