openai/openai-agents-js
9 skills1k installs31.7k starsGitHub
Install
npx skills add https://github.com/openai/openai-agents-jsSkills in this repo
1Pnpm UpgradeEight-step toolchain refresh for the openai-agents-js monorepo. Updates pnpm via self-update or corepack prepare, captures PNPM_VERSION, fetches npm registry integrity, converts sha512 digest to hex for packageManager field format pnpm@VERSION+sha512.HEX. Queries GitHub API for latest pnpm/action-setup release tag, resolves immutable commit SHA via git ls-remote, and hand-edits each workflow file using that action without broad regex replacements. Verifies pnpm -v matches packageManager, confirms integrity suffix, and diffs only intended files. Notes required tools curl, jq, base64, xxd, and recommends light verification unless runtime code changed.131installs2Docs Syncopenai-agents-js documentation sync skill. Analyzes main branch code and configuration against docs/ directory to identify gaps, inaccuracies, and stale pages. Used when asked to audit doc coverage, sync docs with code, or prepare documentation updates after API changes. Compares exported APIs, configuration options, and example code against written documentation, producing a prioritized list of doc fixes aligned with monorepo package structure.124installs3Code Change VerificationMandatory verification skill for openai-agents-js monorepo changes touching runtime code, tests, or build and test configuration. Defines the required command sequence including typecheck, lint, unit tests, and integration checks before PR submission. Ensures contributors do not merge changes that break the pnpm workspace build graph or package exports. Referenced by other skills like pnpm-upgrade as the follow-up when runtime code is modified.117installs4Test Coverage Improveropenai-agents-js test coverage improvement skill. Runs pnpm test:coverage, inspects coverage artifacts and reports, identifies low-coverage files and uncovered branches, and proposes high-impact tests to add. Focuses on meaningful coverage gains in runtime packages rather than trivial assertion padding. Guides contributors toward tests that exercise critical agent SDK paths, error handling branches, and public API surfaces with the highest risk from untested code.114installs5Changeset Validationopenai-agents-js changeset validation skill. Uses LLM judgment to verify that changeset files in .changeset/ accurately describe the git diff for modified packages. Runs when packages/ or .changeset/ are modified or when verifying release notes before publish. Compares declared version bump type and changelog entries against actual code changes including uncommitted local work, catching mismatches between changeset prose and implementation before merge.113installs6Pr Draft Summaryopenai-agents-js PR draft summary skill for final handoff after moderate or larger runtime changes. Produces required summary block format, suggested branch name, PR title, and draft description following monorepo conventions. Used in the final handoff step after code-change-verification completes, ensuring PRs have consistent structure for reviewers. Captures what changed, why, test evidence, and any breaking change notes aligned with package release expectations.112installs7Integration Testsopenai-agents-js integration tests skill for the pipeline depending on a local Verdaccio npm registry. Executes integration tests and local publish workflows validating package consumption as published artifacts rather than workspace links. Used when asked to run integration tests or local publish workflows in the monorepo. Documents Verdaccio startup, registry configuration, test execution order, and cleanup after integration test runs complete.108installs8Examples Auto Runopenai-agents-js examples auto-run skill for executing examples:start-all in auto mode. Parallel execution of all example scripts with per-script log capture and start/stop helper utilities. Validates that SDK examples run successfully against configured providers in batch. Used for smoke testing the examples directory after changes to core packages or provider integrations.103installs9Final Release Reviewopenai-agents-js final release review skill. Locates previous release tag from remote tags and audits the diff between that tag and target commit for breaking changes, regressions, and improvement opportunities. Comprehensive pre-publish gate ensuring release notes accuracy, API stability, and no overlooked breaking changes before npm publish. Used as final checklist before cutting a new agents-js release version.100installs