发现 Skills

KEGG pathway and module enrichment analysis using clusterProfiler enrichKEGG and enrichMKEGG. Use when identifying metabolic and signaling pathways over-represented in a gene list. Supports 4000+ organisms via KEGG online database.

End-to-end multiome workflow for joint scRNA-seq + scATAC-seq analysis. Covers data loading, separate modality processing, and WNN integration with Seurat/Signac. Use when analyzing joint scRNA+scATAC data.

Create scalable, containerized bioinformatics pipelines with Nextflow DSL2 supporting Docker, Singularity, and cloud execution. Use when building portable pipelines with container support, running workflows on cloud platforms (AWS, Google Cloud), or leveraging nf-core community pipelines.

Analyze Perturb-seq and CROP-seq CRISPR screening data integrated with scRNA-seq. Use when identifying gene function through pooled genetic perturbations in single cells.

Use when managing asset metadata, dependencies, and delivery workflows across teams.

Xcode 26 and Apple platform update notes with a focus on Liquid Glass, Foundation Models Framework, and Apple Intelligence. Use when asked to explain, summarize, compare, or implement Xcode 26 era framework changes across SwiftUI, UIKit, AppKit, Foundation, App Intents, StoreKit, MapKit, WidgetKit, visionOS, or Swift language features.

Godot UI interface system development expert that uses natural language descriptions to automatically create menus, HUDs, dialogs, responsive layouts and complete UI systems.

Standards for separation of concerns, layer dependency rules, and DDD in Flutter. Use when applying DDD or layer-based clean architecture in Flutter.

Standards for synchronous (Feign) and asynchronous (Cloud Stream) communication

Use when the user explicitly requests "check/optimize the citations in the body of `{topic}_review.tex`" or "run check-review-alignment". Check each citation against the literature content through the semantic understanding of the host AI, and only make minimal rewrites to the "sentences containing citations" when a fatal citation error is found. Reuse the rendering script of `systematic-literature-review` to output PDF/Word (the script does not directly call the LLM API locally). Core principle: **do not change just for the sake of changing**. When it is unclear whether it is a fatal error, keep it as is and issue a warning in the report. ⚠️ The following situations do not apply: - The user just wants to generate the body of the systematic review (should use systematic-literature-review) - The user just wants to add/verify BibTeX entries (should use a dedicated bib management process)

Review Express.js security audit patterns for middleware and routes. Use for auditing Helmet.js, CORS, body-parser limits, and auth middleware. Use proactively when reviewing Express.js apps. Examples: - user: "Secure my Express app" → add Helmet.js and disable x-powered-by - user: "Check Express CORS config" → verify origin allowlists and credentials - user: "Review Express auth middleware" → check route order and coverage - user: "Scan for Express path traversal" → verify path normalization and validation - user: "Audit Express session config" → check secure, httpOnly, and sameSite flags

Control Sonos speakers (discover/status/play/volume/group).

Extracts content from news sites. Supports WeChat Official Accounts, Jinri Toutiao, NetEase News, Sohu News, and Tencent News. Activate when the user needs to extract news content, scrape public account articles, crawl news, or obtain news in JSON/Markdown.

Generate comprehensive trading plans with risk management, position sizing, entry/exit strategies, and performance tracking to trade with discipline and consistency.

Delegate coding tasks to Codex, Claude Code, or Pi agents via a background process. Use when: (1) building or creating new features or apps, (2) reviewing PRs (spawn agents in a temp dir), (3) refactoring large codebases, (4) performing iterative coding that requires file exploration. NOT for: simple one-liner fixes (just edit directly), passive code reading (use the read tool), or any work inside the ~/clawd workspace (never spawn agents there). Requires a bash tool that supports pty:true.

Create comprehensive steering documents for development projects. Generates project-specific standards, git workflows, and technology guidelines in .kiro/steering/ directory.

Troubleshoot Cursor codebase indexing: stuck indexing, empty search, @codebase failures, and performance issues. Triggers on "cursor indexing", "cursor index", "@codebase not working", "cursor search broken", "indexing stuck".

Implement production pre-recorded speech-to-text with Deepgram. Use when building audio transcription, batch processing, or implementing diarization and intelligence features. Trigger: "deepgram transcription", "speech to text", "transcribe audio", "batch transcription", "deepgram nova", "diarize audio".

This skill empowers Claude to perform feature engineering tasks for machine learning. It creates, selects, and transforms features to improve model performance. Use this skill when the user requests feature creation, feature selection, feature transformation, or any request that involves improving the features used in a machine learning model. Trigger terms include "feature engineering", "feature selection", "feature transformation", "create features", "select features", "transform features", "improve model performance", and similar phrases related to feature manipulation.

Detect profitable arbitrage opportunities across CEX, DEX, and cross-chain markets in real-time. Use when scanning for price spreads, finding arbitrage paths, comparing exchange prices, or analyzing triangular arbitrage opportunities. Trigger with phrases like "find arbitrage", "scan for arb", "price spread", "exchange arbitrage", "triangular arb", "DEX price difference", or "cross-exchange opportunity".

Optimize Granola transcription accuracy, note quality, and processing speed. Use when improving transcription quality, reducing processing time, optimizing templates for better AI output, or tuning audio setup. Trigger: "granola performance", "granola accuracy", "granola quality", "improve granola", "granola transcription better".

Optimize Langfuse tracing performance for high-throughput applications. Use when experiencing latency issues, optimizing trace overhead, or scaling Langfuse for production workloads. Trigger with phrases like "langfuse performance", "optimize langfuse", "langfuse latency", "langfuse overhead", "langfuse slow".

Implement Langfuse security best practices for API keys and data privacy. Use when securing Langfuse integration, protecting API keys, or implementing data privacy controls for LLM observability. Trigger with phrases like "langfuse security", "langfuse API key security", "langfuse data privacy", "secure langfuse", "langfuse PII".

Configure Lokalise CI/CD integration with GitHub Actions and automated sync. Use when setting up automated translation sync, configuring CI pipelines, or integrating Lokalise into your build process. Trigger with phrases like "lokalise CI", "lokalise GitHub Actions", "lokalise automated sync", "CI lokalise", "lokalise pipeline".