发现 Skills

Refine code for clarity and maintainability while preserving functionality

Design meeting intelligence architecture with Fireflies.ai GraphQL API, webhooks, and CRM sync. Use when designing new integrations, planning transcript pipelines, or establishing architecture for meeting analytics platforms. Trigger with phrases like "fireflies architecture", "fireflies design", "fireflies project structure", "meeting intelligence pipeline".

Data handling for Guidewire: entity management, data migration, batch operations, and governance. Trigger: "guidewire data handling", "data-handling".

Manage and avoid common mistakes when using Kling AI. Use when troubleshooting issues or learning best practices to prevent problems. Trigger with phrases like 'klingai pitfalls', 'kling ai mistakes', 'klingai gotchas', 'klingai best practices'.

Complex migration strategies for LangChain applications. Use when migrating from legacy LLM frameworks, refactoring large codebases, or implementing phased migration approaches. Trigger with phrases like "langchain migration strategy", "migrate to langchain", "langchain refactor", "legacy LLM migration", "langchain transition".

Luigi Task Generator - Auto-activating skill for Data Pipelines. Triggers on: luigi task generator, luigi task generator Part of the Data Pipelines skill category.

Performs deep clause-by-clause risk scoring across 10 categories with poison pill detection and financial exposure estimation. Use when a user needs to understand the specific risks in a contract before signing. Trigger with "/risk-analysis" or "what are the risks in this contract".

Configure Supabase CI/CD pipelines with GitHub Actions: link projects, push migrations, deploy Edge Functions, generate types, and run tests against local Supabase instances. Use when setting up CI pipelines for Supabase, automating database migrations, deploying Edge Functions in CI, or running integration tests. Trigger with phrases like "supabase CI", "supabase GitHub Actions", "supabase deploy pipeline", "CI supabase migrations", "supabase preview branches".

Implement features following spec-driven workflow. Read specs first, extract design principles, plan file strategy, then write production-ready code with type hints and docstrings. Use when user asks to implement a feature, write code, or build a module. Depends on spec-sync for specification access.

Track progress across sessions using SESSION.md with git checkpoints and concrete next actions. Converts IMPLEMENTATION_PHASES.md into trackable session state. Use when: resuming work after context clears, managing multi-phase implementations, or troubleshooting lost context.

Apache Superset dashboard automation for Finance SSC, BIR compliance, and operational analytics. Auto-generate dashboards, datasets, and charts. Tableau/Power BI alternative saving $8,400/year in licenses.

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Ultra-fast validation library for TypeScript/JavaScript (77x faster than Zod). Use when building validated schemas for APIs, forms, or data processing. Provides Zod 4-compatible API with WASM-powered SIMD validation.

Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria: methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing and manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.

Use when the user asks about higgsfield.ai - generating images, generating videos, animating an image, Soul ID characters, Cinema Studio 3.5, Seedance, Kling, Veo, Minimax Hailuo, Wan, Nano Banana, Soul 2.0, Soul Cinema, Flux, Seedream, UGC Factory, Lipsync Studio, Marketing Studio, or saving credits / avoiding credit spend on the Creator plan.

three_dart loaders — GLTFLoader for GLTF/GLB models, TextureLoader for images, async loading patterns, and Flutter asset loading. Use when importing 3D models, textures, or external assets into a Flutter three_dart scene.

Manages shared ledgers for family or team collaboration, including shared account summaries, spending statistics, and member settlements. Use when user asks about shared expenses, family ledger, team budget, or joint accounts. 关键词：共享账本、家庭账单、团队支出、AA制。

Generates Puppeteer scripts for browser automation, scraping, and PDF generation. Triggers on: "Puppeteer", "headless Chrome", "page.goto", "scrape", "PDF generation".