eval-skill
A test skill for CSV data processing and analysis. Use when testing functional and trigger evaluation.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Data & analytics
17,418 results
data-platform-pipeline
Build a production-ready serverless data lake pipeline on AWS. Creates S3 storage (3-bucket layout), Glue Catalog, ETL jobs, IAM roles, and Athena query…
db-migration-inception
Inception phase (assessment & planning) of an AI-DLC database migration. Use after the orchestrator has gathered intake and verified connectivity, or when the…
db-migration-operations
Operations & Cutover phase of an AI-DLC database migration. Use after Validation is approved, or when the user asks to plan cutover, go-live, rollback, or…
db-migration-orchestrator
Entry point for an AI-DLC-style database migration. Use when the user wants to migrate a database or convert a schema between engines, or says things like…
boj-statistics
Fetch, search, and analyze time-series statistical data from the Bank of Japan (BOJ) public API. Covers all BOJ databases including interest rates, money…
diagram-generator
Generate diagrams and charts using Python code via Bedrock Code Interpreter (matplotlib, pandas, numpy).
cosmosdb-best-practices
Azure Cosmos DB performance optimization and best practices guidelines for NoSQL, partitioning, queries, SDK usage, and vector search. Use when writing,…
extract-blockchain-media
This skill should be used when extracting media files from BSV blockchain transactions — downloading inscribed ordinals, retrieving on-chain…
stack-api
This skill should be used when working with the 1sat-stack unified BSV indexing API — whenever an agent needs to fetch UTXOs, look up inscriptions or ordinals,…
famou-data-analysis
Data analysis skill, used to understand data, analyze data, create data processing workflows, and summarize data analysis results. When the user mentions "analyze data", "data processing", "data exploration", "statistical analysis", "data cleaning", "data summarization", "create a data report", "understand this data", "take a look at this CSV/Excel/dataset", this skill must be used. Even if the user only says "help me take a look at this data" or "analyze it", as long as the context...
famou-result-visualization
Generate a Python code solution visualization result page for a feasible solution of the FaMou evolutionary algorithm. When the user mentions "FaMou visualization", "visualize this solution", "feasible solution result display", "evolution result", "evolve visualization", or provides Python...
prototype
Autonomous prototype builder using the Generator-Evaluator loop. Builds any interactive prototype - pages, dashboards, flows, tools, visualizations - then…
scienceclaw-benchmark-for30
Use when segmenting top-down field or UAV RGB images of crops (sugar beet, PhenoBench-style) into soil / crop / weed semantics plus crop-plant and crop-leaf…
scienceclaw-benchmark-for31
Use when ranking or predicting the fitness effect of single amino-acid substitutions in a protein (deep mutational scanning, ProteinGym-style assays) from…
scienceclaw-benchmark-for33
Use when forecasting day-ahead hourly electricity load of individual buildings (residential and commercial smart-meter data, BuildingsBench-style) from the…
scienceclaw-benchmark-for34
Use when predicting a binary molecular property such as HIV replication inhibition (OGB ogbg-molhiv, MoleculeNet-style activity) from SMILES strings and…
scienceclaw-benchmark-for35
Use when forecasting monthly tourism, visitor or other seasonal business and service series (Monash Tourism Monthly, 24-month horizon, period 12) from each…
scienceclaw-benchmark-for38
Use when a task asks to forecast annual country-level economic series several years ahead (for example GDP per capita levels or unemployment rates, horizon 4)…
scienceclaw-benchmark-for39
Use when a task asks to predict whether students answer held-out diagnostic multiple-choice questions correctly, from a large student-by-question correctness…
scienceclaw-benchmark-for40
Use when a task asks for unsupervised anomalous sound detection for one machine type in the first-shot setting (only normal source-domain training clips, no…
scienceclaw-benchmark-for41
Use when a task asks for 30-day-ahead probabilistic daily forecasts of dissolved oxygen (mg/L) and water temperature (degC) at freshwater monitoring sites from…
scienceclaw-benchmark-for42
Use when a task gives hourly ICU records (vitals, labs, demographics, one stay per patient) with sepsis labels and asks for causal hour-by-hour sepsis alarms…
scienceclaw-benchmark-for44
Use when a task gives a covariate table plus, for each of many simulated observational datasets, a binary treatment vector and an outcome vector, and asks for…