DATA AND RESEARCH / OpenAI
OpenAI Data Analytics Notebooks
Turns SQL or Python analysis into a traceable notebook whose conclusions are tied to executed outputs and stated assumptions.
“Create, edit, or validate reproducible SQL or Python notebooks.…”
01 / THE REASONING
Why this made the selection.
- Records query links, input versions, filters and cohort definitions next to the analysis.
- Requires surprising results to pass reasonableness checks before they enter the summary.
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- plugins/data-analytics/skills/jupyter-notebooks/SKILL.md
- plugins/data-analytics/.codex-plugin/plugin.json (license Proprietary)
- plugins/data-analytics/README.md
Our findings
- The workflow prefers notebook-aware tooling to hand-editing raw JSON and preserves existing notebook intent.
- Summary and takeaways are written after checking executed cells, with missing execution clearly called out.
- For decision-support results it routes to the plugin’s separate data-validation skill.
- Execution uses python -m jupyter nbconvert --execute --to notebook --inplace, with uv pip install jupyterlab nbformat nbclient ipykernel as optional setup. If execution is impossible, the agent must name the missing command, dependency, credential, data access or kernel.
- Re-pinned from 1dc195897af4161d039b80d8471ec0a10c9bbc89 to 0722921d5542fc593105c27bd52630babd8b8c2a: no file under plugins/data-analytics changed between the two (GitHub compare), and plugin.json still declares license Proprietary.
Not established by this review
- Source inspection only; no skill installation or workflow execution was performed.
- Not executed: it was not installed or run.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Add a skill to your workflow.
- Use the complete data-analytics Codex plugin through its supported distribution and setup instructions.
- Retain plugin-level references and companion skills; this is not a standalone SKILL.md installation.
- Confirm plugin availability and any required connectors in the Codex host before invoking the workflow.
Before you start
- A Codex host with access to this plugin and its applicable service terms
- A compatible kernel and source data
- Authorized connector access where live queries are needed
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
https://github.com/openai/plugins/blob/0722921d5542fc593105c27bd52630babd8b8c2a/plugins/data-analytics/skills/jupyter-notebooks/SKILL.md
Supports: summary, upstreamDescription, whySelected, bestFor, limitations, review, compatibility, access
https://github.com/openai/plugins/blob/0722921d5542fc593105c27bd52630babd8b8c2a/plugins/data-analytics/.codex-plugin/plugin.json
Supports: license
https://github.com/openai/plugins/blob/0722921d5542fc593105c27bd52630babd8b8c2a/README.md
Supports: install, compatibility, access
https://github.com/openai/plugins/blob/0722921d5542fc593105c27bd52630babd8b8c2a/plugins/data-analytics/README.md
Supports: install, compatibility, access, review
https://raw.githubusercontent.com/openai/plugins/0722921d5542fc593105c27bd52630babd8b8c2a/plugins/data-analytics/skills/jupyter-notebooks/SKILL.md
Supports: bestFor, review.notTested, upstreamDescription, review.reviewedAt