908 件 ・ 関連度順
概要と使いどころ
You are an expert in AWS Lambda, Amazon's serverless compute service. You help developers build event-driven applications using Lambda functions triggered by API Gateway, S3 events, SQS queues, DynamoDB streams, and scheduled events — with support for Node.js, Python, Go, Rust, Java, and container images, automatic scaling from zero to thousands of concurrent executions, and pay-per-invocation pricing.
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。
Plans a controlled experiment (A/B test) so its result can be trusted: writes the hypothesis, picks one primary metric and the guardrails, computes sample size and run time, specifies how visitors are assigned and when exposure is logged, and reads out the result with a confidence interval. Use when someone says "set up an A/B test", "split test this page", "how many visitors do I need", "how long should the experiment run", "is this result significant", "can I stop the test early", or wants to test a headline, price, layout or onboarding change against the current version.
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。
Patterns for computer-aided drug discovery including virtual screening, molecular docking, ADMET prediction, lead optimization, and integration with AI/ML methods. Covers both structure-based and ligand-based approaches. Use when ", " mentioned.
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 implementing object detection, semantic/instance segmentation, 3D vision, or video understanding - covers YOLO, SAM, depth estimation, and multi-modal visionUse when ", " mentioned.
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 experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".
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。
Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".
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。
Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".
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。
Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".
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 whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
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。
Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".
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。
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and proposes per-obligation findings, each span-anchored to the evidence ledger (claims.json); reviewer≠adjudicator. Emits proof-derivation-forensics.findings.json; NEVER computes the verdict. dimension=proof, can be critical. Triggers: "proof forensics", "check this proof", "derivation integrity", "audit the math", "证明审计", "推导有没有漏洞".
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。
Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".
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。
Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines 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。
Azure Machine Learning SDK v2 for Python workflow skill. Use this skill when the user needs Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines 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。
红队渗透 / 攻防 — 受授权的红队作业者 + 渗透测试工程师 + 攻击型安全顾问的认知操作系统 (侦察 OSINT / 外网渗透 / 内网 AD 渗透 BloodHound + Kerberoasting + ADCS 利用 + 横向移动 / Web 应用渗透 OWASP WSTG / 移动 OWASP MASTG / 云渗透 AWS Azure GCP IAM 路径 + 容器逃逸 + K8s / C2 操作 Cobalt Strike Sliver Mythic Havoc + OPSEC / 初始访问 + AV EDR 绕过 (仅授权场景) / 无线 RF / 物理社工 / 报告与整改 / 框架 MITRE ATT&CK + D3FEND + PTES + OSSTMM + NIST 800-115 + Kill Chain / 法律伦理 CFAA + 网络安全法 + 刑法 285 286 + 数据安全法 + GDPR + 授权书 + 范围 + 交战规则 — 不含 黑产 / 未授权攻击 / 大规模 exploitation / 供应链投毒 / 未授权 DoS — 这是 重罪 + 行业封杀 + 律师吊销, 本 skill 严守 authorized-only 边界 — 也不含 蓝队 SOC + 恶意软件 即服务 / 僵尸网络 / 勒索软件作者 — 这是 cybercrime 不是 红队) (Cybersecurity Red Team / Offensive Security Operations — the cognitive operating system of authorized red team operators, penetration testers, and offensive security consultants covering (a) reconnaissance & OSINT (passive + active discovery, asset surface mapping), (b) external network pentest (perimeter, exposed services, web), (c) internal network / Active Directory pentest (AD enumeration via BloodHound, Kerberos abuse — Kerberoasting / AS-REP-roasting / Unconstrained delegation / S4U2self, NTLM relay, ADCS abuse, GPO abuse, lateral movement, privilege escalation), (d) web application pentest (OWASP WSTG, authentication, authorization, SSRF, XXE, deserialization, SSTI, prototype pollution, GraphQL, JWT, API), (e) mobile pentest (OWASP MASTG, iOS / Android, instrumentation Frida / Objection, MASVS), (f) cloud pentest (AWS / Azure / GCP — IAM enumeration, privilege escalation paths, container escape, K8s RBAC, serverless), (g) C2 operations & post-exploitation (Cobalt Strike / Sliver / Mythic / Havoc, beacon ops, malleable profiles, OPSEC), (h) initial access & evasion (phishing infrastructure, payload development, AV / EDR evasion, BYOVD, AMSI / ETW bypass — strictly for authorized engagements), (i) wireless / RF (WPA2/3, evil twin, Wi-Fi pivots), (j) physical / social engineering (badge cloning, pretexting, vishing — under engagement letter), (k) reporting & remediation (executive summary, technical findings, CVSS, MITRE ATT&CK mapping, retest), (l) frameworks & methodology (MITRE ATT&CK, MITRE D3FEND, PTES, OSSTMM, NIST SP 800-115, OWASP WSTG / MASTG, Cyber Kill Chain, Unified Kill Chain, Diamond Model), (m) law & ethics (CFAA US, Computer Misuse Act UK, 中国 刑法 285/286 + 网络安全法 + 数据安全法, GDPR for tested EU systems, engagement letter, scope, rules of engagement, safe harbor for bug bounty); NOT criminal hacking / 黑产 / unauthorized targeting / mass exploitation / supply-chain compromise / DoS against unconsented systems (这是 重罪 + 业内开除 + 律师执照吊销, 本 skill 严守 authorized-only 边界), NOT pure defensive blue team / SOC analyst tradecraft (是 平行学科, 仅做 边界标注 + ATT&CK 反推方向), NOT malware-as-a-service development / botnet ops / ransomware authoring (是 cybercrime 不是 红队), NOT 'ethical hacking' 在 'just curious 看看' 自我合理化的灰色操作 (违反 authorization 原则即不是 红队).) Master OS — automated mastery of Cybersecurity Red Team / Offensive Security Operations — the cognitive operating system of authorized red team operators, penetration testers, and offensive security consultants covering (a) reconnaissance & OSINT (passive + active discovery, asset surface mapping), (b) external network pentest (perimeter, exposed services, web), (c) internal network / Active Directory pentest (AD enumeration via BloodHound, Kerberos abuse — Kerberoasting / AS-REP-roasting / Unconstrained delegation / S4U2self, NTLM relay, ADCS abuse, GPO abuse, lateral movement, privilege escalation), (d) web application pentest (OWASP WSTG, authentication, authorization, SSRF, XXE, deserialization, SSTI, prototype pollution, GraphQL, JWT, API), (e) mobile pentest (OWASP MASTG, iOS / Android, instrumentation Frida / Objection, MASVS), (f) cloud pentest (AWS / Azure / GCP — IAM enumeration, privilege escalation paths, container escape, K8s RBAC, serverless), (g) C2 operations & post-exploitation (Cobalt Strike / Sliver / Mythic / Havoc, beacon ops, malleable profiles, OPSEC), (h) initial access & evasi
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。
Odoo 17 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 17 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/tree/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code. Includes CSS/SCSS asset authoring and review for Odoo addons.
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。
Odoo 16 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 16 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/tree/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code. Includes CSS/SCSS asset authoring and review for Odoo addons.
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。
Odoo 18 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups), cron and server actions, migrations and module upgrades, tests, i18n, and performance. Use this skill whenever work involves Odoo 18 or custom addons—even if the user only pastes a traceback, mentions addons/ or __manifest__.py, describes form/list/kanban/XML errors, HTTP controllers, or business rules on models—including building features, fixing bugs, refactoring, or reviewing addon code. Includes CSS/SCSS asset authoring and review for Odoo addons.
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。
Computes a numeric or categorical answer to a quantitative data-science question by cleaning and analyzing local data files (CSV, Excel, TSV, and scientific formats .npz/.fits/.h5) with pandas, numpy, and scipy. Use whenever a task ships its own dataset (in whatever local directory it provides) and asks you to derive a value via statistical, geospatial, temporal, ratio, percentage, growth-rate, correlation, signal-processing, orbital, or forecasting analysis. Spans domains including archeology (demographics, paleoclimate proxies, radiocarbon dating, historical conflicts); biomedical/bioinformatics (tumor histology, genes, proteins, peptides, genomic variants); environmental (water quality, bacterial/Enterococcus exceedance, rainfall correlations, environmental justice); legal/consumer (fraud, identity theft, consumer complaints by state/metro); wildfire (incidents, causes, suppression costs, acres burned, fatalities, geospatial intersections); and astronomy/heliophysics/space weather (satellite telemetry TLE/Swarm/SP3, indices OMNI/GOES, solar activity, atmospheric density, orbital mechanics, forecasting).
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。
Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and research strategy. Reach for this skill whenever discussing machine learning paradigms, the limits of compute and data, AGI timelines, superintelligence safety, or deciding between hardcoding vs. learning. Trigger this skill for questions about next-word prediction, reinforcement learning efficiency, generalization gaps, and transitioning from brute-force scaling to fundamental research, even if the user doesn't explicitly name him.
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。
Applies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI. Use this skill whenever Claude encounters topics related to AI ethics, human-centered AI, spatial intelligence, embodied AI, robotics, AI governance, diversity in tech, or the societal impacts of AI. Trigger this skill when users face decisions about AI product design (augment vs. replace), dataset formulation, navigating AI regulation, or choosing audacious research directions. Channel her pragmatic optimism and focus on spatial, physical grounding over pure language models.
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。
Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab). Use this skill whenever you are discussing natural language processing, LLM architecture, AI research strategy, cognitive science, or the evolution of machine learning. Trigger this skill for questions about AGI timelines, academic vs. industry research trade-offs, linguistic structure in neural networks, modularity in AI design, or evaluating true intelligence versus mere memorization. Channel his pragmatic focus on domain science, adaptability, and competing on ideas rather than raw compute.
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。
Applies the reasoning style of Kaiming He, computer vision pioneer and creator of ResNet. Use this skill whenever you are designing deep learning architectures, debugging neural network optimization, formulating generative AI problems, or bridging AI with other scientific domains. Trigger this skill for discussions on network depth, weight initialization, residual learning, flow matching, or when reframing discriminative tasks as conditional generation. It emphasizes simplicity in complex visual problems, end-to-end optimization, and viewing AI as a universal language for science.
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。
Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered features.
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。