second-opinion
FeaturedRuns external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.
Install
Quality Score: 93/100
Skill Content
Details
- Author
- trailofbits
- Repository
- trailofbits/skills
- Created
- 10 months ago
- Last Updated
- 6 days ago
- Language
- Python
- License
- CC-BY-SA-4.0
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
second-opinion
Get a second opinion from OpenAI's Codex CLI. Default model is gpt-5.5. Three modes: review (pass/fail code review on the current diff), challenge (adversarial pass — try to break it), consult (multi-turn Q&A with session persistence). Uses ChatGPT subscription auth, not an API key. Use when asked for "second opinion", "codex review", "adversarial review", "challenge this code", "cross-model review", or "/second-opinion".
second-opinion
Cross-check the current work against an independent model (Codex/GPT) as an ADVERSARIAL reviewer — it tries to break the work, not co-sign it. Use for 'second opinion', 'cross-check this', 'what would codex say', 'have another model review this', or before shipping something high-stakes/irreversible. NOT for routine diffs.
second-opinion
Get an independent second opinion from the Codex CLI (OpenAI GPT-5.x) on a plan, prompt, design, code change, or any piece of work — then run a structured debate/relay between Claude and Codex until they converge, and synthesize a joint recommendation. Codex shares Claude's skills (via ~/.agents/skills) so it can ground its critique in the same playbooks (e.g. seedance-2-prompt-engineer). Use when the user says "second opinion", "ask codex", "what does codex think", "run it by codex", "debate this with codex", "sanity check with gpt", or "/second-opinion".