ratchet:debate

Inspect and continue Ratchet debates from stored .ratchet/debris round files and metadata.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/netbrain/ratchet --skill ratchet-debate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ratchet:debate
Source: https://github.com/netbrain/ratchet/tree/main/skills/debate
Command: npx skills add https://github.com/netbrain/ratchet --skill ratchet-debate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a safe, auditable way to inspect and continue paired-agent debates stored in a project's .ratchet directory, addressing the need to read full transcripts, recover corrupted state, and resume or conclude escalated debates without manual file surgery.

Core Features & Use Cases

  • List debates and statuses: Enumerate debates by reading .ratchet/debates/*/meta.json and present concise choices to the user.
  • Full transcript viewing: Aggregate meta.json and per-round generative/adversarial round files to present a readable transcript with verdict and metadata.
  • Recovery and resilience: Attempt to regenerate malformed meta.json from existing round files, surface recovery notes, and guide user decisions.
  • Controlled continuation: Resume debates only when allowed (initiated/escalated), enforce agent tool boundaries, increment max_rounds or reset rounds, and update meta.json for abandon or verdict actions.
  • Use case: A maintainer investigating why an automated debate stalled can inspect transcripts, regenerate corrupted metadata from round files, and safely run another round or render a human verdict.

Quick Start

Run /ratchet:debate to list debates, select an ID to view its full transcript, or add --continue to resume an eligible debate.

Frequently Asked Questions about ratchet:debate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I view a full debate transcript stored in my project directory?

To view a debate transcript, run the command to list debates, select an ID, and the tool aggregates meta.json and per-round generative/adversarial files to present a readable transcript with verdict and metadata.

Can I recover a corrupted meta.json file from existing round files in ratchet?

Yes, the tool attempts to regenerate malformed meta.json from existing round files, surfaces recovery notes, and guides user decisions to safely resume or conclude the debate without manual file surgery.

How do I resume an escalated paired-agent debate without breaking role tool boundaries?

You can resume eligible debates by running the continue command, which enforces agent tool boundaries, increments max_rounds or resets rounds, and updates meta.json for abandon or verdict actions.

What is the best way to inspect why an automated debate stalled in the ratchet workflow?

Inspecting stalled automated debates involves reading the full transcript from the .ratchet/debates directory, validating meta.json, and checking per-round generative and adversarial files to identify the failure point.

Do I need ratchet to list and manage paired-agent debate statuses in my project?

Yes, this applies to projects using Ratchet where paired-agent debates generate round files and meta.json for planning, testing, building, reviewing, and hardening workflows stored in the .ratchet/debates directory.

When should I manually abandon a debate instead of running another round?

You should abandon a debate when further automated rounds cannot resolve the issue, using the tool to safely update meta.json with an abandon action and conclude the escalated debate state.