Knowledge Discovery
- 16 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
knowledge-discovery is a Claude skill that discovers patterns, builds knowledge graphs, and extracts insights from linguistic and historical data.
About
knowledge-discovery is a Claude skill for finding hidden patterns, building knowledge graphs, and extracting insights from structured and unstructured data. A researcher uses it to profile data, detect patterns via clustering and anomaly detection, construct entity-relation graphs, and validate discoveries against known phenomena. It matters because it follows a defined protocol and insists on distinguishing correlation from causation and reporting statistical significance.
- Discovers patterns, builds knowledge graphs, and extracts insights from linguistic and historical data
- 6-step protocol from data exploration through pattern detection to knowledge-graph construction
- References WALS and HistWords datasets for linguistic typology and semantic change
Knowledge Discovery 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)
knowledge-discovery capabilities & compatibility
Free; a prompt/protocol skill with no external dependencies or keys.
- Capabilities
- pattern detection · knowledge graph construction · insight generation
- Use cases
- data analysis · research
- Pricing
- Free
What knowledge-discovery says it does
Discover patterns, build knowledge graphs, and extract insights from linguistic and historical data
WALS** (wals.info): World Atlas of Language Structures — 192 linguistic features across 2,679 languages in CLDF format (CC-BY 4.0)
Distinguish between correlation and causation in discovered patterns
npx skills add https://github.com/beita6969/scienceclaw --skill knowledge-discoveryAdd 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
Discover patterns, build knowledge graphs, and extract insights from linguistic and historical datasets.
Who is it for?
Exploratory pattern detection and knowledge-graph construction over linguistic, historical, or scientific data.
Skip if: Confirmatory analysis without exploration; the protocol is built around discovery and validation.
When should I use this skill?
The user needs to discover hidden patterns, build a knowledge graph, or extract novel insights from data.
What you get
Validated patterns, entity-relation knowledge graphs, and domain-contextual insights.
- Detected patterns with significance and effect sizes
- An entity-relation knowledge graph
- Domain-contextual insights
By the numbers
- 6-step discovery protocol
- WALS covers 192 linguistic features across 2,679 languages
- 4 discovery types (linguistic, semantic, scientific, biomedical)
Files
Knowledge Discovery & Graphs
Purpose
Discover hidden patterns, build knowledge graphs, and extract novel insights from structured and unstructured data.
Key Datasets
- WALS (wals.info): World Atlas of Language Structures — 192 linguistic features across 2,679 languages in CLDF format (CC-BY 4.0)
- HistWords (nlp.stanford.edu/projects/histwords): Historical word embeddings tracking semantic change across 4 languages over centuries (.npy/.pkl format)
Protocol
1. Data exploration — Profile data, identify patterns, check distributions 2. Feature engineering — Create derived features, temporal features, cross-references 3. Pattern detection — Apply clustering, association rules, anomaly detection 4. Knowledge graph construction — Build entity-relation graphs from discovered patterns 5. Insight generation — Interpret patterns in domain context 6. Validation — Verify discoveries against known phenomena
Discovery Types
- Linguistic typology: Cross-linguistic universals, language family features, areal patterns
- Semantic change: Word meaning evolution, neologism tracking, conceptual drift
- Scientific trends: Emerging research topics, citation patterns, collaboration networks
- Biomedical discovery: Drug repurposing candidates, gene-disease associations
Rules
- Distinguish between correlation and causation in discovered patterns
- Report statistical significance and effect sizes
- Validate against domain expertise and existing literature
- Handle missing data transparently
- For knowledge graphs, use standard ontologies (RDF, OWL) when possible
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 datasets does this skill reference?
WALS (World Atlas of Language Structures) with 192 features across 2,679 languages, and HistWords, historical word embeddings tracking semantic change across 4 languages.
How does it handle causation claims?
The rules require distinguishing correlation from causation, reporting statistical significance and effect sizes, and validating against domain expertise and existing literature.