Skip to content
Back to skills

Conduct Test

ASecurity

Delegate writing tests to a free/cheap model, then verify

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentsbashgit

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add KevalParikh22/conductor-ai --skill conduct-test --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Conduct Test?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Conduct Test
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kevalparikh22-conduct-test/badge)](https://www.skillsdirectory.com/skills/kevalparikh22-conduct-test)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: conduct-test
description: "Delegate writing tests to a free/cheap model, then verify"
argument-hint: "<what to test, e.g. \"src/auth/reset.ts edge cases\">"
disable-model-invocation: true
allowed-tools: "Read, Bash(conductor:*), Bash(git status:*), Bash(git diff:*), Bash(git add:*), Bash(git commit:*), Bash(git stash push:*)"
---

You are the controller. Make sure the tree is clean, then run in the background:
`conductor run test "Write tests for: the arguments the user gave" --files <the source files under test>`

Check `conductor diff`: the tests must test real behaviour (not just mocks), follow the existing test style, and must not change production code. If verify passes and the tests are meaningful, commit (`test: ...`). If the worker reports a real bug, tell the user. If the tests are weak, retry once with `--note`, then write them yourself.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.