数据表

数据 社区

技能解读

当前原文的自动摘译,尚未人工审校。

目的

从组件数据表 PDF 中提取结构化、机器可读的规格,并将其提供给分析人员。适用于在 <project>/datasheets/ 下下载的任何 PDF(下载由经销商技能拥有,如 digikey、mouser、lcsc、element14)。

适用范围

该技能拥有: 提取模式 — 每个 MPN 规范的规范 JSON 结构。通过 EXTRACTION_VERSION 中的 scripts/datasheet_extract_cache.py 版本。 PDF 页面选择 — 启发式选择最有可能包含引脚排列、电子字符、应用程序、SPICE 模型的页面。质量评分 — 加权评分标准(引脚覆盖范围、额定电压、应用信息、电气特性、SPICE 规格)。消费者 API — scripts/datasheet_features.py 中的帮助程序,用于查询特定字段的其他技能(例如,get_regulator_features(mpn)、get_mcu_features(mpn))。

非目标

没有 PDF 下载。这是由经销商技能拥有的(digikey,mouser,lcsc,element14)。没有全局库。每个项目的提取都存在于<project>/datasheets/extracted/中。没有共享的跨项目缓存。

参考指南

references/extraction-schema.md — 规范模式,定义的每个字段 references/field-extraction-guide.md — 如何在常见供应商(TI、ST、NXP、Espressif、Microchip)的数据表中查找每个字段 references/quality-scoring.md — 标题详细信息、分数阈值 references/consumer-api.md — kicad/emc/spice/Thermal 如何消耗提取

入口点脚本

scripts/datasheet_extract_cache.py — 缓存管理器、解析器、索引器 scripts/datasheet_page_selector.py — 页面选择启发式 scripts/datasheet_score.py — 提取质量评分 scripts/datasheet_verify.py — 交叉检查提取与原理图使用 scripts/datasheet_features.py — 消费者助手 API(v1.3 中的新增功能)

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
数据
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@aklofas · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Datasheets Skill

## Purpose

Extract structured, machine-readable specifications from component datasheet PDFs and make them available to analyzer skills. Works on whatever PDFs are downloaded under `<project>/datasheets/` (downloads are owned by distributor skills like `digikey`, `mouser`, `lcsc`, `element14`).

## Scope

This skill owns:
- **Extraction schema** — the canonical JSON structure for per-MPN specs. Versioned via `EXTRACTION_VERSION` in `scripts/datasheet_extract_cache.py`.
- **PDF page selection** — heuristics to pick pages most likely to contain pinouts, e-chars, applications, SPICE models.
- **Quality scoring** — weighted rubric (pin coverage, voltage ratings, application info, electrical chars, SPICE specs).
- **Consumer API** — helpers in `scripts/datasheet_features.py` for other skills to query specific fields (e.g., `get_regulator_features(mpn)`, `get_mcu_features(mpn)`).
- **Verification** — consistency checks between extracted data and schematic/PCB usage.

## Non-goals

- **No PDF downloading.** That is owned by distributor skills (`digikey`, `mouser`, `lcsc`, `element14`).
- **No global library.** Each project's extractions live in `<project>/datasheets/extracted/`. There is no shared cross-project cache.

## Cache location

```
<project>/
  design.kicad_sch
  datasheets/
    TPS61023DRLR.pdf        # downloaded by distributor skills
    extracted/
      manifest.json         # extraction manifest (legacy name: index.json)
      TPS61023DRLR.json     # structured extraction (this skill's output)
```

## Reference guides

- `references/extraction-schema.md` — canonical schema, every field defined
- `references/field-extraction-guide.md` — how to find each field in datasheets from common vendors (TI, ST, NXP, Espressif, Microchip)
- `references/quality-scoring.md` — rubric details, score thresholds
- `references/consumer-api.md` — how kicad/emc/spice/thermal consume extractions

## Entry-point scripts

- `scripts/datasheet_extract_cache.py` — cache manager, resolver, indexer
- `scripts/datasheet_page_selector.py` — page selection heuristics
- `scripts/datasheet_score.py` — extraction quality scoring
- `scripts/datasheet_verify.py` — cross-check extraction vs schematic usage
- `scripts/datasheet_features.py` — consumer helper API (new in v1.3)

## Extraction workflow

1. User runs an analyzer or requests extraction.
2. This skill checks the cache (`<project>/datasheets/extracted/<MPN>.json`).
3. On cache miss / stale / low score: Claude reads selected PDF pages and extracts structured data.
4. Extraction is scored; if score ≥ 6.0, cached.
5. Consumers query via `datasheet_features.py`.

## When to trigger this skill

- **Immediately after downloading datasheets** via `sync_datasheets_digikey.py`, `sync_datasheets_lcsc.py`, or equivalent. Without extraction, IC-aware checks (VM-001 rail voltage, PS-001 power-good, PR-004 USB, DP-002 USB speed classification) fall back to heuristics on unknown ICs.
- **Before running analyzers on a new project** where datasheets are present but `datasheets/extracted/` is empty — the analyzers won't produce the extractions themselves.
- **When a review flags low trust level** due to missing manufacturer evidence: extracting the ICs referenced by power regulators, MCUs, and high-speed peripherals typically flips `trust_level: low` → `mixed` or `high`.
- **When a user asks for pin verification** ("verify U1 pin names match datasheet") — this skill's cached extraction is the authoritative source.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。