joy-check

Community

Prevent grievance framing with evidence-based rewrites.

Authornotque
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Joy-check ensures human-facing and LLM-facing content is framed through curiosity and actionable intent rather than grievance, accusation, or prohibition-heavy instructions.

Core Features & Use Cases

  • Mode-aware framing validation: Detects whether content should be evaluated with the writing rubric or the instruction rubric, then applies the correct scoring rules.
  • Two-stage gating (fast scan + semantic scoring): Runs a regex/grep pre-filter to catch obvious negative framing, then uses rubric-guided semantic analysis to score and flag subtler cases.
  • Actionable reframe suggestions and optional auto-fix: Produces per-paragraph/per-instruction scores and rewrite proposals, and can rewrite flagged items in place with re-verification.

Quick Start

Run joy-check in instruction mode on a newly generated skill file by executing: joy-check --mode instruction path/to/skill/SKILL.md.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: joy-check
Download link: https://github.com/notque/vexjoy-agent/archive/main.zip#joy-check

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.