Skip to content
TrustedSkillsbeta
Back to all skills

Final Release Review

Official
openai·vlatest·devops·MIT

Automates final release checks, verifying deployment readiness and identifying potential issues before production launch.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add openai/openai-agents-python --skill final-release-review -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

openai

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned openai/openai-agents-python at e6c680672c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
e6c680672c
Manifest
.agents/skills/final-release-review/SKILL.md
Scanned
4 files, 390 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Final Release Review skill automates checks for release candidates, ensuring deployment readiness and identifying potential issues before a production launch. It fetches remote tags, compares changes between a previous release tag (BASE_TAG) and the latest commit (TARGET), and analyzes this diff for breaking changes, regressions, bugs, or risks. The goal is to provide a stable and actionable review that avoids false positives when blocking a release.

When to use it

  • Validating a new release candidate before production deployment.
  • Inspecting changes between the previous released version and the latest commit on origin/main.
  • Identifying potential breaking changes, regressions, or security vulnerabilities introduced in the new release.
  • Ensuring that all necessary checks are completed before approving a release for shipment.

Key capabilities

  • Fetches remote tags to identify the BASE_TAG (previous release).
  • Compares code changes between BASE_TAG and TARGET commit using git diff and git log.
  • Analyzes changes for breaking changes, regressions, data loss, or security impacts.
  • Provides a deterministic gate policy: GREEN LIGHT TO SHIP unless specific blocking triggers are met.
  • Requires concrete evidence and actionable steps to issue a BLOCKED call.

Example prompts

  • "Run the final release review on the latest commit."
  • "Perform a final release check comparing tag v1.0.0 with origin/main."
  • "Review changes between the previous release and the current version, focusing on potential security risks."

Tips & gotchas

  • Ensure the repository is at the root directory: path-to-workspace/openai-agents-python.
  • The skill assumes that the target commit (origin/main) has already passed code change verification in CI.
  • Avoid issuing a BLOCKED call without concrete evidence and clear unblock actions; prioritize GREEN LIGHT TO SHIP with targeted validation follow-ups when evidence is incomplete.