test-loop

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

IndexedMIT★ 5

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/swdomass-test-loop

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

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

Use cases: testing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/test-loop

What's inside

Skill name: test-loop
Description: Run tests, fix failures, re-run until all tests pass
License: MIT
Instructions: 13 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

## 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.

From swDomass/AI_orchestrator, MIT.

Signals

Stars: 5
Forks: 0
Open issues: 0
Last commit (this folder): Sep 11, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/swDomass/AI_orchestrator
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from swDomass

Cite this page

test-loop skill. Agent Mart. https://agentmart.dev/skills/swdomass-test-loop (last updated 2026-10-24)