Diagnosis · Code

unit-test

Name: unit-test
Author: oprogramadorreal

Improves unit test coverage on demand — discovers testing gaps via a reconnaissance agent and writes new tests that follow project…

by oprogramadorrealgithub.com/oprogramadorreal/optimus-claude ↗Source ↗MIT73 repo stars

Examining code for the line that is wrong

Add it to your AI

View source

Works with

ClaudeChatGPTGeminiClaude CodeCodexCursorCopilotGemini CLI

Setup

Upload one file

About a minute in Claude. One command in coding tools.

Contains

Instructions only

Text files — no scripts or programs.

Maintained

Last change 28 Sept 2026

On the repository’s main branch.

Check

Nothing found by our check

What it does

Improve unit test coverage for existing code. An optional path argument scopes the run.

What it can touch

No script files in its folder
Its folder holds text, not programs. It changes how your AI works; it does not bring code of its own.
How we know
Listed the 4 files in the skill’s folder on GitHub; none is a script or program.
No known risk pattern found
Launch7’s automated check read all 4 text files in this skill and matched none of its risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit db331ab by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to oprogramadorreal/optimus-claude: 2026-09-28 (7 days before the scan).

Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check

Add it to your AI

Supported. Upload it once in Claude’s settings. Works on every plan, including Free.

Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.

How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end

Where it comes from

Publisher: oprogramadorreal
Found on: GitHub
Licence: MIT
Source dated: 20 Aug 2026
Repo stars: 73

Stars count the whole repository, which holds 8 other listings here.

Why it is listedNothing reaches this catalogue from GitHub unless three things hold at once: the source is a genuine first-hand publication rather than a copy, its licence clearly permits redistribution, and it scores at least 8.0 on the quality model. That says where it came from and how complete it looks — not what it does. What Launch7's own check found in its files is under “What it can touch”. Launch7 has not installed or run it.

Other skills for this task

code-testing-agent
Generate or add unit tests for existing code, from one function to a complete project-wide suite.
From MicrosoftInstructions only
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
mattpocockIts code sends data over the internet
automating-api-testing
Test automate API endpoint testing including request generation, validation, and comprehensive test coverage for REST and GraphQL APIs.
jeremylongshoreIncludes 2 scripts
test-suite-architect
Establish world-class QA testing processes for any software project using proven methodologies from Google Testing Standards and OWASP security best practices.
zebbernIncludes 2 scripts
subagent-testing
Test skills via TDD in fresh subagents.
atholaRuns terminal commands

All skills for “Write tests that catch real bugs” →

What it does

What it can touch

Add it to your AI

More from oprogramadorreal