Agent skill

create-table-classifier

Train vision models to predict optimal Camelot extraction strategies for PDF tables.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill create-table-classifier --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/ai-ml/create-table-classifier/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

--- name: create-table-classifier description: > Train vision classifiers for Camelot table extraction strategy prediction. Uses MobileNetV2 with GRPO training and Camelot execution feedback. Integrates with Federated Taxonomy for preset-aware predictions. allowed-tools: Bash, Read triggers: - train table classifier - table strategy training - camelot strategy model - extraction strategy training - s05 strategy predictor metadata: short-description: GRPO training for table extraction strategy prediction provides: - create-table-classifier composes: [, task-monitor] --- # Create Table Classifier Train vision models to predict optimal Camelot extraction strategies for PDF tables. Uses GRPO with execution feedback from actual Camelot extractions. ## Training Approaches | Approach | Description | Use When | |----------|-------------|----------| | **GRPO (Recommended)** | RL with Camelot execution feedback | Production training | | **SFT Only** | Supervised fine-tuning | Quick baseline | | **Collect Only** | Data collection from corpus | Building dataset | ## Quick Start (GRPO with Execution Feedback) ```bash cd .pi/skills/create-table-classifier # 1. Setup environment cp .env.example .

What's inside
Steps it walks through
  1. Training Approaches
  2. Quick Start (GRPO with Execution Feedback)
  3. GRPO Training Pipeline
  4. Reward Functions
  5. Federated Taxonomy Integration
  6. Evaluation Thresholds
  7. Architecture
  8. Training Data Format
  9. Commands
  10. Data Collection
  11. GRPO Training
  12. Utilities
  13. S05 Integration
  14. GPU Requirements
Ships with 1 file
  • metadata.json
Commands it runs
cd .pi/skills/create-table-classifier
cp .env.example .env
Edit .env with paths to corpus and extractor
View training progress
TensorBoard
Run full self-improvement cycle
More from claude-skill-registry
All skills →
About this skill
What does the create-table-classifier skill do?

Train vision models to predict optimal Camelot extraction strategies for PDF tables.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill create-table-classifier --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going