1,173 件 ・ 関連度順
概要と使いどころ
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
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。
统一接口协议、请求响应、错误码、兼容性与上下游协作约束。 当架构师、前后端开发或 QA 需要锁定 API 合同时使用。
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。
自动化视觉测试与 UI 交互验证。部署功能后使用浏览器自动化验证关键页面、核心路径和发布前回归。 当任务需要真实浏览器验证渲染、导航、交互或前端上线风险时使用。
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 for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect clone", or "AI website clone". Requires browser automation and records component specs, assets, implementation, build output, and visual QA as Superloopy evidence.
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。
Используй только внутри активного Codex Project Autopilot-проекта для verification/handoff; не включай для обычного code review вне автопилота.
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。
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links. Use when automating signup, login, or email verification without parsing HTML manually.
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。
Analyzes alternative splicing from PacBio Iso-Seq (HiFi, Kinnex/MAS-Iso-seq) and Oxford Nanopore (direct cDNA, direct RNA, R10.4.1+) long-read RNA-seq with full-isoform resolution. Tools include FLAIR (correct/collapse/quantify/diffSplice for PacBio + ONT), IsoQuant (de-novo or annotation-guided isoform discovery 2024 SOTA), Bambu (annotation-aware Bayesian discovery + quantification with Novel Discovery Rate), SQANTI3 (isoform classification: FSM/ISM/NIC/NNC + artifact flags), rMATS-long (event calling on long-read isoforms), and minimap2 (-ax splice:hq for HiFi; -ax splice -k14 for ONT cDNA; add -uf only for direct RNA or stranded cDNA preps). Solves microexon detection, recursive splicing, complex multi-exon isoforms, and DTU without transcript-quantification uncertainty. Use when short-read AS limitations (anchor length, complex isoforms, microexons, recursive splicing, transcript ambiguity) demand full-isoform resolution.
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。
Answer Viking AI Search product questions, CLI usage questions, API/auth questions, configuration questions, and troubleshooting questions by grounding every claim in either the installed `vs` CLI's own output or official Volcengine documentation. Never fabricate.
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。
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
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。
Select and use Audio Toolbox acoustic, psychoacoustic, and speech quality metrics. Use when computing loudness, sharpness, roughness, fluctuation strength, noise criteria (NC/RNC/RC), speech transmission index (STI), speech intelligibility index (SII), speech quality (ViSQOL, STOI), SPL, reverberation time (RT60), tone-to-noise ratio, or prominence ratio. Also use when asked about PESQ, POLQA, calibration factor, EBU R 128, LUFS, HVAC noise, background noise evaluation, or how to measure audio quality or noise compliance. Covers calibration, standard selection, signal alignment, and the complete function inventory including what does NOT exist.
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。
Generate 3GPP-compliant 5G NR downlink and uplink baseband waveforms. Use to create NR signals, test model (TM) waveforms, fixed reference channels (FRC), test and measurement (T&M) signals, or test vectors for conformance testing. Covers configuring data, control, and broadcast channels and signals: PDSCH, PUSCH, PDCCH, PUCCH, SRS, SSBurst, CSI-RS, DM-RS, PT-RS, CORESET, and BWP parameters including bandwidth, subcarrier spacing (SCS), modulation (QPSK, QAM), numerology, FR1, FR2, TDD, FDD, and multi-bandwidth-part setups. Use for signal generation, RF instrument playback, or IQ baseband synthesis. Requires 5G Toolbox.
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。
Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the multi-pane stress matrix, visual polish sweep, component perfection checklist, automated a11y (axe-core), pragmatic performance budget (LCP/CLS/INP), scenario battery (11 scenarios), and stress recipes including the real-flavour data battery. Hard gates: console errors/warnings = 0, network 5xx = 0, layout collapse = 0, axe Critical/Serious = 0, perf budget green. Audit-the-audit meta-check rejects rushed reports. Each finding has reproduction steps, evidence path, and suspected code location. Trigger with 'ux audit', 'walkthrough', 'qa sweep', 'audit the app', 'dogfood this', 'check all pages', 'find what's broken', 'stress the UI'.
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。
Translate, transcreate, review, or maintain multilingual product and marketing content, including source locking, glossary decisions, language style, machine-assisted workflows, legal-content safeguards, QA, and source-change synchronization. Use localization-strategy for market scope, locale architecture, rollout, and production release planning.
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 finished Scenario assets have to give something back: a caption for a dataset or alt text, a reusable style description, a verdict against a brief, a canny, depth, pose, or segmentation control map for the next model, or the asset itself found again by text, tags, or visual similarity and filed into a collection. Keywords: caption, describe, analyze, QA, control map, find similar, reverse image search, semantic search, tag, collection.
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 a Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.
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。
Exercise the delivered customer journey using real runtime or browser evidence. Use for functional acceptance testing after implementation, including failure paths.
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。
Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples. Use this skill whenever the user wants to define how a brand sounds, write a voice and tone document, audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing. Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit. Also triggers when the user has copy that 'feels off' and the underlying issue is voice, even if not stated explicitly. On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes.
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。
Systematic content refresh discipline. Quarterly audits, refresh prioritization (which pieces, when, how deep), refresh-vs-merge-vs-delete decisions, the lifecycle that distinguishes intentional refresh from set-and-forget decay. Builds on the refresh sections of pillar-content-architecture and editorial-qa with a program-level discipline. Triggers on content refresh, content decay, content audit, refresh prioritization, content lifecycle, refresh strategy, traffic decay, ranking drop, content freshness, evergreen content, content maintenance. Also triggers when traffic is eroding silently across an aging content library, when teams cannot decide which pieces to refresh, or when refresh work is happening but the impact is unclear.
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。
Eng manager-mode plan review. Scope challenge, architecture review, code quality review, detailed test coverage diagram, performance review. Produces test plan artifact for downstream QA. Optional cross-model outside voice.
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。
Headless Chromium CLI for QA testing and site dogfooding. 100-200ms per command after startup. Persistent state with cookies, tabs, sessions. Snapshot system with element refs. Navigate, interact, verify page state, take screenshots, check responsive layouts, test forms, handle dialogs.
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。
Live-site visual QA audit with fix loop. 10-category checklist (~80 items) including AI Slop Detection (10 blacklisted patterns). Atomic commits per fix. Before/after screenshots. A-F grading. Parallel cross-model code-level design audit. Modes: Full, Quick, Deep, Diff-aware, Regression.
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。
Answer Engine Optimization (AEO): optimize content to be cited by LLMs (ChatGPT, Claude, Perplexity, Gemini) in their answers. Use when designing content for LLM citation, auditing citability, or structuring Q&A schema.
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。
Testing for React/Next.js with Jest, React Testing Library, and Playwright. Use when generating tests, writing unit tests, analyzing coverage, scaffolding E2E tests, configuring Jest, or improving test quality.
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。
A zero-hallucination privacy-policy generator that takes anyone — non-lawyer founder to lawyer — from a guided intake to a publishable, jurisdiction-aware privacy policy. Jurisdiction-first: it detects which laws apply from where your users are, then drafts only the required clauses — GDPR/EU + UK, US (CCPA/CPRA, ~20 state laws, COPPA, sector overlays), and global/MENA (LGPD, Quebec Law 25, India DPDP, China PIPL, UAE/DIFC, Saudi PDPL), plus app-store, cookies, and AI/EU AI Act disclosures. Its rule: state only what you confirm; never invent a statute, citation, fine, or date — every claim is source-cited and QA-gated. Not legal advice.
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。