Datasheet Parser Agent

{
  "schema_version": 1,
  "type": "skill",
  "slug": "ds-parser-agent",
  "title": "Datasheet Parser Agent",
  "brief": "Parses manufacturer PDF datasheets into structured wiki markdown via the ds-extract service, using Claude vision only on ambiguous bbox crops.",
  "version": "1.0.0",
  "tags": [],
  "license": "MIT",
  "discovery_triggers": [
    "datasheet",
    "parse datasheet",
    "ds-extract",
    "datasheet agent"
  ],
  "discovery_pitch": "A subagent that parses manufacturer PDF datasheets into structured wiki pages using the ds-extract service.",
  "sample_prompts": [
    {
      "prompt": "Parse the LM358 datasheet",
      "label": "Parse a datasheet"
    },
    {
      "prompt": "Deploy the datasheet-parser agent to my container",
      "label": "Deploy agent"
    },
    {
      "prompt": "Process datasheets from the queue using this agent",
      "label": "Batch parse"
    }
  ],
  "source_path": "SKILL.md",
  "readme": "A Claude Code subagent that parses manufacturer PDF datasheets into structured wiki markdown. Delegates heavy extraction to the ds-extract service (docling + pdfplumber + PyMuPDF) and only uses Claude vision on the ~40 bbox crops the service couldn't resolve autonomously.\n\n## What it does\n\n1. Acquires the PDF (URL, local path, or queue item)\n2. Sends it to ds-extract for deterministic block extraction\n3. Processes the escalation queue (vision on ambiguous crops)\n4. Assembles structured wiki markdown from merged blocks\n5. Publishes to the Adom Wiki with diagrams and screenshots\n\n## When to use\n\nDeploy this agent as a background worker for batch datasheet processing, or invoke it directly when you want to parse a specific IC datasheet into the wiki.\n\n## Requirements\n\n- `adom-wiki` CLI (installed by gallia)\n- `ds-queue` CLI (installed by gallia)\n- Access to ds-extract service\n",
  "author": {
    "id": "695820315b5f1e4db2fcf602",
    "name": "Kyle Bergstedt",
    "email": "[email protected]"
  },
  "visibility": {
    "public": true
  },
  "hero": null,
  "metadata": {},
  "created_at": "2026-05-28T05:30:45.086Z",
  "updated_at": "2026-05-28T05:30:45.086Z",
  "sub_skills": [],
  "parent_app": null
}