Agent skill

doc-extraction

Classify and extract structured content from engineering documents using a 3-layer taxonomy: generic content types, engineering patterns, and domain sub-skills. Use when ingesting standards, reports, or technical manuals into structured data for downstream analysis. type: reference

Stars 4
Forks 4

Install this agent skill to your Project

npx add-skill https://github.com/vamseeachanta/workspace-hub/tree/main/.claude/skills/engineering/doc-extraction

SKILL.md

Doc Extraction

When to Use

  • Ingesting a new standard or code (DNV-RP, API RP, ISO, ASME)
  • Extracting constants, equations, or tables from technical reports
  • Building structured datasets from engineering manuals
  • Populating knowledge bases from document collections
  • Pre-processing documents before analysis workflow

Related Skills

  • document-index-pipeline — 7-phase A→G pipeline
  • doc-intelligence-promotion — Deep extraction post-processing
  • cathodic-protection — CP system design
  • viv-analysis — VIV assessment for risers
  • fitness-for-service — FFS assessment
  • structural-analysis — Structural checks

References

  • DNV-RP-B401: Cathodic Protection Design
  • DNV-RP-C205: Environmental Conditions and Environmental Loads
  • API 579-1/ASME FFS-1: Fitness-for-Service
  • API RP 16Q: Design, Selection, Operation, and Maintenance of Marine Drilling Riser Systems

Sub-Skills

  • Yield Reality (WRK-1246 Corpus Assessment)
  • Architecture
  • 1. constants (0% yield — not yet implemented) (+7)
  • Unit Detection and Normalization (+4)
  • Extraction Workflow
  • Output Schema
  • Domain Sub-Skills
  • Hybrid Classification Strategy (WRK-1188 Learning)

Expand your agent's capabilities with these related and highly-rated skills.

Didn't find tool you were looking for?

Be as detailed as possible for better results