openai/openai-agents-js

code-change-verification

Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.

changeset-validation

Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.

final-release-review

Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block.

maintainer-review

Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. Desk review only.

implementation-final-review

Review completed implementation changes before final verification. Use when repository policy requires independent review or the user explicitly requests it.

docs-sync

Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence.

examples-run-analysis

Analyze logs and source from a completed repository example run. Never execute or control examples.

implementation-kickoff

Carry implementation through an isolated worktree and local handoff. Use only when this skill is explicitly invoked.

implementation-strategy

Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design.

openai-knowledge

Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.

pr-draft-summary

Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work.

sensitive-logging-audit

Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry.

test-coverage-improver

Measure JS SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.

runtime-behavior-probe

Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations. Use only when explicitly invoked to verify behavior that code review and normal tests cannot settle; define a controlled validation matrix, keep disposable JS…

pnpm-upgrade

Keep pnpm current: preflight the published package and pnpm/action-setup self-installer, update pnpm locally, align packageManager in package.json, and refresh CI pins. Use this when refreshing the pnpm toolchain manually or in automation.

invoice-total-fixer

Use when fixing invoice total calculations in the sandbox quickstart repository.

csv-workbench

Analyze CSV files in /mnt/data and return concise numeric summaries.