harsh-critic
100 / 100 · Low risk
Fine to try.
Adversarial review of a solution, plan, architecture, PR or piece of code — a severity-ranked list of concrete, evidence-backed failures with exact file:line, never vague concerns and never praise. Use when asked to critique, tear apart, poke holes in, stress-test, red-team or find everything wrong with something, and before merging anything whose failure would be expensive. Always dispatches the critique to a fresh sub-agent, then verifies its claims independently.
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/'harsh-critic' ] || [ -L ~/.agents/skills/'harsh-critic' ]; then echo 'A skill folder named harsh-critic already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/vibegameengine/web-starter-kit' "$d" && git -C "$d" checkout --quiet '846b119f62f55ff8557651f180b624f053ad4c85' -- 'agents/skills/harsh-critic' && mkdir -p ~/.agents/skills && cp -R "$d"/'agents/skills/harsh-critic' ~/.agents/skills/'harsh-critic' && 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/'harsh-critic' ~/.claude/skills/'harsh-critic' (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/vibegameengine/web-starter-kit/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 846b119 | 100 |