发现 Skills

Use when optimizing performance or reviewing security. Covers code-splitting, React Compiler patterns, asset optimization, a11y testing, and security hardening for React apps.

Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via Claude, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok Code Fast) and proven consultation strategies based on real-world testing.

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Apply production-grade Symfony architecture and execution workflows with controlled scope and clear checkpoints. Use for writing plans tasks.

Implement an Empirica experiment from a spec using the correct Classic lifecycle primitives, updating server callbacks, client components, and treatment/lobby config consistently.

> This module is a **submodule** of `novel-harness`, designed to reduce AI-like phrasing and restore an ordinary human's natural writing style. > ⚠ **This file is the L1 index layer** — it only contains core principles and a directory of rules. > Specific rules are placed in the `rules/` directory and are loaded on demand. > > **Core positioning**: not a grammar corrector, but stylistic alignment of writing sensibility. Teach the AI "how ordinary people write", not "how the AI thinks it should write".

Create content in the user's voice — LinkedIn posts, emails, blog posts, proposals, or ad copy. Use when user says "write a post about X", "draft an email to X", "create content about X", or "write copy for X".

Comprehensive OAuth2 authentication skill covering authorization flows, token management, PKCE, OpenID Connect, and security best practices for modern authentication systems

Advanced Python unit testing framework for customer support tech enablement, covering FastAPI, SQLAlchemy, PostgreSQL, async operations, mocking, fixtures, parametrization, coverage, and comprehensive testing strategies for backend support systems

Comprehensive Vue.js development skill covering Composition API, reactivity system, components, directives, and modern Vue 3 patterns based on official Vue.js documentation

Common style patterns, layer configurations, and recipes for typical mapping scenarios including restaurant finders, real estate, data visualization, navigation, and more. Use when implementing specific map use cases or when looking for proven style patterns.

Write a Marimo notebook to a Python (.py) file using the correct Marimo formatting.

Use when adding logging, debugging output, metrics collection, or when a user mentions logging, observability, diagnostics, monitoring, or debug data. Implements structured logging, diagnostics, and observability patterns optimized for AI agent consumption; examples use Python but the principles are language-neutral.

This skill should be used when the user asks to "write agent spec", "define agent role", "specify an agent", "agent specification", "what should my agent do", "agent inputs outputs", "agent design discovery", "design my agent", or needs to create a proper agent definition. Provides discovery questions and specification format that prevents 42% of MAS failures.

Configure and customize OpenCode CLI. Use when (1) setting up opencode.json config, (2) connecting providers and API keys, (3) creating custom agents, (4) building skills, (5) configuring MCP servers, (6) setting up themes and keybinds, (7) managing tool permissions, (8) configuring formatters and rules.

Comprehensive guide for building 2D games with Flutter and Flame Engine. Covers game architecture, sprites, animations, collision detection, input handling (keyboard/joystick/gamepad), camera systems, Tiled maps, audio, particles, and UI overlays. Use when creating or refactoring Flutter games.

Invoke Gemini for design/code review. PROACTIVE: (1) BEFORE proposing new features/architecture, (2) AFTER >100 lines or >3 files changed (before tests), (3) AFTER security/perf changes, (4) ON SESSION RESUME - check thresholds first. Triggers on "new feature", "architectural decision", "security review", "performance review", "code review", "gemini review", "debug", "cross-service", "data flow", "frontend backend", "analysis", "implementation complete", "run the tests", "commit these", "modified multiple files", "session resumed", "context compaction", "left off", "I've implemented", "I've added", "I've modified", "changes are done", "done implementing", "finished implementing", "implementation is complete", "let me run", "now let me test", "rebuild", "make rebuild", "pytest", "all tests pass", "tests pass", "fixed the", "added the", "updated the".

Token-saving delegation to Gemini. Use for reasoning, research, code analysis, or generation tasks where Claude Pro tokens are limited.

Use this skill when reusable functionality has stabilized and is used by multiple components, to extract it into a dedicated library with clear ownership, versioning expectations, and minimal surface area.

SQLiteData queries, @Table models, Point-Free SQLite, RETURNING clause, FTS5 full-text search, CloudKit sync, CTEs, JSON aggregation, @DatabaseFunction

Comprehensive SEO analysis for any website or business type. Performs full site audits, single-page deep analysis, technical SEO checks (crawlability, indexability, Core Web Vitals with INP), schema markup detection/validation/generation, content quality assessment (E-E-A-T framework per Dec 2025 update extending to all competitive queries), image optimization, sitemap analysis, and Generative Engine Optimization (GEO) for AI Overviews, ChatGPT, and Perplexity citations. Analyzes AI crawler accessibility (GPTBot, ClaudeBot, PerplexityBot), llms.txt compliance, brand mention signals, and passage-level citability. Industry detection for SaaS, e-commerce, local business, publishers, agencies. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "page speed", "structured data".

Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Use when user says "analyze this page", "check page SEO", or provides a single URL for review.

Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.