「adversarial review」の検索結果

This skill should be used when the user wants to "stress-test a design", "challenge an idea", "red team a proposal", "get critical feedback on a design", "validate a design", "adversarial architecture review", "risk assessment", "設計を検証して", "反論をもらいたい", "設計を批判的にレビュー", "デビルズアドボケート", "ストレステスト", "弱点を指摘して", "穴を見つけて", "この設計で良いか", "リスク評価", "設計のアーキテクチャレビュー", or mentions structured adversarial review of a proposal or design. NOTE: Use this for validating PROPOSALS and DESIGNS through adversarial debate, NOT for generic code review, PR review, or normal review requests (use /codex:review or /codex:adversarial-review for those). Also NOT for investigating unknown bugs (use /agent-dialectics:strong-inference for that).

Run an adversarial two-phase code review of a change with TWO independent reviewers — Claude and Codex — who review alone, then cross-examine each other's findings, then Claude synthesizes a single weighted verdict. Use when the user says "/adversarial-review", "adversarial review", "review this with Codex", "get Codex to review", "two-reviewer review", "cross-examine this PR", or wants a second independent model to grade a change before merge.

日本語の概要は準備中です。原文の説明を表示しています。

N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.

日本語の概要は準備中です。原文の説明を表示しています。

Multi-pass structural code review with adversarial analysis, scope-aware dispatch, adversarial persona passes, and forced-finding protocol. Supports input modes: branch diff (default), PR number (#123), commit hash, pending changes (--pending). Use when asked to "review this PR", "code review", "pre-landing review", "check my diff", or "review #123". Proactively suggest when the user is about to merge or land code changes. NOT for behavioral verification against a running build (see mk:evaluate); NOT for post-implementation simplification (see mk:simplify).

日本語の概要は準備中です。原文の説明を表示しています。

Use when reviewing PRs/diffs/branches/documents for .NET quality, correctness, performance, security, data access, messaging, and observability. Includes adversarial critical-thinking mode for skeptical/cynical review requests. Keywords: code review, review PR, review diff, critical review, cynical review, adversarial review, production readiness, low GC, AOT, security review.

日本語の概要は準備中です。原文の説明を表示しています。

codex exec review を基本に、必要なら codex exec を使ってコード変更のレビューを依頼し、指摘事項を報告する。通常 / 厳しめ (--strict) / 敵対的 (--adversarial、実装を壊しにいく red team) の 3 モードを持つ。「codexでレビューして」「codex-review」「/codex-review」「敵対的にレビューして」で発火。Codex 単体での単独レビュー用途。複数エージェント並行レビューは cross-review、差分ではなくコードベース全体の監査は audit を使う。

Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode (common): the user describes a change in Chinese or English and the manuscript (LaTeX or Markdown) is edited directly through a CS-venue writing toolkit with author sign-off (use for 改这段 / 把中文想法写成 latex / polish / de-AI / translate / compress a passage). REVIEW mode (occasional, pre-submission): harden the paper through an adversarial courtroom review engine (N holistic domain reviewers / contestability routing / two-sided trial / three-way verdict / clerk-converged multi-round loop) with consensus-gated, author-signed revisions (use for review / critique / 审稿 / 评审 / mock-review). AUTO mode (unattended, opt-in via /goal): run the review-revise loop toward a verifiable goal, applying safe fixes under a drift-bounded policy and queueing risky ones. Resolves all inputs at runtime, no hardcoded paths. Not a from-scratch drafter (use ml-paper-writing) and not an official-venue rebuttal.

日本語の概要は準備中です。原文の説明を表示しています。

Multi-agent adversarial code review. Spawns three reviewer subagents (Auditor, Adversary, Pragmatist) on a single model, runs a cross-examination round, then deterministically synthesizes a single ranked report. Use this for non-trivial PRs, security-sensitive changes, refactors that touch many files, or any change where one perspective has obvious blind spots. Trigger phrases include "adverse review", "adversarial review", "multi-perspective review", "review my changes from multiple angles", "panel review". NOT suitable for trivial diffs (typos, dependency bumps, formatting).

日本語の概要は準備中です。原文の説明を表示しています。

Adversarial, security-first review of a pull request from an EXTERNAL or untrusted contributor — a fork PR, a first-time or unknown author, anyone without write access — before a maintainer merges it. Use this whenever you're reviewing, triaging, or deciding whether to merge a PR opened against tbh-meter by someone outside the maintainer team: 'review PR #123', 'someone opened a PR — is it safe to merge?', 'check this contributor's changes', 'can we take this fork PR?', 'is this contribution legit?'. This is supply-chain DEFENSE, not ordinary code review: every merged PR auto-updates onto every user's machine and ships a memory-reading .exe plus an unsandboxed Electron app, so the author and the PR description are UNTRUSTED and the diff is the only evidence. It posts its verdict as a real GitHub review — an inline comment pinned to each problematic line (via the pulls/reviews API), not just one summary comment. NOT for your own or a fellow maintainer's branch (use self-review for that), and prefer this over the generic review flow for anything coming from outside the team.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user asks for a multi-agent .NET code review - five parallel reviewers (correctness, performance, security/observability, data/messaging/integration, generalist) plus an adversarial maintainer that refutes weak findings. Requires the review agent roles registered by scripts/install-codex.sh. Keywords: dotnet review pipeline, multi-agent review, parallel reviewers, maintainer pushback, review this branch, cynical review.

日本語の概要は準備中です。原文の説明を表示しています。

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.

日本語の概要は準備中です。原文の説明を表示しています。

Adversarial dual-model code review that runs two AI models in parallel, cross-references findings, and produces a consensus severity table with fix confidence ratings. Use when asked for a thorough code review, adversarial review, dual-model review, confidence-rated review, or 'Hanselman review'.

日本語の概要は準備中です。原文の説明を表示しています。

Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit skill:bmad-review directive from another skill counts as that ask. A request to act on feedback from an earlier review is a change, not a review. Never invoke this uninvited, including on edits you just made.

日本語の概要は準備中です。原文の説明を表示しています。

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

日本語の概要は準備中です。原文の説明を表示しています。

Review of a PR, branch, or your own uncommitted work across eight dimensions — security, correctness, test coverage, API/compatibility, usability, documentation, code quality, performance. Sizes the diff, reviews inline or fans out reviewers off a shared brief, verifies findings against code, reports a grouped list with a shape verdict, fixes on approval. Use for "review this PR", "/pr-review 3011", or a pre-flight self-review before submitting; add "thorough" for adversarial verification.

日本語の概要は準備中です。原文の説明を表示しています。

Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit skill:bmad-review directive from another skill counts as that ask. A request to act on feedback from an earlier review is a change, not a review. Never invoke this uninvited, including on edits you just made.

日本語の概要は準備中です。原文の説明を表示しています。

Use when adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, statistical analyses, benchmark reports, whitepapers. Inventories every equation and quantitative claim, verifies each AS NAMED in the text (never a paraphrase or a neighboring statement), and classifies VERIFIED / REFUTED / UNVERIFIABLE / VACUOUS. Triggers on "check this paper", "verify these claims", "is this derivation right", "review this proof", "audit this benchmark", "does the math hold up". For source-code review see code-review-and-quality; for skill/agent library audits see skill-library-review; for content quality scoring see content-ops.

日本語の概要は準備中です。原文の説明を表示しています。

Use when recording, tallying, or triaging stochastic review findings — the append-only JSONL ledger where Tier 2 (advisory, unevidenced) reviewer output goes instead of blocking language. Triggers on "log this finding", "ledger add", "tally the findings", "triage findings", "is this finding recurring", "retire this noise", or whenever a reviewer produces an unevidenced concern that should be measured for recurrence rather than chased. For the review itself see code-review-and-quality or skill-library-review; for verifying formal claims with deterministic evidence see adversarial-claims-reviewer.

日本語の概要は準備中です。原文の説明を表示しています。

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

日本語の概要は準備中です。原文の説明を表示しています。

公開前の文章やコードを二つの独立したエージェントが同じ基準で審査し、両方の合格まで修正と再審査を繰り返し、上限を超えたら人へ判断を引き継ぐスキル。

• 公開前に文章の事実関係を確認したいとき
• 顧客向け文章とブランドルールの照合
• 本番配布前に独立した審査を加えたいとき

[omh] Technical proposal facing adversarial scrutiny: independent perspectives attack a proposal, then distill into a bundle a separate planner consumes. Use when the user says: adversarial-consensus, adversarial planning, adversarial plan review, red team this plan, red-team this plan, red team the proposal, multi-perspective review, multiple perspectives.

日本語の概要は準備中です。原文の説明を表示しています。

SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-model sanity check before implementation. Builds on Matt Pocock's grill-me (MIT). For the docs-aware variant use /grill-with-docs-codex; if you already have a plan and want only the Codex review use /codex-review. NOT for reviewing already-written code (use /codex:review) and NOT for trivial changes.

日本語の概要は準備中です。原文の説明を表示しています。

Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "adversarial review", "second opinion review", "用codex", "让gpt实现", "对抗式审查", "让codex审查计划", "第二意见". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code or plan reviews via codex, get a second-opinion review from a different model, or execute tasks in a sandboxed environment.

日本語の概要は準備中です。原文の説明を表示しています。

Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go / no-go gate. Triggers before building anything high-blast-radius, when the user says "review the spec", "red-team this", "is this plan sound", "senior review", or invokes /ck:review.

日本語の概要は準備中です。原文の説明を表示しています。