aeon-skill-evals
100 / 100 · Low risk
Fine to try.
Validate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL). Bootstrap mode generates a starter manifest from a skill's recent successful runs so manifests aren't written speculatively. Triggers: "evaluate this skill's output", "check skill X for regressions", "bootstrap evals for Y", "did this skill outp…
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/'aeon-skill-evals' ] || [ -L ~/.agents/skills/'aeon-skill-evals' ]; then echo 'A skill folder named aeon-skill-evals already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/cyotee/indexedex' "$d" && git -C "$d" checkout --quiet '90ff0307a7a8e084aa073e02eff125e9c7973933' -- 'lib/bankr-skills/aeon-skill-evals' && mkdir -p ~/.agents/skills && cp -R "$d"/'lib/bankr-skills/aeon-skill-evals' ~/.agents/skills/'aeon-skill-evals' && 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/'aeon-skill-evals' ~/.claude/skills/'aeon-skill-evals' (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/cyotee/indexedex/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-09 | 90ff030 | 100 |
Also found in
- BankrBot/skills/aeon-skill-evals