skill-evaluation-graph — tool profile and history

Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • agent-skills
  • agentic-ai
  • ai-agents
  • ai-evaluation
  • ai-safety
  • antigravity
  • antigravity-skills
  • benchmarking
  • claude-code
  • claude-code-skill
  • codex
  • codex-skill
  • developer-tools
  • developer-tools-ai-agent
  • gemini-cli
  • gemini-cli-skills
  • llm-evaluation
  • prompt-engineering
  • skill-evaluation
  • static-analysis

Install git clone https://github.com/MaxLaurieHutchinson/skill-evaluation-graph ~/.claude/skills/skill-evaluation-graph

Current measurement

2GitHub stars—
estimated momentum

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
2GitHub stars

Classifications

Domains
Type
Agent skills
Use cases