Scientific Classification
- 16 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
scientific-classification is a Claude skill that classifies scientific objects and detects patterns using established taxonomies and confidence-scored classifiers.
About
This skill classifies scientific objects and detects patterns across astronomy, biology, and social sciences using established taxonomies. A developer uses it to map data to standard classification schemes, apply a classifier with confidence scores, and validate against labeled examples. It flags ambiguous or borderline cases and reports alternative labels.
- Five-step protocol from feature extraction to edge-case analysis
- Covers astronomy, biology, chemistry, text and image classification domains
- References SDSS stellar (100K objects) and Allen AI Social Bias Frames datasets
Scientific Classification by the numbers
- 16 all-time installs (skills.sh)
- Ranked #1,318 of 2,065 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
scientific-classification capabilities & compatibility
- Capabilities
- data analysis
- Use cases
- data analysis · research
- Pricing
- Free
What scientific-classification says it does
Classify scientific objects and detect patterns using established taxonomies and classification schemes.
Report classification confidence and alternative labels
Cross-validate against known labeled examples
npx skills add https://github.com/beita6969/scienceclaw --skill scientific-classificationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 16 |
|---|---|
| repo stars | ★ 869 |
| Last updated | June 8, 2026 |
| Repository | beita6969/scienceclaw ↗ |
What it does
Classify scientific objects such as stellar types or galaxy morphology using standard taxonomies and confidence scores.
Who is it for?
Mapping scientific data to standard taxonomies and applying classifiers with confidence scores.
Skip if: Generating new content or making predictive forecasts (those are separate scienceclaw skills).
When should I use this skill?
Classifying astronomical objects, biological taxa, chemical compounds, or text for sentiment and bias.
What you get
Confidence-scored classifications mapped to domain-standard taxonomies with alternative labels and flagged edge cases.
- confidence-scored classifications
- alternative labels
- flagged edge cases
By the numbers
- five-step classification protocol
- 100K-object SDSS stellar dataset referenced
Files
Scientific Classification & Detection
Purpose
Classify scientific objects and detect patterns using established taxonomies and classification schemes.
Key Datasets
- SDSS Stellar Classification (Allanatrix/Astro): 100K objects from SDSS DR17 — Stars, Galaxies, Quasars with photometric features (u, g, r, i, z magnitudes, redshift)
- Social Bias Frames (allenai/social_bias_frames): Allen AI SBIC corpus for detecting implicit social biases in text
Protocol
1. Feature extraction — Identify relevant features for classification task 2. Taxonomy mapping — Map to standard classification scheme 3. Classification — Apply appropriate classifier with confidence scores 4. Validation — Cross-validate against known labeled examples 5. Edge case analysis — Flag ambiguous or borderline cases
Classification Domains
- Astronomical objects: Stellar spectral types (OBAFGKM), galaxy morphology (Hubble), AGN types
- Biological taxonomy: Species classification, protein families, cell types
- Chemical compounds: Functional groups, drug classes, toxicity levels
- Text classification: Sentiment, bias detection, topic classification
- Image classification: Histopathology, satellite imagery, microscopy
Rules
- Report classification confidence and alternative labels
- Use domain-standard taxonomies (not ad-hoc categories)
- Handle multi-label and hierarchical classification
- Document decision boundaries and feature importance
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511FAQ
Which domains does it cover?
Astronomical objects, biological taxonomy, chemical compounds, text classification, and image classification.
Does it report uncertainty?
Yes. It reports classification confidence and alternative labels, and flags ambiguous or borderline cases.