codex-strategy-reviewlisted

Run an independent Codex adversarial strategy and logic review using GPT-5.6 with xhigh reasoning. Generic by default; flexible for optional persona lenses resolved from the persona registry. Use for strategy docs, research conclusions, optimizer proposals, risk frameworks, decision memos, or arguments that need stress-testing.
dgrissen2/persona-review-kit · ★ 0 · Code & Development · score 67

Install: claude install-skill dgrissen2/persona-review-kit

# Codex Strategy Review Independent adversarial logic review using Codex (`gpt-5.6`, `model_reasoning_effort=xhigh`). This skill is generic by default and flexible for different personas. > Requires the `codex` CLI (`npm install -g @openai/codex`, then `codex login`). > Persona listing/resolution works without it. ## Focus Use this to stress-test a strategy, argument, proposal, research conclusion, risk framework, optimizer design, decision memo, or any other plan where the question is "does this logic hold up?" The generic review checks: - conclusions that do not follow from premises - hidden, circular, fragile, or unstated assumptions - made-up thresholds, constants, weights, or scoring rules - missing evidence, counterexamples, and falsification tests - incorrect math, units, base rates, or time horizons - feasibility, incentives, adoption, and operational constraints - downside, tail risks, failure modes, monitoring, and reversibility - contradictions between goals, constraints, and proposed mechanisms ## Personas Personas are optional lenses, not a fixed enum. Decide which to use up front when the review is initiated. Example lenses: `architect`, `cto`, `red-team`, `quant`, `portfolio-manager` — or pass a direct path to a persona `.md` file. Run without personas for a generic review; pass `--personas a,b,/path/to/persona.md` for a panel. List what's available via the shared resolver (works even without Codex): ```bash python3 ~/.claude/skills/persona-registry/