kreuzberg
High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
310 skills found
High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.
Elasticsearch DBA skill for cluster architecture, mapping design, performance tuning, and production operations including ILM, shard strategy, and troubleshooting.
Operate the btca CLI for source-first code research. Manage git, local, and npm resources to ground AI answers in actual codebase context rather than outdated documentation.
An agent-first, zero-based envelope budgeting CLI for tracking finances with SQLite or Turso/libSQL backends.
Evidence-first literature collector for automated research pipelines. Scales paper pools to 1200+ with metadata normalization, provenance tracking, and multi-source ingestion.
Access Y Combinator’s library of 443+ startup resources for expert advice on fundraising, co-founders, product development, growth, and scaling your business.
A structured repository of Agent Skills for context engineering, multi-agent architectures, and production-grade agent system optimization.
Unified AI gateway for 100+ LLMs with OpenAI-compatible API, model fallbacks, load balancing, and enterprise-grade tools.
Guidelines for curating high-quality datasets for LLM post-training (SFT/DPO/RLHF), covering data formats, quality filtering, and collection strategies.
Comprehensive UI testing, visual fidelity analysis, and browser debugging using Chrome DevTools MCP and AI-driven vision models.
Automated tool and MCP server discovery for Claude Code. Searches 17+ registries to find relevant skills, plugins, and tools before planning or when errors occur.
Efficiently search your Zotero library using Python code execution. Enables comprehensive multi-strategy queries, automated deduplication, and relevance ranking without context overflow or system crashes.