dialectic

SKILLWorkflowcommunity
v0.0.0beingcognitiveMITUpdated 2mo agoSource →

Harden a plan/design/algorithm/decision via a thesis→antithesis→synthesis loop: each round, two independent reviewers (a different model + a freshly-spawned subagent) critique the current draft; fold in only findings the draft doesn't already resolve, adjudicating reviewer disagreements by evidence;

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
1Clients
1Formats
2mo agoLast update
Skill
Authorbeingcognitive
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Harden a plan/design/algorithm/decision via a thesis→antithesis→synthesis loop: each round, two independent reviewers (a different model + a freshly-spawned subagent) critique the current draft; fold in only findings the draft doesn't already resolve, adjudicating reviewer disagreements by evidence; stop after two consecutive clean rounds (cap 10, usually 3–5). Independence is the engine — a diffe

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.