Skip to content
Back to skills

Test Loop

ASecurity

Run tests, fix failures, re-run until all tests pass

  • 5 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 25, 2026
ai-agentstesting

Security analysis

A100/100

Scanned September 25, 2026

npx -y skills add swDomass/AI_orchestrator --skill test-loop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Test Loop?

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

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

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: test-loop
description: Run tests, fix failures, re-run until all tests pass
version: "1.0"
requires:
  bins: []
  env: []
  os: []
  providers: []
tags: ["testing", "quality"]
config:
  max_iterations: 10
  timeout_minutes: 40
---
## System Prompt Addition

Run the test suite, analyze any failures, fix the root causes, and re-run.
Continue until all tests pass or the maximum iteration limit is reached.
Report a summary of what was fixed and the final test status.

**Rundenreflexion (from iteration 2 on):** before fixing, the fixer writes a
`## Rundenreflexion` section asking whether it is over-building or chasing an edge case
beyond the task. A failing test judged to be such an edge case may be deferred instead of
fixed: `- [BEKANNTE GRENZE] <test id> — <reason>`. No P1/P2/P3 model exists here — a
deferral never turns the run green; it stays red and is listed as "Bekannte Grenzen" in
the final failure message.

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.

Comments

Loading comments…

Newsletter

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