Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Multi-AI second opinion via OpenAI Codex CLI. Three modes: Review (pass/fail gate), Challenge (adversarial edge-case finder), Consult (freeform with session continuity). Read-only with streaming output and thinking traces. Cross-model analysis when review has already run.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 141% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -53% | 0% |
name: codex description: > Multi-AI second opinion via OpenAI Codex CLI. Three modes: Review (pass/fail gate), Challenge (adversarial edge-case finder), Consult (freeform with session continuity). Read-only with streaming output and thinking traces. Cross-model analysis when review has already run. metadata: sources:
repo: garrytan/gstack path: codex/SKILL.md commit: f4bbfaa5bdfd2d6ce59541c2145432febde57fed attribution: Garry Tan license: MIT usage: referenced
Other measured skills in the registry, with their headline benchmark lift.