Conduct systematic meta-analyses with effect size pooling and heterogeneity

Sample size calculation and statistical power analysis guide

Load, explore, clean, and analyze CSV data with statistical summaries

Systematic data cleaning workflows for research datasets

Clean, transform, and validate messy research data using Stata

End-to-end data analysis AI agent with Streamlit UI

Clean, recode, and prepare survey response data for analysis

Curated guide to generative AI covering LLMs and diffusion models

Guide to Transformer architectures for NLP and computer vision

Workflows for RNA-seq, GWAS, and variant calling in genomic research

Medical image analysis with deep learning for research applications

Query computational catalysis reaction data via Catalysis Hub GraphQL

Access 4M+ economics working papers and articles via RePEc API

Access earth and environmental science datasets via PANGAEA API

Topological data analysis: persistent homology, Mapper, and TDA tools

Disambiguate author identities via the VIAF authority file API

Search and retrieve preprints from the arXiv open-access repository

Command-line tools for searching and batch-downloading arXiv papers

Research data sharing and repository

Build and analyze citation networks from academic reference data

Design ontologies and knowledge graphs for research data modeling

RAG architecture for academic knowledge retrieval and synthesis

Manage references with BibLaTeX, natbib, and LaTeX bibliography styles

LaTeX drawing examples for Bayesian networks, tensors, and diagrams

Create publication-quality scientific diagrams with TikZ in LaTeX

Create SVG graphical abstracts for journal paper submissions

>-

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

Competitive intelligence, market analysis, and strategic positioning for product differentiation.

SerpApi search engine results API via curl. Use this skill to scrape Google, Bing, YouTube, and other search engines.

Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.

Automatically evaluates OmG sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.

Use when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview.

**🚀 Enhanced with Local Validators**: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. C

Deterministic workflow to download MATLAB Package Manager (mpm) and install MathWorks products from the OS command line with consistent, repeatable behavior. Use when installing MATLAB, Simulink, toolboxes, or support packages via command line, or setting up scripted installations for CI/CD, containers, or fleet provisioning.

Calculate line-of-sight and road distances between two cities using free OpenStreetMap services.

Manipulate PDF files including merge, split, extract, redact, convert, and secure workflows.

Search for torrents by title or IMDB ID via a Torznab-compatible API. Use when: (1) User asks to find a torrent for a movie or show, (2) You need a magnet link for a given title, or (3) User provides an IMDB ID and wants download options.

>

>

>

>

将绑定/映射结果写回 .bkn 文件。

Send and receive messages via Telegram for two-way agent communication. Use when the agent needs to notify the user, alert them about something, relay a response, or when Telegram messaging is the requested channel. Trigger words: send message, Telegram, notify, alert user, message me, ping me, let me know, reach out.

Fetch web content efficiently by checking llms.txt first, then Cloudflare markdown endpoints, then falling back to HTML. Reduces token usage by 80% on sites that support clean markdown delivery. No external dependencies — installs a single Python script. Trigger words: fetch URL, web content, read website, scrape page, download page, get webpage, read this link.

Primitive web crawling and scraping for one or more URLs. Use when a user shares links, asks to ingest or archive web content, or needs raw source artifacts normalized into reusable local records before feed-building or synthesis.

Implements Syncfusion .NET MAUI ListView (SfListView). Use when displaying lists or collections of data in MAUI applications, implementing data grids, creating scrollable item lists, or adding sorting/filtering/grouping. Covers item selection, layout customization, swipe actions, pull-to-refresh, load more, and drag-drop items.

Implements and customize Syncfusion .NET MAUI TreeView (SfTreeView) for displaying hierarchical data structures. Use when working with TreeView, hierarchical data display, tree structures, organizational charts, nested data, expand/collapse nodes, file explorer UI, folder structures, parent-child relationships, or multi-level data visualization in .NET MAUI applications.

sqlite-vec extension for vector similarity search in SQLite. Use when storing embeddings, performing KNN queries, or building semantic search features. Triggers on sqlite-vec, vec0, MATCH, vec_distance, partition key, float[N], int8[N], bit[N], serialize_float32, serialize_int8, vec_f32, vec_int8, vec_bit, vec_normalize, vec_quantize_binary, distance_metric, metadata columns, auxiliary columns.

- **Stage:** Seed-stage B2B SaaS