The library

yfinance · Rapid prototyping of quant research and backtesting without API keys or rate limits

snowflake-development · Build low-latency data transformations and AI-powered agents on Snowflake without external orchestration

statistical-analyst · Rigorously validating A/B test results when business decisions depend on statistical confidence.

debug · Debugging across software/data/infra layers when the cause isn't obvious from symptoms alone

miudb · Running structured SQL and smoke-testing database connections when you need machine-readable JSON output for scripting or agent tasks.

build-vault-universe · Keeping performance-ranked portfolios current without manual list maintenance.

sqlit · Ad-hoc database queries without leaving the agent session.

analytics · When defining and implementing product telemetry and metrics.

ktx-analytics · Getting a quick operational health snapshot of your Kubernetes cluster without setting up full monitoring infrastructure

dbt_ingest · Extracting structured metadata from a dbt project for documentation, lineage visualization, or quality auditing without running dbt

historic_sql_patterns · Identifying which query patterns consume the most resources and repeat most frequently so you can optimize the highest-impact ones first

historic_sql_table_digest · Understanding how a table evolved over time and what breaking changes happened so data pipelines can be updated correctly

ingest_triage · Automatically sorting mixed-format inbound data into typed flows so downstream processors only see valid, correctly categorized items

live_database_ingest · Continuously loading timestamped data into a database for real-time analytics dashboards without manual batch jobs

looker_ingest · Extracting Looker dashboard structure and lineage for documentation or migration without manually re-creating in code

lookml_ingest · Mapping Looker views to semantic layer overlays when manifest tables exist.

metabase_ingest · Harvesting Metabase questions into reusable semantic layer sources with deduplication.

metricflow_ingest · Flattening MetricFlow semantic models and metrics into KTX overlay and derived sources.

sl · Querying predefined business metrics and joins from a structured semantic catalog.

sl_capture · Capturing and deduplicating semantic layer sources while verifying warehouse identifiers.

csv-processor · Parsing and transforming CSV data with flexible schema handling.

data_exploration_workflow · Before modeling or deciding on a dataset to expose missing values, duplicates, and anomalies.

deep-research · the user wants thorough research on any topic with evidence and citations

refactoring-08-experiment-tracking · For structured refactoring 08 experiment tracking workflows.

stata-log · See body for use case.

electronic · When Prepare CP2K electronic-analysis task inputs from prior converged context. Use when the user requests post-ground-state electronic analyses and needs prerequisite-aware setup

firecrawl-scraper · - When you need deep content extraction from web pages

sql-escaper · When sql escaper capability is needed

pi-dynamic-workflows · When pi dynamic workflows capability is needed

tmr-content-decay-detector · When you need to prioritize content refresh and identify evergreen vs. decayed assets without manual review.

skill · Wallets and block explorers needing fast account balances and token holdings without running a full NEAR node.

tmr-website-traffic-growth-analyst · Website owners needing automated SEO audit (CTR, traffic drops, cannibalization, gaps) without manual data export.

feedradar · Teams tracking multiple feeds needing automated summarization without copy-paste of release notes.

universal-scraping-architect · Data engineers needing flexible web scraping without writing per-site parsers.

aminer-rec5 · Delivering personalized paper recommendations to researchers in Feishu without exposing recommendation logic.

SKILL · Decentralized apps (dapps) querying blockchain data without running a full node.

data-visualization · When creating charts, designing dashboards, critiquing visualizations, or choosing how to display data.

skill · When this is the appropriate approach for the task.

data-wrangling · When preparing, cleaning, or transforming data for analysis.

experimental-design-ds · When designing experiments, planning a/b tests, calculating sample sizes, or reasoning about causation from data.

cradle-ecosystem-data-ingestion · When this is the appropriate approach for the task.

machine-learning-foundations · When building predictive models, selecting algorithms, or understanding the machine learning pipeline.

statistical-modeling · When fitting models, testing hypotheses, or selecting among competing statistical explanations.

arrow-cli · Quick exploration and transformation of Parquet files in data pipelines

human-impact-assessment · Forecasting extinction risk or habitat loss from proposed development when receptor sensitivity is quantifiable.

cartography-gis · Creating area-accurate or direction-accurate maps when projection distortion directly affects decision (navigation vs. density comparison).

species-interaction-tracking · When studying what a species actually does over time rather than just identifying it.

contested-claims-in-nutrition · When evaluating nutritional claims with scientific rigor and distinguishing settled from genuinely contested evidence.

dietary-assessment · When you need to choose the right dietary measurement method (24-h recall, FFQ, diary, biomarker) for your question.

nutrient-metabolism · When you need detailed biochemistry of how your body processes specific nutrients.