Sırdaş

Sırdaş: local document skills for agents

Le enseña a un agente cuándo y cómo usar Sırdaş.

Empieza aquí

https://sirdas.app/skills/sirdas-documents/SKILL.md

Para tu agente de IA

Pega esto en Claude, ChatGPT o Cursor y el agente se instala y se configura solo, leyendo la versión en Markdown de esta página.

Ver Markdown (para agentes)

La documentación técnica está en inglés, que es lo que leen las herramientas y los agentes.

Every operation runs on the user's machine. No file, text or field leaves it, so it is safe for health, legal and financial documents.

Setup (once)

Claude Code: claude mcp add sirdas -- npx -y @sirdaspdf/mcp Other MCP clients: {"mcpServers": {"sirdas": {"command": "npx", "args": ["-y", "@sirdaspdf/mcp"]}}} Without MCP: npx sirdas <file.pdf> (add --json for machine output).

Files must live inside the allowed root (default: the directory the server starts in; change it with SIRDAS_ROOT).

The default workflow

  1. Always start with read_document. One call unlocks restricted PDFs, runs OCR on scans, identifies the type, extracts key fields with page citations, anonymizes personal data, finds tables and returns cited chunks plus next_steps.
  2. Tell the user what it is, in one line: type, pages, the 3–5 most useful fields (cite the page).
  3. Offer the next_steps proactively, as a short choice — don't run write operations without a yes.
  4. If status is needs_password or wrong_password, ask the user and call again with password. Never guess or brute-force.

Choosing the next tool

The user wants…Tool
Ask an AI about a sensitive documentprompt private_ai_answer (anonymize → answer → deanonymize_text)
Index for search / RAGpdf_to_chunks (use id as vector id; store pages, section) or prompt index_pdf_for_rag
Invoice lines or statement movements in Excelpdf_tables
Just the fields from text you already haveextract_fields
What changed between two versionscompare_pdfs
Password on / offprotect_pdf / unlock_pdf
Remove, keep or rotate pagesedit_pages
«Página X de Y», CONFIDENCIAL stampadd_page_numbers, add_watermark
Join / split / shrinkmerge_pdfs, split_pdf, compress_pdf_lossless
Training data from many PDFspdf_to_dataset, find_duplicates, check_contamination

Honesty rules

  • Type detection and field extraction are rule-based: say "looks like an invoice" and show the evidence when confidence is below 0.6.
  • Anonymization can miss unusual formats: suggest a quick review before sharing outside.
  • A watermark or copy restriction is not real protection; a password (AES-256) is.