Skip to content

slior/dialectic

v0.2.0MIT

Configuration-first multi-agent design debate. Agents with different roles (architect, security, performance, simplicity, ...) run structured debate rounds and a judge decides when convergence is reached.

judge

Evaluates convergence across agent refinements and, when the debate ends, writes the final synthesized solution. Operates in two modes: convergence_check (per-round verdict) and synthesis (final output). Use when the orchestrator needs a convergence verdict or a final synthesis document.

Compatibility
Requires the prompt payload that ships beside this skill (prompts/shared/, prompts/generalist/), which the skill resolves from its own location; pass PROJECT=<plugin root> on clients that do not expose a skill's own path. Needs no subagent dispatch of its own: it only reads and writes files, and is usually run as a subagent dispatched by the orchestrate skill.
Read SKILL.md at the source

Pinned to revision 3d89241e847a, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.