skill-generator
Generate SKILL.md files with proper YAML frontmatter, capabilities documentation, and usage examples following Babysitter SDK conventions.
language-server-protocol
Expert skill for implementing Language Server Protocol servers with full IDE feature support
tree-sitter
Expert skill for creating tree-sitter grammars for incremental parsing and syntax highlighting
python-sdk-specialist
Python SDK development with async support and type hints
typography-calculator
Calculate typography scales, metrics, and responsive font sizing
styled-components
Styled Components theming, variants, SSR support, and patterns.
openjudge
Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.
how-to-use-browser
Browser automation skill for web page interaction. Two strategies: (1) Snapshot + refs for simple static pages; (2) JavaScript-first for login forms, SPA, and dynamic pages (PREFERRED). Covers opening URLs, snapshots, clicking, filling forms, evaluating JS, screenshots, tab management, and navigation. Built on go-rod/CDP with headless Chrome. If snapshot returns 0 element refs, DO NOT retry -- switch to JavaScript strategy immediately.
ref-hallucination-arena
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
bib-verify
Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.