使用方法
- 复制安装命令,在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物,并对照来源检查输出。
npx skills add https://github.com/novainsilico/jinko-skills --skill jinko-data-table开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况,不等于独立质量或安全测试。
按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Jinkō Data Table SDK Workflows
Use this skill for data-table mechanics through the SDK. Data tables can support trial overlays and calibration objectives; the row schema is the same, and fitness-function compatibility is reported by metadata when available.
PREREQUISITE: This skill needs an initializedjinko-sdkconnection and an SDK satisfying itsmetadata.requires_sdkrange. Run thejinko-sdk-setupskill (../jinko-sdk-setup/SKILL.md) and proceed only once its check passes. UseJINKO_API_KEYwhen it is set. Only without a key, callget_session_codeagain before this skill's own SDK process, because a session code can be exchanged only once. If that skill is not found, install it fromnovainsilico/jinko-skills.
Scope
- Use
client.create_data_table_from_csv()for CSV files or bytes. - Use
client.create_data_table_from_sqlite()for SQLite files or bytes. - Use
client.create_data_table_from_dataframe()for pandas DataFrames. - Inspect existing data tables with
get_data_table(),content(),summary(),validate(), andexport(). - Update an existing data table with
data_table.replace_csv(...),data_table.replace_sqlite(...), ordata_table.update_mappings(...). See "Update an existing data table". - Check
metadata.public.validForFitnessFunctionafter creation or inspection when available if the data table needs to be attached through trial/calibrationdataTableDesigns. - For trial workflows that attach data tables through
jinko-trial, use a data table withvalidForFitnessFunction: True; point-value overlay tables may upload successfully but fail trial launch sanity.
Update an existing data table
When you correct or extend the observed data of the same experiment, update the existing data table. Do not create a new data table for each attempt.
data_table.replace_csv(csv_text, version="<short name>")replaces the data with new CSV content.replace_sqlite(sqlite_bytes, version=...)does the same for SQLite. The SID, mappings, and earlier versions stay.data_table.update_mappings(mappings, version=...)changes only the mappings.- Check
metadata.public.validForFitnessFunctionagain after the update. - A Trial or Calibration keeps the data-table Snapshot that it was given. Call
trial.set_components(data_tables=[data_table], version=...)or the same method on the Calibration to use the new version.data_tablesreplaces the complete list. - Create a new data table only for a different dataset, for example another study or endpoint.
Project Folder Hygiene
- Prefer creating data tables inside a dedicated Jinkō folder instead of the project root. At the start of a workflow, ask for or propose a folder name, for example
YYYY-MM-DD-<experiment-name>. - Reuse an existing exact-match folder when possible:
client.get_folder_by_name(name, exact_match_only=True). - If the folder does not exist, create it only after user confirmation or when a script is run with
--apply. - Resolve one folder object or folder id, then pass
folder=folderto SDK creation calls that support it.
Row Schema
Read assets/data-table.json before changing CSV structure.
Supported row shapes:
- Point-value row:
obsId,time,value, plus optionalunit,armScope, ranges, weight, and reference. - Range row:
obsId,time,narrowRangeLowBound,narrowRangeHighBound, plus optionalunit,armScope, wide ranges, weight, and reference.
Use ISO-8601 duration strings for time, for example PT0S, PT6H, or P1D.
Bundled Assets
assets/toy_data_table_values.csv: point-value observations for trial overlays.assets/toy_data_table_ranges.csv: range observations suitable for calibration objective workflows.assets/data-table.json: schema subset for supported data-table rows.
SDK Scripts
These are on PATH as console scripts once the SDK is installed, and also runnable via python -m as shown below.
jinko.cli.create_data_table: dry-run-validates every CSV row and creates a
data table with --apply; use --allowed-obs-id, --require-unit, --require-experiment-ref, and --require-fitness for calibration inputs.
jinko.cli.create_data_table --data-table-sid dt-...: replaces the data of
an existing data table and saves a new version named with --version-name. It runs the same row checks.
jinko.cli.inspect_data_table: inspects existing data tables and can enforce
fitness compatibility with --require-fitness.
Examples:
python -m jinko.cli.create_data_table --source skills/jinko-data-table/assets/toy_data_table_ranges.csv --method csv
python -m jinko.cli.create_data_table --source extracted.csv --allowed-obs-id Drug --require-unit --require-experiment-ref --require-fitness --apply
python -m jinko.cli.create_data_table --source skills/jinko-data-table/assets/toy_data_table_ranges.csv --method csv --apply
python -m jinko.cli.create_data_table --source skills/jinko-data-table/assets/toy_data_table_ranges.csv --method csv --folder 2026-06-15-fit-data --create-folder --apply
python -m jinko.cli.create_data_table --source skills/jinko-data-table/assets/toy_data_table_values.csv --method dataframe --apply
python -m jinko.cli.create_data_table --source corrected.csv --data-table-sid dt-... --version-name "fix Drug units" --require-fitness --apply
python -m jinko.cli.inspect_data_table --data-table-sid dt-... --fitness --validateReference Routing
- Read
references/data-table-schema.mdfor row shape and fitness-function notes. - Read
assets/data-table.jsonwhen checking required columns.
