doc-extraction-unit-detection-and-normalization
Sub-skill of doc-extraction: Unit Detection and Normalization (+4).
Best use case
doc-extraction-unit-detection-and-normalization is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of doc-extraction: Unit Detection and Normalization (+4).
Teams using doc-extraction-unit-detection-and-normalization should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/unit-detection-and-normalization/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How doc-extraction-unit-detection-and-normalization Compares
| Feature / Agent | doc-extraction-unit-detection-and-normalization | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of doc-extraction: Unit Detection and Normalization (+4).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Unit Detection and Normalization (+4)
## Unit Detection and Normalization
Recognize units in parentheses, brackets, or inline: `(m/s²)`, `[ksi]`,
`N/mm²`. Normalize to a canonical form:
| Input variants | Canonical |
|---------------|-----------|
| `ksi`, `KSI` | `ksi` |
| `N/mm²`, `MPa` | `MPa` |
| `mA/m²`, `mA/m2` | `mA/m²` |
| `°C`, `deg C` | `°C` |
| `lb/ft`, `lbs/ft` | `lb/ft` |
Flag SI vs imperial vs field units. Prefer SI in output; keep original as
`units_original`.
## Standards Reference Parsing
Parse references like `DNV-RP-B401 Section 3.4.6` into structured form:
```yaml
standard_ref:
body: DNV
document: RP-B401
edition: null # null unless explicitly stated in source text
edition_inferred: 2021 # set only when edition can be inferred; null otherwise
section: 3.4.6
table: null
figure: null
raw: "DNV-RP-B401 Section 3.4.6"
```
**Inference rule**: `edition` must be null unless the source text explicitly
states the year. Use `edition_inferred` only when surrounding context (title
page, header, or adjacent reference) provides strong evidence; never guess.
Common patterns:
- `DNV-RP-XXXX Sec N.N.N` / `Section N.N` / `Table N-N` / `Figure N-N`
- `API RP NNX Section N` / `API 579-1 Part N`
- `ASME BPVC Section VIII Div 2`
- `ISO NNNNN-N:YYYY Clause N.N`
## Safety and Design Factor Identification
Flag values tagged as safety factors, design factors, or usage factors:
- Keywords: "safety factor", "design factor", "utilisation factor", "usage factor"
- Often dimensionless ratios between 0 and 10
- Extract: {name, value, standard_ref, applicability}
## Material Property Recognition
Detect material properties in text or tables:
- Yield strength (SMYS), tensile strength (SMTS), Young's modulus
- Density, thermal expansion coefficient, Poisson's ratio
- Fatigue S-N curve parameters
- Extract: {property, value, units, material_grade, temperature, standard_ref}
## Condition and Applicability Tagging
Many values have applicability constraints. Tag extracted items with:
- Temperature range
- Depth/pressure range
- Material grade or category
- Environmental condition (seawater, air, buried)
- Service life assumptionsRelated Skills
llm-wiki-source-extraction-coverage
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a reviewer can re-verify or revise against the actual document, (4) deciding whether OCR fallback or manual transcription is needed. Codifies workspace-hub's existing OCR fallback chain and python-docx / openpyxl / trafilatura patterns into a format-specific routing table. Companion to research/llm-wiki-page-shape-contract (Rule 7 input-layer pages) and research/llm-wiki — this skill is the defense against silent extraction failure.
portable-baseline-pattern-extraction
Extract and separate portable baseline config from machine-specific overrides in multi-environment projects
multi-format-csv-detection-and-deduplication
Detect and handle multiple CSV format versions from the same data source; deduplicate records across format variants
units
Unit-safe engineering calculations with provenance tracking, dimensional consistency verification, and unit conversion across SI, inch, and metric systems.
doc-extraction-naval-architecture
Layer 3 domain sub-skill for extracting naval architecture data from SNAME PNA, IMO stability codes, IACS structural rules, and classification society guidelines. Provides detection heuristics for stability constants, resistance equations, hull form coefficients, hydrostatic curves, IMO stability criteria, and structural scantling tables. type: reference
doc-extraction-drilling-riser
Layer 3 domain sub-skill for extracting drilling riser data from API RP 16Q, DNV-RP-C205, and riser analysis reports. Provides detection heuristics for VIV parameters, kill/choke line specs, and BOP stack configurations. type: reference
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
gmail-email-to-repo-extraction
Extract structured data from Gmail inbox emails, enrich with domain-specific classification, legal-scan against deny list, commit to appropriate repo, then optionally delete originals.
gmail-data-extraction
Extract structured data from Gmail emails using REST API (no pip dependencies). Covers inbox scanning, subject line regex extraction, email text parsing, thread-aware drafting, and legal-scan-before-commit workflow.
clean-code-god-object-detection
Sub-skill of clean-code: God Object Detection.
orcawave-analysis-orcfxapi-result-extraction
Sub-skill of orcawave-analysis: OrcFxAPI Result Extraction (+3).
orcaflex-extreme-analysis-basic-extreme-extraction
Sub-skill of orcaflex-extreme-analysis: Basic Extreme Extraction (+1).