Improve how interfaces use photos, screenshots, icons, illustrations, and user-uploaded media so visuals support clarity instead of undermining it. Use when the user mentions images, screenshots, background photos, hero images, icon sizing, user-uploaded media, crops, overlays, or image readability.

Comprehensive mobile app testing strategies for iOS and Android. Covers unit tests, UI tests, integration tests, performance testing, and test automation with Detox, Appium, and XCTest.

Uses the Selora AI MCP server to inspect home state, validate/create automations, manage automation lifecycle, and handle proactive pattern/suggestion workflows. Use when users ask to analyze their home, review Selora automations, validate YAML, create/enable/delete automations, list or act on suggestions/patterns, trigger a scan, or continue Selora chat sessions.

>-

Add dark mode styles to components using Tailwind dark: variant classes. Use when creating new components, adding dark mode support to existing components, or when the user mentions dark mode, theming, or light/dark variants.

Prepares the CHANGELOG.md file for release by updating the [Unreleased] section with the current plugin version and date. Use when the user asks to prepare changelog for release, update changelog for release, or finalize changelog entries.

>-

Building AI/LLM features. Semantic Kernel setup, plugins, prompt templates, memory stores, agents.

Generate a sprint review changelog from GitHub pull requests. Lists PRs by a given author since a given date, groups them into Features and Fixes, and writes a markdown summary.

>-

React Hooks技能。当用户需要编写自定义Hooks、理解Hooks用法、封装Hooks逻辑、或询问React状态管理时使用此skill。

Write and edit QuickMarkup declarative UI markup in C# projects. Use when the project uses QuickMarkup, identifiable by `using QuickMarkup.Infra`, `using QuickMarkup.SourceGen`, or `[QuickMarkup(...)]` attribute in .cs files.

Implements the Untitled Placeholder Technique: create N placeholders → capture IDs → generate all scripts with correct wiring → deploy → rename.

Expert in systematic debugging, root cause analysis, test automation, and stealth bug hunting. Find what developers forgot. Test behavior, not implementation.

This skill provides expertise in Clean Architecture and Hexagonal Architecture (Ports and Adapters) patterns in Go, including dependency inversion, layer separation, and testable design.

YWeb 基础设施模块规范。在使用缓存（@cached）、异常处理（Err/register_exception_handlers）、日志（get_logger）、配置（AppSettings/YAML）、文件存储（本地/OSS/S3）、定时任务（Scheduler）、限流（setup_ratelimit）时使用。

Seek out and update agent discovery files as conventions evolve. Use when agent ecosystems add new ways to state behavior, skills, or rules; when discovery files need revision; or when maintaining FOR_AGENTS.md, .cursorrules, docs/for-agents.md, docs/agent-discovery.md.

Analyze OpenAPI/Swagger spec (JSON or YAML) against existing test files and generate an HTML coverage report with QA automation tasks. Use when user provides an OpenAPI spec file and wants to know test coverage status.

Set up Claude Code for your project by:

>-

Implement video streaming and content systems including video-on-demand, live streaming, video conferencing, and content management. Use when building video platforms, streaming apps, video conferencing features, or media content systems. Triggers on requests for video upload, live streaming, video calls, media libraries, or video content management.

Deep TypeScript typing for discriminated unions, exhaustive handling, generics, satisfies, branding, and fixing tsc output without any or silent unknown on public APIs. Use when resolving complex type errors or designing type-heavy APIs. Pairs with general-typescript (no any; unknown only with explicit user approval). Triggers on generics, union, narrowing, exhaustive, satisfies, inference.

'Define como componentes Angular devem ser criados, estruturados, documentados e testados no Design System Lumo.'

Evaluate and validate ground truths for Oak semantic search using the COMMIT protocol.

Fix a specific bug or problem in the codebase. Supports two modes: immediate fix or plan-first approach.

以资深架构师视角对 Diff/源码做深度 Code Review：正确性与防御性、架构合规、DRY、KISS、测试完备性；禁止格式挑刺；单次最多 5 条高价值问题；无重大问题输出 LGTM。在用户附上改动、请求审查、PR review、走查、diff 评审时触发。

>

Create an implementation plan for a feature or task. Two modes:

Transforms AI-generated text into human-sounding writing by applying a **fixed, ordered pipeline of rules**. Each rule is a specific find/replace or structural operation. The agent executing this skil

Generate an app icon from a single 1024² master and fan out to iOS (AppIcon.appiconset with squircle-ready 1024 opaque), Android (adaptive foreground + background + Android 13 monochrome), PWA (192/512 + 512 maskable with 80% safe zone), and visionOS (3-layer parallax).

PyVISA and lab instrument control in Python: VISA resource lifecycle, timeouts and terminations, raw TCP/UDP sockets vs VISA, when to introduce hardware abstraction layers, validating user and config input before hardware, testing without hardware, and extracting tables or text from instrument manuals and datasheets (PDF). Triggers on pyvisa, VISA, GPIB, USB-TMC, serial instrument, socket lab, SCPI, datasheet PDF, instrument driver.

STEP 2 of the application pipeline. Evaluates fit between active_application/job_description.md and the user's profile, then produces active_application/application_brief.md. Trigger: user explicitly asks to evaluate fit, discuss the role, or generate an application brief — AND active_application/job_description.md is already populated. Do NOT trigger when the user is sharing or pasting a raw job description for the first time; that is handled by job-researcher (Step 1).

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Audits PWA aspects of SunnahSleep. Use when working on offline support, service worker, manifest, caching, or install flow. Covers vite-plugin-pwa, Workbox, and PWA best practices.

You are a helpful coding assistant for a LLM-as-a-judge evaluation task. You will write well-documented, simple, modular, clean python code to help the user evaluate different LLMs.

Query, inspect, or refresh codebase intelligence files in .planning/intel/

Grade an attached rule or command file using the rubric.

Generate or review least-privilege MCP configs for this project.

Execute development work from a pool of GitHub issues. Take one at a time, implement via act-dev, close the issue when done. Use when architect/PM has produced a backlog of issues to implement in parallel.

Storage backends and indexing for vector databases in Elixir. Use when choosing persistence, implementing exact vs approximate k-NN, or integrating pgvector, file, or ETS for vector storage.

Ordo testing and benchmarking guide. Includes unit tests, integration tests, Criterion benchmarks, k6 load tests, CI configuration. Use for writing tests, performance analysis, continuous integration.

Write comprehensive, user-focused documentation following the Diataxis framework. Use this skill when creating or improving tutorials, how-to guides, reference documentation, or explanatory content. Helps identify the right documentation type and apply best practices for each.

>

Export the design profile as CSS custom properties with dark mode overrides.

>-

Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Guidance for `effect/Tuple` focused on APIs like get, map, and make. Load after `effect-skill-router` when this module is the primary owner.

Guide for continuing work on a VOM ticket - reminds agents to claim and check guidance before starting.

>-

Expert-level Mermaid diagram creation, validation, and multi-format rendering. Creates diagrams from descriptions or code analysis, validates syntax, and renders to SVG, PNG, or ASCII with professiona