StackMap
Subscribe

cc-thinking-skills vs council-of-high-intelligence

18 mental models as Claude Code skills — First Principles, Bayesian reasoning, Systems Thinking, OODA, Pre-Mortem and more — invoked when a problem needs a thinking framework. — versus — /council: 18 AI personas deliberate your hardest decisions across multiple LLM providers — structured multi-round disagreement, confidence-weighted verdicts, one slash command.

The curated verdict

Two upgrades for decision quality in Claude Code: Council convenes 18 disagreeing personas across providers; thinking-skills hands one model 18 explicit frameworks. Deliberation breadth vs reasoning discipline.

cc-thinking-skillscouncil-of-high-intelligence
Stars6903.6k
Forks112320
LanguageJavaScriptShell
LicenseMITMIT
Last activity1 months ago2 days ago
Topicsskillsagents, skills
Curated connections12

cc-thinking-skills — the curator's take

Decision frameworks as installable capability: instead of hoping the model reasons well, you hand it the explicit framework the situation calls for — pre-mortem before a launch, Bayesian updating on flaky evidence, OODA under time pressure. Cheap to adopt, zero infrastructure. The honest ceiling: a framework prompt shapes reasoning, it doesn't guarantee it — the model can still pattern-match its way past the discipline; treat the outputs as structured drafts for YOUR judgment.

council-of-high-intelligence — the curator's take

Structured disagreement as a product: 18 personas with genuinely different priors argue your decision across providers (real model diversity, not one model roleplaying), through quick/standard/deep deliberation modes, ending in a confidence-weighted verdict. Its own README has a 'When Not to Use It' section — our kind of project. Best for irreversible, ambiguous calls where you'd otherwise ask three friends. NOT for anything with a checkable answer (deliberation theater costs real tokens), and a council is still only as wise as its training data — it widens perspective, it doesn't add ground truth.