eval-driven-agent-dev
100 / 100 · Low risk
Fine to try.
Eval-driven agent development — 3-layer evaluation (static benchmarks, custom offline, online production). Evaluator-optimizer tight loop. Evals in CI, score-gated PRs. SWE-bench/GAIA/BFCL V4 for cross-model comparison. Trajectory-based and LLM-as-judge evals. Sources: rohitg00/ai-engineering-from-scratch (Apache-2.0).
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'eval-driven-agent-dev' ] || [ -L ~/.agents/skills/'eval-driven-agent-dev' ]; then echo 'A skill folder named eval-driven-agent-dev already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/yanacuti1121/Yana-AI' "$d" && git -C "$d" checkout --quiet '54d4aa9fa3241319f4d37212bd23826658bf6bed' -- '.claude/skills/eval-driven-agent-dev' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/eval-driven-agent-dev' ~/.agents/skills/'eval-driven-agent-dev' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'eval-driven-agent-dev' ~/.claude/skills/'eval-driven-agent-dev' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/yanacuti1121/Yana-AI/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 54d4aa9 | 100 |
| 2026-11-08 | 4a78f20 | 100 |
Also found in
- yanacuti1121/Yana-AI/core/skills/eval-driven-agent-dev