New skills

Pymatgen is a comprehensive Python library for materials analysis that powers the Materials Project. Create, analyze, and manipulate crystal structures and molecules, compute phase diagrams and thermodynamic properties, analyze electronic structure (band structures, DOS), generate surfaces and interfaces, and access...

Comprehensive guide to using Salesforce's BLIP-2 for vision-language tasks with frozen image encoders and large language models.

Agile sprint planning provides a structured approach to organize work into time-boxed iterations, enabling teams to deliver value incrementally while maintaining flexibility and responding to change.

LLM-generated codebases accumulate semantic duplicates: functions that serve the same purpose but were implemented independently. Classical copy-paste detectors (jscpd) find syntactic duplicates but miss "same intent, different implementation."

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.

Search across all major scientific literature databases (PubMed, arXiv, bioRxiv, medRxiv) simultaneously using natural language queries powered by Valyu's semantic search API.

Smaller bundles download faster, parse faster, and execute faster, dramatically improving perceived performance especially on slower networks.

NVIDIA's toolkit for preparing high-quality training data for LLMs.

A technical roadmap provides a strategic plan for technology evolution, guiding architectural decisions, infrastructure investments, and capability development aligned with business objectives.

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.

NVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs.

Comprehensive assistance with unsloth development, generated from official documentation.

Check build environment BEFORE debugging code. Core principle 80% of "mysterious" Xcode issues are environment problems (stale Derived Data, stuck simulators, zombie processes), not code bugs.

Fast, production-ready tokenizers with Rust performance and Python ease-of-use.

Information Architecture creates logical structures that help users find and understand information easily.

Comprehensive guide to implementing internationalization and localization in applications. Covers message translation, pluralization, date/time/number formatting, RTL languages, and integration with popular i18n libraries.

OpenAlex is a comprehensive open catalog of 240M+ scholarly works, authors, institutions, topics, sources, publishers, and funders. This skill provides tools and workflows for querying the OpenAlex API to search literature, analyze research output, track citations, and conduct bibliometric studies.

Generate high-quality SVG graphics using Python scripts. All scripts output valid SVG to stdout (or file with -o ).

Evaluate interfaces against proven UX principles. Based on Making UX Decisions by Tommy Geoco.

Enable reliable interaction with Anki through the AnkiConnect local HTTP API. Use this skill to translate user requests into AnkiConnect actions, craft JSON requests, run them via curl/jq (or equivalent tools), and interpret results safely.

The GGUF (GPT-Generated Unified Format) is the standard file format for llama.cpp, enabling efficient inference on CPUs, Apple Silicon, and GPUs with flexible quantization options.

Optimize JVM performance through profiling, GC tuning, and memory analysis.

Facebook AI's library for billion-scale vector similarity search.

Source provenance, compatibility, automated checks, and current evidence depth are available on the full page.