Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/biosshot/easyeda-copilotnpx agentmods add skills/biosshot/easyeda-copilot/datasheetsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/biosshot/easyeda-copilot/datasheets)<a href="https://agentmods.dev/skills/biosshot/easyeda-copilot/datasheets"><img src="https://agentmods.dev/badge/skills/biosshot/easyeda-copilot/datasheets/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/biosshot/easyeda-copilot/datasheets"><img src="https://agentmods.dev/badge/skills/biosshot/easyeda-copilot/datasheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01013 |
| Opus 5 | $0.00026 | $0.00507 |
| Sonnet 5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
datasheets scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataSheets
Standalone Node.js >=20.19 scripts; no Python, npm packages, EDA connection or LLM API required. Resolve scripts relative to this SKILL.md. PDF reading and engineering interpretation belong to the calling agent. Optional text navigation uses an existing Poppler pdftotext; missing Poppler never invalidates a successful download.
Workflow
- Identify the question, exact component and package. Reuse a local PDF when already available. Obtain a URL from the caller's component search (for EasyEDA,
component_searchreturnsdatasheet), supplied URL, or manufacturer documentation. Do not repeat a component search whose result is already available. - Run
node scripts/download.mjs "URL" --out ./datasheets/MPN.pdf. It follows HTTP redirects and supported explicit PDF links/refreshes in wrapper pages, rejects obvious non-PDF/incomplete responses, and returns the absolute path, source/final URLs, SHA-256 and optional page suggestions. It does not prove the file belongs to the requested part. Existing different files are never overwritten. No recursive catalogue search or replacement-part selection is performed. - Use the outline if available.
contents_pageidentifies a page containing a textual table of contents;suggested_pageis a keyword heuristic.pdfPageis 1-based; numbers printed inside contents lines are document labels and may have an offset. Check them against actual pages. No outline is normal for a short datasheet. A failed or unavailable helper means use the environment's PDF reader, not that the PDF is unusable. - Read the relevant PDF pages with the environment's native PDF, browser or rendering tools. Inspect diagrams, pin tables, multi-column tables and curves visually when extracted text loses their associations. Search more widely if a required fact is missing; suggested pages are not exhaustive. The scripts do not render images or run OCR. A scanned PDF may still be readable visually.
- Confirm the manufacturer, family member and package before using pin numbers. Distinguish absolute maximum ratings, recommended operation and typical performance; retain test conditions. A full ordering suffix may be documented separately. Do not infer a package from a family cover alone. Unknown is not zero or false, and a typical application is not a universal requirement.
- During schematic creation/review, automatically preserve the useful facts actually read in
MPN.notes.mdbeside the PDF, following reading and notes. Record pinout, electrical limits, thermal data and caveats only as relevant to the task, with PDF pages and source hash. A one-off answer need not produce a full component extraction. Reuse matching notes, inspect their scope, and recheck claims when the PDF or package changes. Notes are written by the agent, not inferred by the downloader. - Compare facts with actual schematic connections or layout only when those are available. Report the conclusion, PDF/page evidence and unresolved questions. Successful download or text extraction is not electrical validation. Do not describe unread sections as checked.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 30 lines · 52 tokens per session scan A fa0318a94a93
datasheets is a skill published in the GitHub repository biosshot/easyeda-copilot (141 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,013 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
pdf-analysis
A PDF analysis method for reading both normal PDFs with selectable text and scanned PDFs made from page images.
sn-da-non-spreadsheet-analysis
A skill for extracting and analysing content from Word files, PDFs, and PowerPoint presentations. It can work with text, tables, numbers, charts, formatting, and information across multiple documents.
ocr-and-documents
Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
datasheets
Extract structured specifications from electronic component datasheet PDFs — pinouts, electrical characteristics, peripherals, topology, and features. Cache extractions per project for consumption by schematic and PCB analyzers. Primary consumer infrastructure for kicad, emc, spice, and thermal analyzers. Use this…