'adversarial' 검색 결과

Critically assess and improve a legal scholarly thesis, article idea, student note, seminar-paper claim, or research agenda using Eugene Volokh's novelty, nonobviousness, utility, and soundness framework, connector-aware research, claim-specific tests, and a sustainable adversarial pass. Produces a self-contained green-, yellow-, or red-light report. Use when a law professor or law student asks whether a claim is viable, novel, publishable, preempted, useful, worth pursuing, or better than competing topics; or wants a thesis stress-tested, narrowed, repaired, or compared. No connector is required: use connected legal and scholarly research when available, public sources otherwise, and disclose any no-research fallback.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adversarial verification of AI-generated legal content with systematic fact-checking, source validation, and quality control. Use when a user asks to verify, fact-check, red-team, validate sources, or quality-control a legal document, briefing, compliance summary, or regulatory analysis before it is distributed to clients, stakeholders, or published. Trigger phrases include "verify", "fact-check", "red team", "red-flag", "check accuracy", "validate sources", "quality control", "is this correct", and "review for errors". Produces a structured verification report with severity-categorized errors, verified sources, unsupported claim list, missing disclaimers, and an explicit distribution-readiness assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adversarially stress-tests a legal text — a contract, statute, regulation, or judicial opinion — for interpretive ambiguity: it finds the seams where the people governed by it will later disagree about what it means and turns each into a concrete dispute scenario with both sides' arguments, the likely outcome, and a fix. Use it whenever someone wants to pressure-test, red-team, audit, or find weak spots, loopholes, gaps, ambiguities, or drafting problems in a legal document; whenever a drafter wants to tighten a contract, statute, regulation, or opinion before it issues; whenever a litigator wants to mine an opinion or contract for arguments; or whenever someone hands over a legal text and asks where it will be fought over or for issue-spotting. Trigger it for contract review, statutory-ambiguity analysis, judicial-opinion scope analysis, and drafting QA — even if the user never says "stress-test" or "ambiguity."

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Claude skill that turns Claude into a Connecticut-specific divorce planner — nine operating modes from pre-flight intake to post-judgment modification, modeled on Untangle.us's feature surface and grounded in C.G.S. Title 46b, Practice Book Chapter 25, and the 2026-08-01 CCSG schedule. Covers eligibility triage (nonadversarial under § 46b-44a vs standard), financial affidavit (JD-FM-6), child support (JD-FM-220 / CCSG-1 / 1A), alimony (§ 46b-82 fourteen factors), parenting plan (with GAL/AMC escalation under JD-FM-224), settlement agreement (JD-FM-172, TCJA-aware), filing packet (marshal 12-day rule, $360 + $50 fees, JD-FM-75 waiver), and post-judgment motion practice. Hard UPL gate: refuses non-CT, domestic violence (refers CTCADV 1-888-774-2900), hidden assets, courtroom advocacy. Heppner-aware: AI prompts are not privileged. First family-law skill in the Lawvable registry.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a labeled evaluation set. Also use when the user mentions test data design, eval coverage, difficulty stratification, synthetic data generation for eval, or "how to create good evaluation data." Outputs datasets in OpenJudge-compatible format.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deep security audit of a smart-contract repo OR a live on-chain contract by address - detect Solidity, model the protocol invariants and trust boundaries first, run Slither (best-effort) plus a bounded agentic pass that hunts for a path breaking each invariant, triage, adversarially verify, prove with a fuzzer, and drive each finding through the shared responsible-disclosure routing. The dedicated contract arm split out of vuln-scanner.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tool safety protocols, adversarial output validation, error recovery patterns, and I/O contracts for research operations

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Enforce Red-Team verification and adversarial protocol audit. Use only when verifying completion, performing self-scans, or checking protocol violations; do not activate for ordinary implementation, configuration, or unit-test requests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adversarial review and fix loop for code, specs, plans, and migration manifests.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Precision-first adversarial bug hunting for runtime, logic, data, concurrency, and security defects. Uses deterministic risk triage, evidence-bounded retrieval, Hunter/Skeptic/Referee review, optional hybrid verification, and explicit immutable Fixer scope. Scan-only and single-pass by default; complete-coverage loops, edits, autonomous fixes, and commits each require explicit intent. Use for code review, security audits, regression hunting, PR review, and evidence-backed remediation planning in skills-capable coding agents.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when user asks for a sequenced learning path within a Buddhist tradition — 学修次第, 先学什么, 从哪入门, 下一步读什么, curriculum, 学习计划, 路径推荐. Differs from /compare-masters (parallel opinion) and /master-debate (adversarial dialectic) by being 纵向 / 时序: stage-by-stage plan keyed on tradition × level (L0-L3) → foundation → intermediate → advanced + blind spots. Trigger is planning intent — "禅宗对比" goes to /compare-masters; "禅宗从哪开始学" goes here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

4-phase execution loop for work units - IMPLEMENT, VALIDATE, ADVERSARIAL REVIEW, COMMIT

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Delegate implementation and review tasks to external AI CLI tools (Codex, Gemini) with cross-model adversarial review

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Automatic adversarial review gate that spawns 3 independent reviewers in parallel after any plan is drafted - all must PASS before presenting to user

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than $smoke-test. Use when the user asks to "exploratory test", "test thoroughly", "test all scenarios", "deep test", "test edge cases", "test everything", "break it", "find bugs by testing", "test usability", or "check the UX while testing".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than /smoke-test. Use when the user asks to "exploratory test", "test thoroughly", "test all scenarios", "deep test", "test edge cases", "test everything", "break it", "find bugs by testing", "test usability", or "check the UX while testing".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analyze what changed and generate a structured test plan at .turbo/test-plans/<slug>.md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what should I test", "generate test scenarios", "test plan for this PR", or "what are the test cases".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "filter false positives".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when attacking an AI/ML system or model — prompt injection & jailbreaks (Crescendo, Skeleton Key, Best-of-N), RAG/vector poisoning, agentic/MCP exploitation (CVE-2025-54136), ML supply-chain RCE (pickle CVE-2025-32434), model extraction / membership inference / adversarial suffixes (GCG)

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Adversarially fact-check DOCS.md files against the actual source code, verifying every concrete claim rather than trusting structure checks. Use when the user asks to audit docs, verify documentation accuracy, check whether docs are still true, or on a scheduled documentation review. This is the semantic layer the mechanical checkers cannot cover.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.