doc-extraction-1-constants-0-yield-not-yet-implemented
Sub-skill of doc-extraction: 1. `constants` (0% yield — not yet implemented) (+7).
Best use case
doc-extraction-1-constants-0-yield-not-yet-implemented is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of doc-extraction: 1. `constants` (0% yield — not yet implemented) (+7).
Teams using doc-extraction-1-constants-0-yield-not-yet-implemented 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/1-constants-0-yield-not-yet-implemented/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How doc-extraction-1-constants-0-yield-not-yet-implemented Compares
| Feature / Agent | doc-extraction-1-constants-0-yield-not-yet-implemented | 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: 1. `constants` (0% yield — not yet implemented) (+7).
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
# 1. `constants` (0% yield — not yet implemented) (+7)
## 1. `constants` (0% yield — not yet implemented)
Named values with units that remain fixed within a standard or design context.
**Detection heuristics**: Named value with "=" sign, units in parentheses or
brackets, appears in tables or definition lists, often prefixed with a symbol
(Greek or Latin letter).
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `name` | Human-readable name |
| `symbol` | Mathematical symbol (e.g. `f_ci`, `ρ`) |
| `value` | Numeric value |
| `units` | SI or field units |
| `source_standard` | Standard reference (e.g. DNV-RP-B401 Sec 3.4) |
## 2. `equations` (0% yield — not yet implemented)
Mathematical relationships between variables.
**Detection heuristics**: Contains mathematical notation, Greek letters, operator
symbols (=, ×, /, ^), variable definitions follow the expression, often numbered
(Eq. 1, Equation 3.2).
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `name` | Equation name or number |
| `expression` | Mathematical expression (LaTeX or plain text) |
| `variables` | List of {symbol, name, units} |
| `source` | Standard and section reference |
| `applicability` | Conditions where equation applies |
## 3. `tables`
Tabular data — lookup values, design parameters, or comparison matrices.
**Detection heuristics**: Grid or tabular layout, header row with column labels,
numeric cells with units, often titled "Table N" or has a caption.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `title` | Table caption or identifier |
| `columns` | List of column headers with units |
| `rows` | Data rows as lists or dicts |
| `interpolation_method` | Linear, step, or none |
| `source` | Standard and table number |
## 4. `curves`
Graphical data — x-y relationships presented as figures.
**Detection heuristics**: Figure references ("Figure N", "Fig."), x-y axis labels,
data series legends, often accompanied by a caption describing the relationship.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `title` | Figure caption |
| `x_axis` | {label, units, range} |
| `y_axis` | {label, units, range} |
| `data_points` | Digitized x-y pairs |
| `source` | Standard and figure number |
## 5. `procedures` (0% yield — not yet implemented)
Sequential steps for performing an operation or assessment.
**Detection heuristics**: Numbered or lettered steps with sequential dependencies,
prerequisites section, action-oriented language. The distinguishing feature vs
`requirements` is sequential execution order — procedures describe *how* to do
something step-by-step, requirements state *what* must be true.
**Disambiguation rule**: If a clause contains both normative language ("shall")
and sequential steps, classify as `procedures` when the steps have execution
order, or `requirements` when each statement stands independently. Multi-label
output is allowed when both types genuinely co-exist in the same passage.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `title` | Procedure name |
| `steps` | Ordered list of step descriptions |
| `prerequisites` | Required inputs or conditions |
| `standard_ref` | Source standard and section |
| `decision_points` | Steps with branching logic |
## 6. `requirements`
Normative statements that define mandatory or recommended practice.
**Detection heuristics**: Contains "shall", "required", "must", "is to be";
often numbered with a requirement ID; may reference verification methods.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `id` | Requirement identifier |
| `text` | Full requirement statement |
| `standard_ref` | Source standard and clause |
| `verification_method` | How compliance is verified |
| `normative_strength` | shall / should / may |
## 7. `definitions`
Terms and their meanings as used within a standard or domain.
**Detection heuristics**: "means", "is defined as", "refers to"; glossary or
definitions section; term followed by colon or em-dash and explanation.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `term` | The defined term |
| `definition` | Full definition text |
| `source` | Standard and section |
| `synonyms` | Alternative terms |
| `domain` | Engineering sub-domain |
## 8. `worked_examples` (0% yield — not yet implemented)
Step-by-step calculations demonstrating application of equations or procedures.
**Detection heuristics**: "Example", "Sample calculation"; given/find/solution
pattern; specific numeric values substituted into equations; final answer with
units.
**Key extraction fields**:
| Field | Description |
|-------|-------------|
| `title` | Example identifier or description |
| `given` | Input parameters {name, value, units} |
| `solution_steps` | Ordered calculation steps |
| `answer` | Final result {name, value, units} |
| `source` | Standard and section/appendix |Related 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
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.
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).
doc-extraction-yield-reality-wrk-1246-corpus-assessment
Sub-skill of doc-extraction: Yield Reality (WRK-1246 Corpus Assessment).
doc-extraction-unit-detection-and-normalization
Sub-skill of doc-extraction: Unit Detection and Normalization (+4).
doc-extraction-output-schema
Sub-skill of doc-extraction: Output Schema.