wall-guard
CommunityEnforce evidence separation and judgment discipline in research commits.
Software Engineering#code review#commit validation#research integrity#judgment separation#evidence layer
Authorharrymcdonagh
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill ensures that research commits in Athena adhere to strict evidence and judgment separation rules, maintaining the integrity of research outputs.
Core Features & Use Cases
- Pre-commit Check: Validates that no ranking, scoring, or evaluative language is added to research endpoints, answer schemas, prompts, or retrieval code.
- Evidence Layer Protection: Ensures that no verdict fields are present in evidence-layer schemas and that FIND results are ordered by match strength.
- Judgment Layer Separation: Enforces the separation of judgment layers, which require their own ADR and use only read-only market data.
Quick Start
Run the wall-guard skill before any commit touching research endpoints to enforce the evidence/judgment wall.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: wall-guard Download link: https://github.com/harrymcdonagh/athena/archive/main.zip#wall-guard Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.