cyberneticlibrary

The library

Everything we index — ranked by what works, never by stars.

ArtifactsCapabilitiesRecipes
kindallskillworkflowmcp_servercommandsubagentplugin|✓ proven✗ harmfulmeasured only550 artifacts
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
WORKS 55
Sweep screenspot parameters single-variableworkflowEngineeringDataL3
screenspot-param-sweep · Best for adversarial evaluation across agent personas.
WORKS 55
Active-learn classification prompt rulesworkflowDataEngineeringL3
classify-improve · improving classifiers via data-driven signal mining from real failures
WORKS 60
Scout and combine research algorithmsworkflowDataL3
scout-and-combine · fan-out parallel research with synthesized results
WORKS 55
Survey binary behavior across reposworkflowDataL3
rebench-binary-survey · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 59
Benchmark model conversion performanceworkflowDataL3
model-convert-benchmark · Multi-phase model-convert-benchmark orchestration with structured phase control and receipts.
WORKS 56
Classify reference taxonomyworkflowDataL2
references-audit-classify · Comprehensive multi-phase scan across heterogeneous source corpus with parallel validation.
WORKS 54
Load bulk contract data into BigQueryworkflowDataL3
cf-parallel-harvester-rawload · Append-loading UK Contracts Finder historical data (2016-2026) into BigQuery in resumable 2-month shards.
WORKS 57
Extract entities from news articlesworkflowDataL2
news-graph-extract · Building knowledge graphs from news corpora where entities and relationships must be structured for Neo4j ingestion.
WORKS 48
Evaluate AI data, models, and qualityskillEngineeringDataL3
SKILL · Automated data quality gates in ML pipelines with both fast rule checks and semantic LLM scoring
WORKS 48
Assess portfolio risk metricsskillFinanceDataL2
trader-risk · Risk management for traders when you need VaR, position sizing, and circuit breaker alerts in one command.
WORKS 48
Ingest and deduplicate data incrementallyskillDataEngineeringL3
sqlite-incremental-reconcile · When sqlite-incremental-reconcile is needed before shipping or in production.
WORKS 48
Extract and paginate PDF contentskillOpsDataL2
server-pdf · When server-pdf is needed before shipping or in production.
WORKS 48
Evaluate machine learning model performanceskillDataEngineeringL2
evaluate-model · Standardized model evaluation reporting post-training.
WORKS 48
Generate machine learning experiment reportsskillDataL2
generate-report · Creating shareable experiment summaries for stakeholder review.
WORKS 48
Run end-to-end machine learning pipelineskillDataEngineeringL3
run-pipeline · Reproducible end-to-end execution after configuration or code changes.
WORKS 49
Search and Scrape the WebskillDataOpsL2
firecrawl-mcp · When large-scale web scraping or extraction is needed beyond simple HTTP fetch.
WORKS 48
Query PostgreSQL SchemasskillEngineeringDataL2
postgres-mcp · When agents need direct database access for queries or mutations.
WORKS 48
Summarize Text Cost-EffectivelyskillProductivityDataL2
cheap-summarizer · When this specialized capability is required.
WORKS 48
Check GitHub Repository StatsskillDataProductivityL1
github-repo · When this specialized capability is required.
WORKS 48
Monitor Website Uptime and HealthskillOpsDataL1
site-status · When this specialized capability is required.
WORKS 48
Track Trending Repos and PostsskillMarketingDataL1
trending · When this specialized capability is required.
WORKS 48
Summarize Long Text AffordablyskillProductivityDataL2
usdc-summarize · When this specialized capability is required.
WORKS 48
Lookup Domain Registration DetailsskillOpsDataL1
whois-lookup · Verifying domain ownership history, checking expiration dates, or extracting registrar and nameserver info for domain takeover assessment.
WORKS 48
Run isolated compute jobs remotelyskillEngineeringDataL2
modal · Running heavy compute (ML training, data processing), GPU-dependent code, or untrusted code in safe isolation without local GPU procurement or Docker management.
WORKS 48
Access prediction market oddsskillFinanceDataL2
prediction-markets · Getting real-time event probabilities and comparing prices across venues
WORKS 48
Query blockchain data directlyskillEngineeringDataL2
rpc · Low-level blockchain reads where native library integration is overkill
WORKS 48
Analyze crypto markets and walletsskillFinanceDataL2
surf · Quick wallet/contract state snapshots without running full indexing
WORKS 48
Query onchain Base network dataskillDataEngineeringL2
query-onchain-data · Querying decoded blocks, transactions, and events on Base via standardized SQL without running a local full node.
WORKS 57
Exhaustive parallel research across all sourcesskillDataProductL3
ultraresearch · When you need maximum-saturation research across every available source.
WORKS 48
Build production Apache Airflow data pipelinesskillDataEngineeringL3
airflow-dag-patterns · Teams automating repetitive tasks while maintaining control over execution and output quality.
WORKS 48
Query ledger tablesskillDataL1
after_skill · Automating post-work tasks like syncing, cleanup, or notifications
WORKS 48
Build trading strategy backtestingskillFinanceDataL2
backtesting-frameworks · Validating trading strategies when look-ahead bias, survivorship bias, and transaction costs must be accounted for.
WORKS 48
Measure performance regressionsskillEngineeringDataL2
benchmark · Catching performance regressions in real browser metrics before and after code changes or before shipping.
WORKS 48
Browse and extract web contentskillOpsDataL2
agent-browser · Automating form submission, data extraction, and web app testing when refs are more resilient than XPath.
WORKS 48
Scrape URLs at scale with Bright DataskillDataOpsL2
brightdata · Sites with bot detection or CAPTCHA that block naive fetch
WORKS 48
Analyze time series and forecastingskillDataProductL2
aeon · Temporal pattern detection faster/more accurate than standard ML
WORKS 48
Work with single-cell genomics dataskillProductDataL2
anndata · Single-cell genomics where scverse integration is mandatory
WORKS 48
Analyze astronomical data with AstropyskillEngineeringDataL1
astropy · Astronomy research when specialized units + coordinates matter
WORKS 48
Automate lab data with Benchling SDKskillOpsDataL2
benchling-integration · Biotech workflows needing certified ELN audit trails
WORKS 48
Search papers and extract experimental dataskillDataProductL2
bgpt-paper-search · Biotech literature review when Google Scholar insufficient
WORKS 48
Organize and validate brain imaging datasetsskillDataOpsL2
bids · When organizing multi-modal neuroimaging/biomedical datasets for repositories (OpenNeuro, DANDI) or validating BIDS compliance.
WORKS 48
Process molecular biology sequences programmaticallyskillEngineeringDataL2
biopython · When writing batch molecular biology pipelines that manipulate sequences, parse multiple file formats, and access NCBI programmatically.
WORKS 48
Query 40+ bioinformatics databases unifiedskillDataEngineeringL2
bioservices · When integrating data from multiple bioinformatics databases (UniProt, KEGG, ChEMBL) in a single workflow with consistent ID mapping.
WORKS 48
Process RNA-seq from reads to enrichmentskillDataEngineeringL3
bulk-rnaseq · When analyzing bulk RNA-seq from raw reads through differential expression and pathway enrichment with reproducible, quality-gated pipelines.
WORKS 48
Query CZ CELLxGENE census for cell dataskillDataEngineeringL2
cellxgene-census · When querying organism-wide single-cell expression data across tissues without downloading multi-terabyte datasets.
WORKS 48
Design quantum circuits for Google hardwareskillEngineeringDataL2
cirq · When designing and simulating quantum algorithms before submission to real quantum hardware.
WORKS 48
Scale pandas workflows beyond memoryskillDataL2
dask · Scaling existing pandas code to multi-GB datasets without Spark rewrite.
WORKS 48
Search scientific and biomedical databasesskillDataL2
database-lookup · One-query lookups across chemistry, biology, regulatory databases.
WORKS 48
Parse and fingerprint moleculesskillDataL2
datamol · Drug discovery pipelines avoiding low-level RDKit chemistry code.
WORKS 48
Predict molecular properties with MLskillDataL3
deepchem · End-to-end neural property prediction when graph models beat hand features.
←page 2 / 11→