The library

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

untested
Calculate geometry and fabrication costsskillEngineeringDataL2
cd-calculator · Rapid structural/environmental analysis in computational design workflows.
untested
Build interactive data visualizationsskillDataProductL2
d3-viz · Custom data narratives where charting libraries lack flexibility.
untested
Analyze urban data and space analyticsskillDataProductL3
data-driven-design · Defending design intent with ASHRAE/LEED compliance and thermal modeling.
untested
Catalog object-detection datasetsworkflowDataL3
find-kitchen33-datasets · When you need systematic discovery and verification of specialized datasets across multiple sources.
untested
Verify retention tournament metricsworkflowDataL3
alberta-retention-tournament-verify · When you need multi-phase orchestration with parallel agents across a complex workflow.
untested
Build driver catalogs by industryworkflowOpsDataL3
driver-menu-build · Building curated driver catalogs from event sources with blind naming.
untested
Analyze with adversarial score verificationworkflowDataL3
wf-analyze · Go/no-go decisions on architecture changes when you want scored evidence from multiple dimensions plus adversarial challenge built in.
untested
Research topics across multiple sourcesworkflowOpsDataL3
research · Synthesizing evidence on academic/technical topics when you need multi-modality (text+code+data) sweep plus two-stage extraction-enrichment pipeline.
untested
Autonomous ML research loopworkflowDataEngineeringL3
{PROJECT_NAME}-autoresearch · Use when workflow operations need {PROJECT_NAME} autoresearch.
untested
Extract and merge literature reviewworkflowDataProductL3
paper-review-literature · Use when workflow operations need paper review literature.
untested
Adversarially review research paperworkflowDataOpsL3
review-paper · Use when workflow operations need review paper.
untested
Fan-out deep research with citationsworkflowDataMarketingL3
deep-research · Use when workflow operations need deep research.
untested
Research and verify specificity audit methodologyworkflowDataL3
step3-specificity-methodology · Auditing bispecific therapeutic window via parallel research, synthesis, and adversarial critique.
untested
Ingest and index large books in parallelworkflowDataL3
ingest-mcluhan-understanding-media · Ingesting large multi-chapter books with deduplication and cross-chunk synthesis via chunked planners.
untested
Cross-check research claims with sourcesworkflowDataL2
deep-research · Running multi-source research with web fetching, fact verification, and cited synthesis.
untested
Fan-out research with adversarial fact-checkworkflowOpsDataL3
research · Fan-out web research, dedup sources, synthesize with citations, and fact-check claims.
untested
Multi-panel refute findings with consensusworkflowDataOpsL3
verify-findings · Verify code audit findings using 3 independent skeptic lenses.
untested
Execute deterministic research pipelineworkflowOpsDataL3
research-pipeline · Execute research through fan-out collection, dedup, and analysis phases.
untested
Extract and verify factual claimsworkflowOpsDataL2
claim_verifier · Verify document claims are grounded in cited sources.
untested
Scan conformal prediction literatureworkflowDataEngineeringL3
cp-lit-scan · Systematically surveying a research frontier across multiple sub-topics to identify novel research gaps.
untested
Curate tech community research digestworkflowOpsDataL2
research-digest · Aggregating research signals from 7 heterogeneous sources with real-time relevance ranking and dedup.
untested
Run ablation study on hardest problemsworkflowDataL3
mhpp-10-ablation · Ablation studies where solver agents invoke external tools themselves (agentic-tool pattern, not pre-generation).
untested
Backfill public contracts data to BigQueryworkflowDataL4
contracts-finder-backfill · Large-scale procurement time-series ingestion where idempotency and resumability are critical.
untested
Execute data pipeline transformationworkflowDataL3
ds-implement · Complex data structure implementations requiring correctness verification.
untested
Map agent-memory landscape by dimensionworkflowDataL3
amf-landscape-2026-06 · Up-to-date AI model ecosystem analysis with concurrent data collection.
untested
Multi-agent equity analysis and tradingworkflowFinanceDataL3
tradingflow · Analyzing multi-leg trading workflows with execution validation
untested
Expand multilingual fact databaseworkflowDataL3
hiraia-expand-wave · Building fact banks when you need medium-grained concept beats expanded into distinct trilingual (Tagalog/English/Bisaya) child-grade facts.
untested
Reverse-engineer trading strategies from resultsworkflowDataL3
polymarket-reverse-engineer · Designing independent, first-principles trading strategies from observed edge patterns, falsifiable through rigorous gauntlet testing, without relying on wallet-copying.
untested
Hunt and abstract EHR document batchworkflowDataL3
hunt-and-abstract-tranche · Executing the hunt-and-abstract-tranche workflow.
untested
Search iteratively until exhaustedworkflowDataL2
loop-until-dry · Executing the loop-until-dry workflow.
untested
Run parallel search strategiesworkflowDataL2
multi-modal-sweep · Executing the multi-modal-sweep workflow.
untested
Run A/B benchmark sweep across testsworkflowDataL3
gimle-ab-sweep · Running A/B experiments with parallel variant evaluation and statistical reporting.
untested
Cross-model audit classification consistencyworkflowDataL2
verify-classify · Fact-check a claim when credibility and source tracing matter.
untested
Classify allergen groups across speciesworkflowDataL2
allergen-multispecies · Merge allergen data across species when conflict resolution and taxonomy consistency are needed.
untested
Classify allergen data with adversarial reviewworkflowDataL2
allergen-classify-misses · Multi-pass allergen data cleanup when rules are complex and precision matters over speed
untested
Verify allergen detection completenessworkflowDataL2
allergen-completeness · Final completeness pass over rejected rows when regex false-negatives are a known risk
untested
Run multi-stage deep research pipelineworkflowOpsDataL3
mishkan-deep-research · In-depth multi-angle research reports where contradictory sources must be reconciled by skeptic review.
untested
Rank items by pairwise comparison tournamentworkflowOpsDataL2
tournament-sort · Ranking hundreds of items by a nuanced criterion without exhausting a single agent's context window.
untested
Search vectors with hybrid retrievalmcp_serverEngineeringDataL2
turbopuffer · Add semantic search to agent systems needing fast, scalable vector DB without managing infrastructure.
untested
Search German business directorymcp_serverSalesDataL2
mcp-server · When you need mcp-server capabilities in your MCP stack
untested
Search, extract, and crawl webmcp_serverDataSalesL2
tavily-mcp · Multi-mode web research (search, extract, map, crawl) for autonomous agents
untested
Classify UK businesses by SIC codesmcp_serverDataSalesL2
sic-codes · Classifying UK businesses by Standard Industrial Classification codes
untested
Fetch crypto prices and on-chain datamcp_serverFinanceDataL2
crypto-mcp · When you need crypto-mcp capabilities in your MCP stack
untested
Run analytical queries without SQL editormcp_serverDataEngineeringL2
clickhouse · Letting AI agents run analytical queries on ClickHouse without SQL editor.
untested
Analyze MLB player stats and performancemcp_serverDataL2
mlb-mcp · Sports analytics agents analyzing player performance and game outcomes.
untested
Access Canadian economic data directlymcp_serverDataFinanceL2
statscan-mcp · Canadian economic and demographic research using official government data.
untested
Query and manage SQL Server databasesmcp_serverEngineeringDataL2
mssql-mcp · Enterprise agents working with SQL Server data pipelines where direct database access is safer than APIs.
untested
Crawl and index web content flexiblymcp_serverMarketingDataL2
exa-mcp-server · Web research and content extraction requiring flexible crawling depth and live indexing.
untested
Query Malaysian government statisticsmcp_serverDataL2
seahboonkeong-chat-opendosm · Malaysian-specific data analytics and government statistics integration for regional AI apps.
untested
Compare products across regional marketplacesmcp_serverSalesDataL2
mcp-server · E-commerce recommendation and shopping agents comparing products across Asian and US markets.
page 10 / 11