constitutional-reasoning

SKILLWorkflowcommunity
v0.0.0Sandeeprdy1729Apache-2.0Updated 1mo agoSource →

Self-critique and Constitutional AI reasoning skill. Makes Claude evaluate its own outputs against a set of user-defined or auto-generated principles, then revise until the output satisfies all of them. Reduces hallucination, over-confidence, and sycophancy by forcing Claude to argue against its own

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
3Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorSandeeprdy1729
Version0.0.0
LicenseApache-2.0
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Self-critique and Constitutional AI reasoning skill. Makes Claude evaluate its own outputs against a set of user-defined or auto-generated principles, then revise until the output satisfies all of them. Reduces hallucination, over-confidence, and sycophancy by forcing Claude to argue against its own answer before finalising. Generates a principle set from the user's domain, runs critique passes, s

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.