.md
Try these ChatGPT and Codex workflows
Turn protein-folding hypotheses into benchmarked experiment loops.
Rank drug targets across multiple evidence lanes.
Review single-cell QC, annotations, and UMAPs in one chat.
Validate bulk RNA-seq inputs before differential expression.
Catch regressions and potential issues before human review.
Find vulnerabilities in your code, review the evidence, and decide what needs attention.
Open a finding from your scan, review and apply a patch, and verify the fix.
Search an authorized repository deeply for plausible vulnerabilities.
Convert Zoom meeting insights into actions across your tools.
Turn dense source material into a clear, reviewable learning report.
Build or update a web app, deploy a preview, and get a live URL.
Turn reviewed findings into minimal fixes with regression evidence.
Review a pull request or local diff for security regressions.
Turn a public package advisory into a safe repo-audit plan.
Click through real product flows and log what breaks.
Create a skill Codex can keep on hand for work you repeat.
Run security scans across repositories and review the findings and coverage.
Rank accounts by risk, upside, urgency, and next action.
Decide which deals belong in commit, upside, or pull.
Combine evidence, tradeoffs, and open questions into one recommendation.
Scan pull requests, commits to main, or your repository on a schedule.
Review scoring patterns without assigning or changing grades.
Find the real blocker and the next customer-facing move.
Turn experiment or launch results into a scale, change, or stop recommendation.
Turn governance context into a review-ready meeting packet.
Turn recent account activity into a current deal strategy pack.
Review a course as one connected system.
Build a source-linked evidence base for research or proposals.
Turn a team workflow into a hosted internal app with Sites.
Give Codex a durable objective for long-running work.
Help users learn your app with a tour that adapts as they go.
Use Codex to turn expected behavior into a Promptfoo eval suite.
Give Codex a composable command for an API, log source, export, or team script.
Run repeatable workflows and verify the result.
Join spreadsheet exports into one refreshable workbook.
Try clearing a few filters or searching for a broader term.
Loading docs agent...
