「adversarial」の検索結果

Designs the contract for an API change inside one codebase — a component's props, a function surface, URL or query parameters, an event payload, or a module boundary — through a discovery pass, an options document with one recommendation, a question round, and an adversarial validation round, with every element of the contract justified from one stated goal. Use when you want to design, shape, decide, or nail down an interface, contract, signature, or API change for a capability you can already describe, sized for roughly one pull request. Produces a design document and changes no code. Does not specify what a feature should do — use plan-a-feature. Does not plan delivery or sequencing — use plan-implementation. Does not assess the architecture of existing code — use architectural-analysis. Does not write the code — use tdd. Does not restructure existing code — use refactor. Runs its rounds without pausing for review; to review each round as it lands, use pairing.

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。

Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-standard. Does not compare two concrete artifacts for gaps — use gap-analysis. Does not assess an existing module's architecture — use architectural-analysis. Does not capture feedback on Han's own skills — use han-feedback.

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。

Run an honest market-fit and viability audit of any project or idea and produce a decision doc, not code. Use when someone asks "is this viable as a business", "audit the market fit", "make the case and compare to competitors", "should I apply to YC or bootstrap", or wants to validate a project, product, or market before investing more time. Gathers verifiable traction data first, researches the competitive field, gets an independent cold read, writes a doc with pre-committed pass/middle/kill criteria and a concrete week-1 assignment, then hardens it with an adversarial review 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。

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved 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 verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrong_if falsifiability review. ≈50-finding cap sorted by severity; content-derived finding IDs; incremental scoping with three backstops; lifecycle hooks at pillar-complete / thesis-complete / pre-reduction.

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 the knowledge/ base and the .claude/ skills, agents and workflows for staleness, self-contradiction, and drift from their own stated rules — four independent adversarial auditors (two lenses over two trees) verify every load-bearing claim against the current tree, cross-examine each other within their tree, and reach a consensus on if/what needs changing. Use periodically, after a run of deliveries that changed build config, target layout or the skills themselves, or whenever you suspect the docs have aged out of true.

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 review the current implementation plan with three independent critic subagents, reconcile their findings into a consensus, and apply the agreed feedback to the plan. Use after drafting a plan (in plan mode or a plan/design doc) and before starting implementation, or whenever the user asks to pressure-test, critique, or harden a plan.

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。

This skill should be used when the user says "/council", "council", "deliberate", "multi-perspective decision", "트레이드오프 분석", "위원회 소집", "여러 관점으로 검토", or wants deep multi-perspective deliberation with tradeoff mapping. Combines tribunal (structured adversarial review), agent-council (external LLM opinions), dev-scan (community sentiment), and step-back (meta-level review) into a unified decision-making committee. Uses Agent Teams for real peer-to-peer debate with iterative step-back moderation 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。

This skill should be used when the user says "/tribunal", "tribunal", "review this", "3-way review", "risk-value-feasibility check", or wants multi-perspective adversarial review. Also triggered by: "트리뷰널", "리뷰 해줘", "3관점 리뷰", "위험성 검토". Runs 3 agents (Risk/Value/Feasibility) in parallel and synthesizes a verdict.

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 for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

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-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.

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。

Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource exhaustion, malformed data, and requirement-linked traceability tests. Use after happy-path tests exist and before claiming coverage is complete, when requirements lack tests, or before a 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。

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

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。

AgentFlow workflow skill. Use this skill when the user needs 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 and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Load at the start of any task whose deliverable is prose another person will read — a PR description, commit message, README, doc, postmortem, blog post, issue or review comment, report, release note or essay — before drafting it, whether the result is pushed, posted, published or saved to a file, without being asked. Draft, then run this pass on the draft before handing it over. Also use when someone says "de-claude", "de-slop", "humanize this", "this reads like AI", "make it sound human", or asks for a voice, tone or register edit. Rewrites the constructions that mark prose as model-written (staged reveals, verdict headers, aphoristic closers, "it's not X, it's Y", em-dash drama, forced triads, flat-certainty adverbs) into plain technical prose and checks the rewrite kept every claim. Not for fiction, poetry, code, or quoted text; for a full adversarial review of a deliverable use challenging.

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。

AI Manipulation Defense System implementation with Midstream, AgentDB, and lean-agentic

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。

Suede Labs copy-only orchestration DAG. Use for one high-stakes piece strangers will read that has to be true: a landing page, launch post, blog post, email, X thread, docs page, README, ad, or store listing, researched, fact-audited, adversarially reviewed, and gated for publish readiness in one pass. The audit targets what the agents invent, never what the requester supplied: their own statements are given, and no phase may verify, hedge, or gate on them. Reads the live surface; never publishes. NOT FOR: multi-surface campaign writing (use johnny-suede-write); changing code (use suede-graph-flo-xr); one surface in one pass with no research (use suede-copy); stripping AI patterns from existing text (use suede-deslop); bulk generation of many independent pieces (private Suede Labs companion, not in this pack: suede-codex-fleet).

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。

Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure.

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。

Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices. Use when impl must be proven to match a PRD/SRS/AC.

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。

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

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。

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

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。