review-adversarial
100 / 100 · Low risk
Fine to try.
Try to break a change with independent fresh-context reviewers who see only primary sources, attack the properties the work promised, prove findings with failing tests in isolated worktrees, and report unfiltered. Use before merging a change you or this agent wrote, or whenever a review must not inherit the author's framing.
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/'review-adversarial' ] || [ -L ~/.agents/skills/'review-adversarial' ]; then echo 'A skill folder named review-adversarial already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ooloth/dotfiles' "$d" && git -C "$d" checkout --quiet 'fde628742507827aa97bd7909486b72f7456c17e' -- 'tools/agents/config/skills/review-adversarial' && mkdir -p ~/.agents/skills && cp -R "$d"/'tools/agents/config/skills/review-adversarial' ~/.agents/skills/'review-adversarial' && 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/'review-adversarial' ~/.claude/skills/'review-adversarial' (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/ooloth/dotfiles/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | fde6287 | 100 |
| 2026-11-09 | 0588285 | 100 |