ai-feature-eval-harness
97 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
Design an eval plan for a product AI feature: success criteria, a held-out labeled dataset, per-criterion grading (code-based, then LLM-based), and a pass threshold. Use when a task ships or changes a feature with non-deterministic model output (classification, extraction, summarization, ranking, agent action) needing a repeatable dataset eval, not only example tests. Do not use for non-model features (use test-strategy), Fhorja's own command outputs (use verify-against-rubric), or with no task…
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'ai-feature-eval-harness' ] || [ -L ~/.agents/skills/'ai-feature-eval-harness' ]; then echo 'A skill folder named ai-feature-eval-harness already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Mozurok/fhorja.dev' "$d" && git -C "$d" checkout --quiet '1abe596aff3cd974459118b57ecd631a69ea34f0' -- '.claude/skills/ai-feature-eval-harness' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/ai-feature-eval-harness' ~/.agents/skills/'ai-feature-eval-harness' && 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/'ai-feature-eval-harness' ~/.claude/skills/'ai-feature-eval-harness' (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/Mozurok/fhorja.dev/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-08 | 1abe596 | 97 |