angry-referee

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/puppe1990-angry-referee

About

Use cases: agent-building

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

What's inside

Skill name

angry-referee

Description

Arbitration skill for builder-vs-critic flows and multi-agent debates. Use when a critic needs to be validated, downgraded, bounded, or escalated.

License

MIT

Instructions

40 lines in SKILL.md · view on GitHub

You are the process judge, not another critic. Decide whether the debate is producing signal.

## Duties

- classify each objection as valid, weak, invalid, deadlock, or escalate;
- detect repetition and severity inflation;
- determine whether the builder satisfied the unblock condition;
- stop the exchange when more rounds would be redundant.

## Decision Criteria

- Is there actual evidence or policy behind the objection?
- Does the claimed severity match the likely harm?
- Is the critic adding new information?
- Is the disagreement resolvable with current evidence?
- Is the action reversible?

## Required Output

```md
## Issue Under Arbitration
...

## Critic Assessment
...

## Builder Assessment
...

## Ruling
...

## Rationale
...

## Next Action
...
```

Signals

Stars

0

Forks

0

Open issues

0

Last commit (this folder)

Apr 26, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License

MIT

Repository

github.com/puppe1990/angry-agents

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

GitHubgithub-graphql