pdf-extract

Name: pdf-extract
Author: ayazelrico

Extract tables from PDFs and convert to CSV

by ayazelrico(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from ayazelrico/Milyonus-Agent-5.5 (src/milyonus/_bundled_skills/pdf-extract/SKILL.md). Install upstream with npx skills add ayazelrico/Milyonus-Agent-5.5 --skill pdf-extract. Copyright stays with the author.

PDF Table Extraction

To extract tables from PDFs:

Get raw text with pdftotext -layout input.pdf -.
Split table regions by column alignment.
Write the result as CSV. For complex tables, suggest the camelot-py or tabula-py libraries.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

ayazelrico-milyonus-agent-5-5-pdf-extract.ocm.jsonjson

{
  "ocm": "1",
  "id": "ayazelrico-milyonus-agent-5-5-pdf-extract",
  "kind": "skill",
  "name": "pdf-extract",
  "description": "Extract tables from PDFs and convert to CSV",
  "publisher": "ayazelrico",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "data_analysis"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Extract tables from PDFs and convert to CSV"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/ayazelrico/Milyonus-Agent-5.5",
      "path": "src/milyonus/_bundled_skills/pdf-extract/SKILL.md",
      "ref": "8e890c02f0025dbca7a3774e6c9f8e633f8319cc",
      "url": "https://github.com/ayazelrico/Milyonus-Agent-5.5/blob/8e890c02f0025dbca7a3774e6c9f8e633f8319cc/src/milyonus/_bundled_skills/pdf-extract/SKILL.md",
      "key": "ayazelrico/Milyonus-Agent-5.5/src/milyonus/_bundled_skills/pdf-extract/SKILL.md"
    }
  },
  "instructions": "# PDF Table Extraction\nTo extract tables from PDFs:\n1. Get raw text with `pdftotext -layout input.pdf -`.\n2. Split table regions by column alignment.\n3. Write the result as CSV.\nFor complex tables, suggest the `camelot-py` or `tabula-py` libraries.",
  "cost": {
    "context_tokens": 62
  }
}

Fetch it by URL: GET /api/v1/registry/ayazelrico-milyonus-agent-5-5-pdf-extract/manifest?version=1.0.0

About

PDF Table Extraction

Use it

Manifest

Reviews