「adversarial review」の検索結果

コミット/PR の「全部置換した」「-N%削減」等の完了主張を grep で反証できる残骸や best/typical/worst 試算で検証し、抽出・集約リファクタでは並列度(Promise.all)/fast-path/遅延評価の性能特性退行と、Map/Set 集約キーの cross-kind 衝突による検出漏れも監査する

変更に含まれる設計判断・実装選択の論理的整合性を徹底的に検証し、確証バイアスを排除して判断精度を高める

攻撃者・競合・悪意あるユーザーの視点で変更を分析し、防御の盲点と悪用シナリオを可視化する

同一ファイル/隣接ファイル内で「規則Xを守れ」と宣言した直後にXを破っている、宣言と実装の乖離を検出する

モジュール/スキルの構造変更で当該ファイルは更新したが、caller 側が古い構造（旧参照・旧シグネチャ・旧採番）を参照したまま残るパターンを検出する

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

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。

Adversarially verify an implementation against its objective, acceptance criteria, definition of done, and prohibitions using fresh evidence. Use for completion gates, release readiness, or independent verification after implementation and 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。

Deliver a small, bounded code change through inspection, a mini-plan, implementation, testing, review, and adversarial verification. Use for bug fixes, configuration changes, and features expected to touch no more than five files.

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。

Run multiple Reforge-guided section-refactor lanes in parallel, each in its own worktree/branch off origin/main, with a score-blind adversarial review panel gating every commit, one draft PR per section. Use when the user wants to reduce Reforge surface/internal score across several sections at once via architecturally-correct deletions (dead surface, entity-leak removal, cross-section read-splits) — not by relocation, parameter bags, or accessibility-dodging. Wraps the per-lane process in .codex/skills/humans-refactor. Triggers: 'refactor swarm', 'parallel section refactors', 'run reforge refactor on Users/Tickets/...', 'burn down surface score across sections'. Has an intensity dial (light|standard|deep) and a workflow|solo execution mode to trade token burn against autonomy per unit of output.

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。

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.

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。

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

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。

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

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。

Run one bounded adversarial pass when the user explicitly requests a report-style stress test or ROSE identifies a concrete material loophole in an existing strategy, spec, plan, review, or claim; do not trigger for an interactive grill/frontier interview or merely before write-back, implementation, reconciliation, or completion.

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。

Audit a compliance-ladder design (C0-C6) and transcript-fidelity ladder (T0-T5) plus their adapter conformance fixtures — Codex, Claude Code, Cloudflare, Ollama/LM Studio, custom stdio/HTTP agents — for the two failure modes that make a C-badge or T-fidelity label a lie: the ladder disagreeing with itself across doc/schema/ui/probe surfaces, and a level being reachable by self-report because no daemon-witnessed negative probe actually tries to forge it. Use when designing or freezing a compliance ladder, wiring an adapter conformance probe suite, deciding whether a numeric C-badge or T-label is safe to ship, or investigating a self-attestation or observed-to-controlled bypass risk. NOT for auditing a cryptographic protocol or whitepaper for adversarial soundness (`redteam-review`), writing TLA+/formal invariants for a daemon monitor (`runtime-verification-for-agents`), or agent identity, successor linkage, and reputation across restarts (`agent-identity-continuity-reputation`).

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。