「adversarial」の検索結果

Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.

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 code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"

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 an implementation against its plan with a hostile peer agent, debate findings to consensus, and drive fix waves until the auditor runs dry. Use when a done-claim needs verification the implementer cannot game ("hostile review", "adversarial audit", "is this PR faithful", "find the escape hatches") — the loop that beats the laziness bias with its own game theory.

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 at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

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。

Go-based security techniques from "Black Hat Go" extended with macOS, Cloud, Mobile, IoT, Supply Chain, API, Web3, AI/ML, Red Team, ATT&CK, and LLM chapters. 186 techniques, 36 tools, 33 defenses across 37 chapters. Includes adversarial bisimulation games with Ungar (order-dependent) and join-semilattice structures. AAIF-compatible multiplayer agent games for human-agent security exercises.

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。

MLX↔JAX bidirectional beacon-repeater with spectral gap random walk, justfile orchestration, catp flow validation, and adversarial malleability for life pattern resurrection.

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 malleability analysis of Aqua Voice Electron app with IPC injection, WebSocket interception, and braided monoidal skill interleaving

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 what to do next, asks for a plan under uncertainty, challenges stalled or low-trust work, requests multiple possible approaches before action, or needs an evidence-first loop that uses RT-ICA-style prerequisite checks, adversarial review, subagent coordination, real validation, and durable concern tracking.

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 verification with convergence loop. Two independent review agents must both pass before output ships.

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。

Drafts a referee report for a journal editor. Produces a recommendation, claim-and-design summary, three to six decision-driving concerns, additional concerns, and a revision plan through five parallel adversarial finders, Breaker, Butcher, Shredder, Void, Situator, a Blue Team error filter, Chief Reviewer synthesis, Tone Guard legal pass, and optional confidential editor note. Use when the user has been asked to referee a manuscript. Self-audits go to paper-review-lite or presubmit, and author responses go to referee-response.

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。

Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 30-plus stages, including Red Team finders, Blue Team defence, verification cascade, legal pass, and copyedit, producing one consolidated report on disk. Verifies installation and API key, chooses the output location and smoke, standard, or custom mode, launches the run, and reports the result path. Use when the user asks to run presubmit, wants a deep unattended pre-submission audit, or needs a math or replication-code audit. Everyday self-audits go to paper-review-lite, and external refereeing to journal-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。

Provides a pre-submission manuscript audit covering argument, numerical consistency, references and DOIs, writing, figures, CONSORT flow, pre-registration, and the replication archive. Use before paper submission or when a draft needs an adversarial, quote-grounded review with a journal-readiness checklist. Add `--codex` to run the specification independently on Claude and Codex, GPT-6 Astra, and cross-check findings.

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。

Draft a referee report on someone else's manuscript for a journal editor, using five adversarial finders, a Blue Team error filter, a Chief Reviewer synthesis, and a Tone Guard legal pass. Use when the user has been asked to referee a manuscript; self-audits go to paper-review-lite or presubmit, author responses to referee-response.

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。

Advanced multi-agent reasoning system for complex questions requiring maximum accuracy. Uses adaptive technique selection, adversarial validation, multi-agent debate, and deep analysis. Trigger phrases "ai board", "expert panel", "deep analysis", "maximum accuracy", "thorough reasoning". Use for critical medical decisions, theological questions, philosophical analysis, complex technical problems, high-stakes decisions, or any question requiring 95%+ confidence.

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-provider deliberation panel for COMPLEX, multi-view questions — architecture, strategy, market research, and codebase sweeps. Runs a 4-stage deliberation across the provider fleet (diverge → contrarian red-team → adversarial verify → cited synthesis), the same multi-perspective rigour the plan-gate already applies to plan reviews, generalised to arbitrary questions. Use when one model's answer isn't enough and you want convergence THROUGH disagreement + verification, not a single opinion.

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。

Senior engineer conducting thorough, constructive code reviews. Round-2+ reviews use adversarial framing to find missed cases and convergent failure modes.

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。

Skeptical analysis and critique of claims, plans, and code without taking anyone at face value. Use when the user says "don't trust me", wants adversarial review, red-teaming, assumption checking, or verification that generated or proposed code is actually correct. Triggers on skepticism, critique everything, verify claims, challenge assumptions, red team, devil's advocate, prove it, smell test.

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 real user interviews aren't possible (solo/hobby/dogfood projects) but persona work is still needed. Enforces epistemic discipline: adversarial spectrum, pre-committed stop conditions, speculation tagging. NOT a substitute for /mycelium:user-interview when real users are available.

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。

ALIGN-video for Claude Code with independent Codex adversarial review. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.

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。

Maps a startup's competitive landscape, scores moat strength across 6+ dimensions, and writes an investor-ready competition narrative with a positioning map. Use when the user asks for a competitive landscape, moat analysis, or positioning review and gives enough to work from: a deck, a list of competitors, or a clearly named startup. A full run takes about 30–40 minutes and searches the web, so for a passing question such as 'who are my competitors?' or 'is that a real moat?', answer briefly in chat and offer the analysis instead of starting it. When it runs, the competitor set and moat scores are checked adversarially, never recalled from memory.

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。

Perform an adversarial review of the current uncommitted changeset, validating it against project contracts and architectural intent.

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。

Scaffold and run Karpathy-style autoresearch loops in any git repo. This skill should be used when setting up autonomous code improvement, generating adversarial eval harnesses, running hypothesis-implement-eval-keep/discard loops, or checking autoresearch progress. Triggers on "autoresearch", "autonomous improvement", "eval loop", "hypothesis loop", "self-improvement loop".

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 a read-only adversarial Kimi challenge review that questions assumptions, design choices, and tradeoffs. Use when the user wants pushback on whether the approach is right, not a defect-only 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。