组织

OpenAI

访问官网 ↗更新于 2026-11-11

Skills
171
仓库
23
职业覆盖
7
场景覆盖
6
Stars
★ 34w

OpenAI 的 Skills 171

openai
openai/openai-agents-python

release-candidate-prep

Prepare a local Python SDK release candidate in a dedicated worktree. Use only when explicitly invoked with a version.

★ 3.1w
openai
openai/openai-agents-python

pr-draft-summary

Prepare the required local PR title, description, and branch suggestion after eligible implementation work is complete.

★ 3.1w
openai
openai/openai-agents-python

openai-knowledge

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

资料检索与研究Skill与智能体开发
★ 3.1w
openai
openai/openai-agents-python

maintainer-review

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

★ 3.1w
openai
openai/openai-agents-python

implementation-strategy

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

★ 3.1w
openai
openai/openai-agents-python

implementation-kickoff

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

★ 3.1w
openai
openai/openai-agents-python

implementation-final-review

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

★ 3.1w
openai
openai/openai-agents-python

final-release-review

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

★ 3.1w
openai
openai/openai-agents-python

examples-run-analysis

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

★ 3.1w
openai
openai/openai-agents-python

docs-sync

Audit or update English SDK documentation against the requested implementation scope.

★ 3.1w
openai
openai/openai-agents-python

code-change-verification

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

开发工程师
★ 3.1w
openai
openai/symphony

release

Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.

★ 2.8w
openai
openai/symphony

push

Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request.

★ 2.8w
openai
openai/symphony

pull

Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices.

★ 2.8w
openai
openai/symphony

linear

Use Symphony's `linear_graphql` client tool for raw Linear GraphQL operations such as comment editing and upload flows.

★ 2.8w
openai
openai/symphony

land

Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion.

★ 2.8w
openai
openai/symphony

debug

Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.

开发工程师
★ 2.8w
openai
openai/symphony

commit

Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work.

★ 2.8w