run-llama/llamaparse-agent-skills
2 skills3.9k installs148 starsGitHub
Install
npx skills add https://github.com/run-llama/llamaparse-agent-skillsSkills in this repo
1LiteparseEffective LiteParse teaches agents to extract document text locally with the lit CLI from LlamaIndex without model calls. The golden rule is parse once to a temp file with lit parse, then search that file with grep, sed, or the bundled BM25 search.py helper instead of re-parsing per query. Born-digital PDFs should use --no-ocr for speed; scanned PDFs drop --no-ocr and may need page screenshots at modest 150-200 DPI as a last resort. Search discipline batches independent lookups in one command, uses grep -C for inline context, bounds output with head, and switches to search.py after two failed greps. The skill documents real trace waste where agents re-parsed the same PDF up to nine times and single screenshots cost 140k+ characters. Setup requires Node 18+, npm i -g @llamaindex/liteparse, LibreOffice for Office files, and ImageMagick for images. Core flags include --format text or json, --no-ocr, --target-pages, and --dpi. Use when a task involves document files and you need text, tables, or specific values to answer questions or extract data cheaply.3.1kinstalls2Llamaparsellamaparse is a run-llama/llamaparse-agent-skills skill at version 1.0.0 under the MIT license from LlamaIndex for parsing unstructured documents with the LlamaParse API. It requires LLAMA_CLOUD_API_KEY in the environment and the @llamaindex/llama-cloud@latest TypeScript library. Supported formats include PDF, DOCX, PPTX, and XLSX with outputs such as text, markdown, and images. Developers invoke llamaparse when agents must ingest contracts, decks, or spreadsheets without manual copy-paste. The skill confirms API key and dependency setup before parsing and fits RAG ingestion, document QA, and automation pipelines that need reliable structure from messy files.806installs