doc-extraction-hybrid-classification-strategy-wrk-1188-learning

Sub-skill of doc-extraction: Hybrid Classification Strategy (WRK-1188 Learning).

5 stars

Best use case

doc-extraction-hybrid-classification-strategy-wrk-1188-learning is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Sub-skill of doc-extraction: Hybrid Classification Strategy (WRK-1188 Learning).

Teams using doc-extraction-hybrid-classification-strategy-wrk-1188-learning 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

$curl -o ~/.claude/skills/hybrid-classification-strategy-wrk-1188-learning/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_archive/engineering/doc-extraction/hybrid-classification-strategy-wrk-1188-learning/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/hybrid-classification-strategy-wrk-1188-learning/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How doc-extraction-hybrid-classification-strategy-wrk-1188-learning Compares

Feature / Agentdoc-extraction-hybrid-classification-strategy-wrk-1188-learningStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Sub-skill of doc-extraction: Hybrid Classification Strategy (WRK-1188 Learning).

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

# Hybrid Classification Strategy (WRK-1188 Learning)

## Hybrid Classification Strategy (WRK-1188 Learning)


For large homogeneous collections, prefer deterministic classifiers over LLM:

| Collection | Strategy | Cost | Accuracy |
|-----------|----------|------|----------|
| ASTM (25,537 docs) | Designation prefix → discipline | $0 | 86% vs LLM |
| API/DNV/ISO (1,062) | LLM (Codex Haiku CLI) | ~$2 | Baseline |
| Unknown org (484) | LLM (Codex Haiku CLI) | ~$1 | Baseline |

**Rule**: If org has predictable title/designation patterns, write a deterministic
classifier first. Validate with 100-doc LLM sample. Accept if >85%.

See `data/document-index-pipeline` skill for full pipeline orchestration.

Related Skills

llm-wiki-source-extraction-coverage

5
from vamseeachanta/workspace-hub

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

5
from vamseeachanta/workspace-hub

Extract and separate portable baseline config from machine-specific overrides in multi-environment projects

boundary-policy-classification-by-role

5
from vamseeachanta/workspace-hub

Classify artifacts as durable vs transient by their functional role rather than directory path, using multi-layer architectural validation

provider-audit-bootstrap-and-path-classification

5
from vamseeachanta/workspace-hub

Fix provider-session ecosystem audit failures caused by source-checkout imports and over-aggressive symbolic-path classification.

tax-filing-strategy-and-packets

5
from vamseeachanta/workspace-hub

Class-level tax filing strategy and packet assembly for C-Corp/personal/TaxAct workflows, including R&D strategy and strategic planning.

c-corp-rd-tax-strategy

5
from vamseeachanta/workspace-hub

Tax optimization for C-Corp engineering consulting firms investing in AI/R&D. Covers §174 amortization, §41 R&D credits, loan-to-equity conversion, NOL planning, and AI growth funding models.

extract-learnings-to-issues

5
from vamseeachanta/workspace-hub

Extract unstructured user reflections and learnings, distill core themes, route insights to existing GitHub issues as contextual comments rather than creating duplicates.

doc-extraction-naval-architecture

5
from vamseeachanta/workspace-hub

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

5
from vamseeachanta/workspace-hub

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

5
from vamseeachanta/workspace-hub

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

5
from vamseeachanta/workspace-hub

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

5
from vamseeachanta/workspace-hub

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.