Construct Python SDK queries to retrieve Isabl data with filters.
npx skills add https://github.com/juanesarango/isabl-mcp --skill isabl-query-data
Please help me install this Agent Skill. Skill: isabl-query-data Source: https://github.com/juanesarango/isabl-mcp/tree/main/skills/isabl-query-data Command: npx skills add https://github.com/juanesarango/isabl-mcp --skill isabl-query-data
This skill helps you construct queries to retrieve data from the Isabl platform using the Python SDK, enabling efficient access to experiments, analyses, samples, and related data.
Generate a Python SDK query to retrieve all experiments for a given project and return their system_id and sample identifier.
High-intent search queries and answers about installing and using this skill.
The Python SDK allows you to query Isabl data by specifying entity types like experiments or samples and applying filters such as status, dates, and project. You can traverse related objects and return results as lists, dictionaries, or DataFrames for downstream analysis.
Yes, you can filter Isabl experiments by status and date ranges. The Skill guides you in applying these filters to experiments, analyses, and samples, enabling precise data retrieval and traversal of related objects across projects.
The best way to retrieve Isabl analysis results in a DataFrame is to build a Python SDK query targeting the analysis entity type. The query supports output formatting into lists, dictionaries, or DataFrames containing identifiers for downstream analysis.
You traverse related objects in Isabl queries by using the Python SDK to build queries that connect entities like samples and experiments. This allows precise data retrieval across projects, applying filters and returning results in convenient formats.
Yes, the Isabl Python SDK supports querying samples across multiple projects. You can build queries targeting the sample entity type and apply project-based filters to retrieve precise results and traverse related objects.
Isabl Python SDK query results can be returned as lists, dictionaries, or DataFrames. These formats include identifiers suitable for downstream analysis, ensuring the retrieved experiments, analyses, and samples are ready for further use.
legoutConnect Streamlit applications to Snowflake databases using st.connection.
kyirexyAnalyze Excel and CSV files with DuckDB SQL queries and export results.
vikrant-projectIndex and fetch bioinformatics skills from bioSkills and ClawBio libraries.
a-ng-dQuery GitLab REST and GraphQL APIs from the CLI, returning JSON.
