data-engineering
770
deduplication
Event deduplication with canonical selection, reputation scoring, and hash-based grouping for multi-source data aggregation. Handles both ID-based and content-based deduplication.
dadbodgeoff
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
data-engineering
770
fuzzy-matching
Multi-stage fuzzy matching pipeline for entity reconciliation. PostgreSQL trigram pre-filter, salient overlap check, and multi-factor similarity scoring.
dadbodgeoff
data-ai
data-engineering
770
intelligent-cache
Multi-layer caching with type-specific TTLs, get-or-generate pattern, memory and database layers, and graceful invalidation without cache stampede.
dadbodgeoff
data-ai
data-engineering
770
snapshot-aggregation
Daily compression of time-series data with merge logic for multiple pipeline runs, structured aggregation for dashboards, and storage estimation for capacity planning.
dadbodgeoff
data-ai
data-engineering
770
validation-quarantine
Data validation with quality scoring and quarantine for suspicious records. Validates incoming data without blocking the pipeline, enabling manual review of edge cases.
dadbodgeoff
data-ai
data-analysis
760
scientific-figure-making
Covers publication-ready matplotlib figures for academic papers, slides, and reports—bars, trends, scatter, heatmaps, and multi-panel layouts—with this repository’s house style, print/vector export conventions, and parity with figures4papers demos. Use when the user is finalizing or creating such figures in matplotlib. Do not use for interactive dashboards or web viz (Plotly, Altair, Bokeh), exploratory-only plots without a publication target, dominant 3D or geographic mapping, or Illustrator/Figma-first infographic workflows.
ChenLiu-1996
data-ai
data-analysis
759
eqtl-catalogue-skill
Submit compact eQTL Catalogue API requests for association retrieval and documented metadata endpoints. Use when a user wants concise public eQTL Catalogue summaries
openai
data-ai
data-analysis
759
clinicaltrials-skill
Submit compact ClinicalTrials.gov API v2 requests for study search, metadata, enums, search areas, and field statistics. Use when a user wants concise ClinicalTrials.gov summaries
openai
data-ai
data-analysis
759
opentargets-skill
Submit compact Open Targets Platform GraphQL requests for target, disease, drug, variant, study, and search data, including associated-disease datasource heatmap matrices. Use when a user wants concise Open Targets summaries or per-datasource evidence context
openai
data-ai
data-analysis
759
tpmi-phewas-skill
Fetch compact TPMI PheWAS summaries for single variants by accepting rsID, GRCh37, or GRCh38 input and resolving to the required GRCh38 query. Use when a user wants concise TPMI association results for one variant
openai
data-ai
data-analysis
759
gwas-catalog-skill
Submit compact GWAS Catalog REST API v2 requests for studies, associations, SNPs, EFO traits, genes, publications, loci, and metadata. Use when a user wants concise GWAS Catalog summaries
openai
data-ai
data-analysis
759
hmdb-skill
Submit compact HMDB search requests for metabolites, proteins, diseases, and pathways. Use when a user wants concise HMDB summaries
openai
data-ai
data-analysis
759
mgnify-skill
Submit compact MGnify API requests for microbiome studies, samples, and biome metadata. Use when a user wants concise MGnify summaries
openai
data-ai
data-analysis
759
metabolights-skill
Submit compact MetaboLights requests for study discovery and study-level metabolomics metadata. Use when a user wants concise MetaboLights summaries
openai
data-ai
data-engineering
759
bgee-skill
Submit compact Bgee SPARQL requests for healthy wild-type expression metadata and ontology-aware lookup patterns. Use when a user wants concise Bgee summaries; save raw results only on request.
openai
data-ai
data-engineering
759
vercel-queues
Vercel Queues guidance (public beta) — durable event streaming with topics, consumer groups, retries, and delayed delivery. $0.60/1M ops. Powers Workflow DevKit. Use when building async processing, fan-out patterns, or event-driven architectures.
openai
data-ai
machine-learning
759
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
openai
data-ai
machine-learning
759
huggingface-llm-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
openai
data-ai
machine-learning
759
next-forge
next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel. Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages.
openai
data-ai
data-analysis
753
edge-signal-aggregator
Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.
tradermonty
data-ai
data-analysis
753
downtrend-duration-analyzer
Analyze historical downtrend durations and generate interactive HTML histograms showing typical correction lengths by sector and market cap.
tradermonty
data-ai
data-engineering
753
edge-candidate-agent
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
tradermonty
data-ai
data-engineering
753
edge-pipeline-orchestrator
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
tradermonty
data-ai
data-engineering
753
edge-strategy-reviewer
Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategy_drafts/*.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.
tradermonty
data-ai