Skip to content
TrustedSkillsbeta
Back to all skills

Test Coverage Improver

Official
openai·vlatest·testing·MIT

Analyzes code & suggests targeted tests to maximize test coverage and identify potential vulnerabilities.

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 test-coverage-improver -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/test-coverage-improver/SKILL.md
Scanned
2 files, 30 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

test-coverage-improver

What it does

This skill automatically analyzes your codebase to identify untested areas and generates new test cases to increase coverage metrics. It specifically targets functions, methods, and logic paths that currently lack verification.

When to use it

  • Before merging a large feature branch to ensure new logic is validated.
  • To quickly raise test coverage percentages on legacy codebases with minimal manual effort.
  • When preparing for a security audit or compliance requirement mandating high coverage thresholds.
  • During refactoring sessions to guarantee existing functionality remains covered after changes.

Key capabilities

  • Scans the entire project structure to map out untested functions and branches.
  • Generates syntactically correct test code tailored to your specific language and framework.
  • Focuses on edge cases and boundary conditions often missed by manual testing.
  • Integrates directly with existing testing workflows via the OpenAI Agents Python library.

Example prompts

  • "Analyze my src/utils directory and generate unit tests for any function currently missing coverage."
  • "Identify critical business logic paths in my API endpoints that have zero test coverage and write tests for them."
  • "Review my recent commit and create a comprehensive test suite to cover all new code paths introduced."

Tips & gotchas

Ensure your project has a compatible testing framework (like Jest, PyTest, or Mocha) installed before running the agent, as it will generate code specific to those tools. While the skill excels at generating syntax-correct tests, you should still manually review generated cases to ensure they align with your specific business logic and error handling expectations.