Use when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill evidence-gate --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Evidence Gate?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-evidence-gate)More formats (shields.io, HTML) on the badges page.
---
name: evidence-gate
description: Use when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.
---
# Evidence Gate
## Core principle
Unknown remains unknown until observed; assertiveness never permits fabricated certainty.
## Procedure
1. Freeze work that depends on the claim.
2. Classify it as fact, inference, assumption, or unknown.
3. Name the cheapest authoritative source.
4. Search and read the smallest relevant evidence.
5. Record path, output, result, and freshness.
6. Proceed with proof or state Not confirmed and remove the dependency.
## Required output
Claim classification, evidence source, finding, and permitted next action.
## Limits
After 3 equivalent searches change evidence source or stop.
## Common mistakes
Do not treat conventions, stale memory, or plausible architecture as repository facts.
## Stop condition
Stop when the claim is proven, safely bounded as inference, or excluded as unconfirmed.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.