发现 Skills

Library of abstract domains for static analysis and abstract interpretation

Expert skill for Node.js-specific profiling and optimization. Use the V8 CPU profiler, analyze heap snapshots, configure clinic.js tools (Doctor, Flame, Bubbleprof), debug event-loop blocking, analyze async_hooks performance, and optimize V8 JIT compilation.

Enforces an opinionated UI baseline to prevent AI-generated interface slop.

This skill should be used when the user mentions Jujutsu version control, "jj" commands, working with jj repositories, or asks about Git to Jujutsu equivalents. Triggers on keywords like "jujutsu", "jj", "jj-vcs", "jj repo", "jj commit", "jj log", "jj new", "jj squash", "jj rebase", "jj bookmark", or questions about Jujutsu workflows and concepts.

Audit and optimize WordPress SEO (Yoast/Rank Math) — checks focus keywords, meta descriptions, and featured images. Uses the Unsplash API to fetch missing images. Run across all pages and posts to identify and fix SEO issues.

Build enterprise Spring Boot applications with annotations, dependency injection, data persistence, REST controllers, and security. Use when developing Spring applications, managing beans, implementing services, and configuring Spring Boot projects.

Microsoft 365 tenant administration for Global Administrators. Automate M365 tenant setup, Office 365 admin tasks, Azure AD user management, Exchange Online configuration, Teams administration, and security policies. Generate PowerShell scripts for bulk operations, Conditional Access policies, license management, and compliance reporting. Use for M365 tenant manager, Office 365 admin, Azure AD users, Global Administrator, tenant configuration, or Microsoft 365 automation.

Relational database implementation across Python, Rust, Go, and TypeScript. Use when building CRUD applications, transactional systems, or structured data storage. Covers PostgreSQL (primary), MySQL, SQLite, ORMs (SQLAlchemy, Prisma, SeaORM, GORM), query builders (Drizzle, sqlc, SQLx), migrations, connection pooling, and serverless databases (Neon, PlanetScale, Turso).

Navigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests. Use when reviewing data processing agreements, responding to data subject access or deletion requests, assessing cross-border data transfer requirements, or evaluating privacy compliance.

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping with scANVI/scArches, (7) RNA velocity with veloVI, or (8) any deep learning-based single-cell method. Triggers include mentions of scVI, scANVI, totalVI, PeakVI, MultiVI, DestVI, veloVI, sysVI, scArches, variational autoencoder, VAE, batch correction, data integration, multi-modal, CITE-seq, multiome, reference mapping, latent space.

Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.

```markdown

Manage local Airflow environment with Astro CLI. Use when the user wants to start, stop, or restart Airflow, view logs, troubleshoot containers, or fix environment issues. For project setup, see setting-up-astro-project.

Use Bedrock tool_use to guarantee structured JSON outputs from Claude models. Eliminates JSON parsing failures by forcing responses through typed tool schemas.

Master Material Design 3 and Jetpack Compose patterns for building native Android apps. Use when designing Android interfaces, implementing Compose UI, or following Google's Material Design guidelines.

Create distinctive, high-converting landing pages that combine proven conversion elements with exceptional design quality. Build beautiful, memorable landing pages using Next.js 14+ and ShadCN UI that avoid generic AI aesthetics while following the 11 essential elements framework.

version: "2.0.0" name: Short Drama Writer description: "Short Drama Writer. Use when you need short drama writer capabilities. Triggers on: short drama writer." Short drama script generator. Vertical short dramas, micro-dramas, plot design, character development. Short dra...

Meta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow. Triggers on "design workflow skill", "create workflow skill", "workflow skill designer".

Transform raw ideas and brain dumps into polished YouTube scripts using a structured, checkpoint-based workflow. Use this Skill when a user wants to write a YouTube script, improve viewer retention, craft hooks, structure educational or entertainment content, or turn source material (transcripts, notes, research) into a compelling video script. Guides creators through research, hook creation, story structure, body content, and editing phases.

Use when the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions 'exit intent', 'popup conversions', 'modal optimization', 'lead capture popup', 'email popup', 'announcement banner', 'overlay', 'collect emails with a popup', 'exit popup', 'scroll trigger', 'sticky bar', or 'notification bar.' Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro.

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' 'partner program,' 'referral incentive,' 'how to get referrals,' 'customers referring customers,' or 'affiliate payout.' Use this whenever someone wants existing users or partners to bring in new customers. For launch-specific virality, see launch-strategy.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when needing clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).