
OpenAI Agents SDK for TypeScript Agent Skills
A TypeScript SDK for agent workflows, tools, handoffs, tracing, and realtime applications.
Repository snapshot · main · 506f736
Scanned 2026-09-17
1–18 of 18 skills
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.
.agents/skills/changeset-validation/SKILL.md
code-change-verification
Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review.
.agents/skills/code-change-verification/SKILL.md
docs-sync
Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence.
.agents/skills/docs-sync/SKILL.md
examples-run-analysis
Analyze logs and source from a completed repository example run. Never execute or control examples.
.agents/skills/examples-run-analysis/SKILL.md
final-release-review
Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block.
.agents/skills/final-release-review/SKILL.md
implementation-final-review
Review completed implementation changes before final verification. Use when repository policy requires independent review or the user explicitly requests it.
.agents/skills/implementation-final-review/SKILL.md
implementation-kickoff
Carry implementation through an isolated worktree and local handoff. Use only when this skill is explicitly invoked.
.agents/skills/implementation-kickoff/SKILL.md
implementation-strategy
Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design.
.agents/skills/implementation-strategy/SKILL.md
maintainer-review
Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. Desk review only.
.agents/skills/maintainer-review/SKILL.md
openai-knowledge
Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence.
.agents/skills/openai-knowledge/SKILL.md
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.
.agents/skills/pnpm-upgrade/SKILL.md
pr-draft-summary
Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work.
.agents/skills/pr-draft-summary/SKILL.md
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 probes outside tracked paths, and report observed evidence.
.agents/skills/runtime-behavior-probe/SKILL.md
sensitive-logging-audit
Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry.
.agents/skills/sensitive-logging-audit/SKILL.md
test-coverage-improver
Measure JS SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.
.agents/skills/test-coverage-improver/SKILL.md
invoice-total-fixer
Use when fixing invoice total calculations in the sandbox quickstart repository.
examples/docs/sandbox-agents/skills/invoice-total-fixer/SKILL.md
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
examples/sandbox/data/coding-task/skills/credit-note-fixer/SKILL.md
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
examples/tools/skills/csv-workbench/SKILL.md
Discovery details
Tracked SKILL.md files, excluding tests, fixtures, dependencies, and vendored directories. The Instructions analysis keeps its own pinned revision.
Give your agents the whole story.
Skills teach agents how your team works. Modem shows them what customers said, who is affected, and what changed.