← All skills

evals-analyze

100 / 100 · Low risk

Fine to try.

By tikalk/adlc-team-skills (GitHub) · coding · 145 stars · scanned at commit e9ac38d

Use when evaluation results need triage and loop-closing — spec failures route to deterministic checks or context rules, generalization failures to the evaluator backlog.

Works with any agent that supports SKILL.md skills.

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/'evals-analyze' ] || [ -L ~/.agents/skills/'evals-analyze' ]; then echo 'A skill folder named evals-analyze already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/tikalk/adlc-team-skills' "$d" && git -C "$d" checkout --quiet 'e9ac38d53de9f7e2967728d8465e95d54921f427' -- 'skills/evals/evals-analyze' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/evals/evals-analyze' ~/.agents/skills/'evals-analyze' && 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/'evals-analyze' ~/.claude/skills/'evals-analyze' (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

The badge for tikalk/adlc-team-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/tikalk/adlc-team-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/tikalk/adlc-team-skills/)

Score history