datasheet-reader

A tool for turning datasheets and technical PDF files into readable Markdown text, from a local file or web address. Datasheets are documents that describe the specifications and use of hardware components.

In plain words
What is it for?
Use it to extract information from electronic-component datasheets and other technical PDFs, including documents referenced by KiCad.
Why use it?
It gives you a consistent text version to read and work from instead of handling the raw PDF directly. It also identifies where the converted files are stored.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/diodeinc/pcb/datasheet-reader
Any agent
npx skills add diodeinc/pcb --skill datasheet-reader
Clone the repo
git clone --depth 1 https://github.com/diodeinc/pcb

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00295
Opus 5 $0.00015 $0.00148
Sonnet 5 $0.00006 $0.00059
Haiku 4.5 $0.00003 $0.00030

Measured 2d ago against content hash af263ea7a4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

datasheet-reader 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.

skills/datasheet-reader/SKILL.md · 35 lines

What it actually says

Datasheet Reader

Use this skill when a task depends on a datasheet or technical PDF.

  • Input: local .pdf path or http(s) URL
  • Command: pcb scan <input>
  • Output: stdout reports materialized PDF: and Markdown: paths
  • Next step: read the file at the Markdown: path, not the raw PDF
  • Images are linked from the markdown

Workflow

  1. Run pcb scan /path/to/file.pdf or pcb scan https://....
  2. Capture the path on the Markdown: line.
  3. Read the markdown file and work from that artifact.
  4. Follow image links only if the task depends on figures, diagrams, or tables.

Examples

pcb scan ./TPS54331.pdf
pcb scan https://www.ti.com/lit/gpn/tca9554

Notes

  • Prefer a URL when pcb scan <url> succeeds. Its cached PDF is not a package artifact; do not copy it into the repository by default.
  • Prefer the minimal invocation above. Do not depend on optional flags unless a task explicitly requires them.
  • If pcb scan fails, report the failure briefly and then choose the best fallback.
Changes

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.

  1. 2d ago First seen · 35 lines · 30 tokens per session scan A af263ea7a4a4

Subscribe to this mod's changes

datasheet-reader is a skill published in the GitHub repository diodeinc/pcb (434 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 295 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

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…

aklofas/kicad-happy · 156 tokens

kernelcad-drawings

Export 2D engineering-drawing sheets (SVG) from any model or assembly — third-angle front/top/left + isometric views with hidden-line removal, overall dimensions, and a title block. Use when the deliverable is a human-readable fabrication or review drawing.

w1ne/kernelCAD-web · 60 tokens

datasheet-interpreter

Extracts key specifications from component datasheet PDFs for maker projects. Use when user shares a datasheet PDF URL, asks about component specs, needs pin assignments, I2C addresses, timing requirements, or register maps. Downloads and parses PDF to extract essentials. Complements datasheet-parser for quick lookups.

wedsamuel1230/arduino-skills · 67 tokens

extract-pattern

Extract passive component MPN pattern (resistor, capacitor, inductor) from a datasheet PDF. Returns structured data via the savepattern tool.

Faradworks/Pinscope · 30 tokens

extract-specs

Extract pin table, package info, and electrical specifications from a discrete/simple component datasheet PDF. Returns structured data via the savespecs tool.

Faradworks/Pinscope · 28 tokens

extract-pintable

Extract pin table, package info, and component subtype from an IC datasheet PDF. Returns structured data via the savepintable tool.

Faradworks/Pinscope · 28 tokens