GitHub organization
Agent skills by openai
- skills
- 31
- official
- 31
- repositories
- 4
Repositories by openai
- openai-agents-pythonOfficialA lightweight, powerful framework for multi-agent workflows30k stars · 14 skills
- openai-agents-jsOfficialA lightweight, powerful framework for multi-agent workflows and voice agents3.9k stars · 10 skills
- openai-guardrails-jsOfficialOpenAI Guardrails - TypeScript / JavaScript104 stars · 5 skills
- snap-oOfficialLightweight Android capture developer tools for macOS114 stars · 2 skills
Skills by openai, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Review completed implementation changes before final verification. | openai/ | 30k | — | ~2k | Automated safety check: Pass | MIT | today |
| 2 | Audit or fix sensitive-data exposure in Python SDK diagnostics, exceptions, logging, and telemetry. | openai/ | 30k | — | ~1k | Automated safety check: Pass | MIT | today |
| 3 | Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). | openai/ | 3.9k | — | ~607 | Automated safety check: Pass | MIT | today |
| 4 | Assess a Python SDK release candidate or release plan against the previous release and recommend ship or block. | openai/ | 30k | — | ~5.4k | Automated safety check: Pass | MIT | today |
| 5 | Prepare a local Python SDK release candidate in a dedicated worktree. | openai/ | 30k | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 6 | 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. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 7 | Assess a JS SDK release candidate or release plan against the previous release and recommend ship or block. | openai/ | 3.9k | — | ~4k | Automated safety check: Pass | MIT | today |
| 8 | Run the required final formatting, lint, type, and test checks after eligible SDK changes pass review. | openai/ | 30k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 9 | Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry. | openai/ | 3.9k | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 10 | Inspect Android network captures and intercept HTTP calls with the Snap-O CLI for a selected device/socket. | openai/ | 114 | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Analyze logs and source from a completed manual examples run. | openai/ | 30k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 12 | Inspect, stream, and explicitly adjust live Android UI tweak values or invoke app-owned actions through Snap-O. | openai/ | 114 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Carry implementation through an isolated worktree and local handoff. | openai/ | 30k | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 14 | Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations. | openai/ | 3.9k | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 15 | Choose supported scope and compatibility boundaries for SDK behavior changes; revisit when feedback changes the design. | openai/ | 30k | — | ~3.7k | Automated safety check: Pass | MIT | today |
| 16 | Run the required final install, build, type, lint, test, and format checks after eligible SDK changes pass review. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 17 | Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes. | openai/ | 104 | — | ~619 | Automated safety check: Pass | MIT | 9 days ago |
| 18 | Measure Python SDK coverage or address measured coverage gaps. | openai/ | 30k | — | ~687 | Automated safety check: Pass | MIT | today |
| 19 | Analyze logs and source from a completed repository example run. | openai/ | 3.9k | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 20 | Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure. | openai/ | 104 | — | ~825 | Automated safety check: Pass | MIT | 9 days ago |
| 21 | Audit or update English SDK documentation against the requested implementation scope. | openai/ | 30k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 22 | Retrieve authoritative OpenAI API and platform documentation when an integration or claim needs current external evidence. | openai/ | 30k | 1 repo | ~408 | Automated safety check: Pass | MIT | today |
| 23 | Prepare the required local PR title, description, and branch suggestion after eligible implementation work is complete. | openai/ | 30k | — | ~1.8k | Automated safety check: Warn | MIT | today |
| 24 | Measure JS SDK coverage or address measured coverage gaps. An agent skill from openai/openai-agents-js. | openai/ | 3.9k | — | ~729 | Automated safety check: Pass | MIT | today |
| 25 | Plan controlled runtime probes when explicitly invoked; execute only after the required probe approval. | openai/ | 30k | — | ~3.8k | Automated safety check: Pass | MIT | today |
| 26 | Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification. | openai/ | 104 | — | ~1k | Automated safety check: Pass | MIT | 9 days ago |
| 27 | Audit or update authored English SDK documentation within a requested topic or diff using implementation evidence. | openai/ | 3.9k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 28 | Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes. | openai/ | 104 | — | ~951 | Automated safety check: Pass | MIT | 9 days ago |
| 29 | Assess a GitHub issue or PR for demonstrated need, supported alternatives, correctness, and maintainer action. | openai/ | 30k | — | ~8.9k | Automated safety check: Pass | MIT | today |
| 30 | Prepare a local PR title, description, and branch suggestion when requested or after eligible implementation work. | openai/ | 3.9k | — | ~1.8k | Automated safety check: Warn | MIT | today |
| 31 | Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers. | openai/ | 104 | — | ~1k | Automated safety check: Pass | MIT | 9 days ago |
Questions, answered from the data.
What is the best skill by openai?
Implementation Final Review (official) from openai/openai-agents-python ranks first of the 31 skills by openai listed here, with the highest score: its repository has 30k GitHub stars, its SKILL.md loads about 2k tokens and it passes the automated safety check with no findings. Next come Sensitive Logging Audit and Changeset Validation.
Are openai's skills official?
31 of the 31 skills by openai are official, published by the vendor's own GitHub organization: Implementation Final Review, Sensitive Logging Audit, Changeset Validation, Final Release Review, Release Candidate Prep and 26 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.