8,369 件 ・ 関連度順
概要と使いどころ
Biblioteca do Facebook para busca eficiente de similaridade e clustering de vetores densos. Suporta bilhões de vetores, aceleração GPU e vários tipos de índice (Flat, IVF, HNSW). Use para busca k-NN rápida, recuperação de vetores em larga escala ou quando você precisa de busca pura de similaridade sem metadados. Melhor para aplicações de alto desempenho.
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。
Testes e benchmarking de agentes LLM incluindo testes comportamentais, avaliação de capacidades, métricas de confiabilidade e monitoramento em produção—onde até os melhores agentes alcançam menos de 50% em benchmarks do mundo real. Use quando: testes de agentes, avaliação de agentes, benchmark de agentes, confiabilidade de agentes, teste de agentes.
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。
Curação de dados acelerada por GPU para treinamento de LLM. Suporta texto/imagem/vídeo/áudio. Recursos incluem deduplicação fuzzy (16× mais rápida), filtragem de qualidade (30+ heurísticas), deduplicação semântica, redação de PII, detecção NSFW. Escala em GPUs com RAPIDS. Use para preparar datasets de treinamento de alta qualidade, limpar dados web ou deduplicar grandes corpora.
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。
Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.
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。
Agentes autônomos são sistemas de IA que conseguem decompor objetivos, planejar ações, executar ferramentas e se auto-corrigir sem orientação humana constante. O desafio não é torná-los capazes - é torná-los confiáveis. Cada decisão extra multiplica a probabilidade de falha. Esta habilidade cobre loops de agentes (ReAct, Plan-Execute), decomposição de objetivos, padrões de reflexão e confiabilidade em produção. Insight-chave: taxas de erro compostas matam agentes autônomos. Uma taxa de sucesso de 95% por passo cai para 60% b
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。
Evaluates candidate profiles against a job description and hiring criteria. Use when the user provides candidate profiles plus a role definition and wants consistent screening, matched requirements, and an interview recommendation.
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。
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
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。
Write, validate, and (optionally) execute an NQL query against a Narrative dataset. Drafts the query from the user's question, runs `narrative_nql_validate` until it compiles, explains the query in plain English, and only runs it on explicit approval (or when invoked with `--run`). Use when: "write an NQL query for X", "query this dataset", "validate this NQL", "run NQL against dataset <id>", "how many rows match Y", "show me the top N records from <dataset>". (narrative-common)
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。
동일한 결과를 내는 여러 조건문(OR 나열·중첩 AND)을 하나로 통합하고 의미 있는 boolean 메서드로 추출. "조건문 합쳐", "같은 결과 반환하는 if 정리", "중첩 if 평탄화", "/consolidate-conditional" 요청 시 사용. 단, 여러 메서드에 흩어진 동일 조건을 호출자 쪽으로 올리는 것은 /lift-up-conditional, 복잡한 조건식·분기를 메서드로 쪼개는 것은 /decompose-conditional이 적합. /consolidate-conditional [commit-ref]로 호출.
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。
Knowledge base from the FAA AMS Lifecycle V&V Guidelines (verification and validation), Version 3.0, dated April 2017. Use for applying verification and validation across the FAA Acquisition Management System (AMS) lifecycle: the verify-vs-validate distinction (built right vs. right thing), the work-product/component/product tiers, the nine V&V planning elements, the four method catalogs (Appendix C), decision-point-gated V&V (SASP, CRD, Investment Analysis, Solution Implementation, In-Service Management), the Appendix B document checklists (PRD/APB/ISPD/PMP), and the DT/OT/IOA test triad. Scope limits: this is an FAA acquisition-V&V doctrine, NOT a general SE process model, requirements-engineering manual, or test-design textbook. It borrows its core V&V definitions from CMMI v1.2 (SEI, paraphrased) and presumes the surrounding AMS lifecycle (see the FAA SEM pack); its phase tables are policy snapshots as of April 2017 and it is thin on detailed test methods, tool specifics, and anything outside FAA acquisition governance.
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。
Knowledge base from the DoD M&S VV&A Recommended Practices Guide (RPG web edition). Use for verification, validation, and accreditation of models and simulations — role responsibilities (user, developer, M&S PM, V&V agent, accreditation agent), fidelity, validation fundamentals, data V&V, risk-informed accreditation, T&E/V&V integration, referent development, and conceptual-model validation. Complements nasa-ms-7009 and T&E packs; does not replace DoDI 5000.61 or Service VV&A policies.
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。
Proposes tag and number structures for the new lines and instruments in a P&ID draft according to the project's numbering procedures, checks every tag extracted from the PFD against the quoted procedure format, and lists cross-section identifier mismatches and the registry checks a human must run. Never invents a numbering convention, never alters a PFD tag and never assigns a sequence number the procedure reserves for the registry. Use when the user asks to "run the tagging and numbering section", "check the tags against the numbering procedure", "propose the tag structure for the new lines and instruments" or "list the registry checks before validation" after the process safety flags. Do not use for validating the four sections, use validation-and-review-package instead; do not use for instrument content, use instrumentation-and-control-enrichment. Drafts for human review; never approves, authorises or signs 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。
Cursorで指定観点を評価するnative入口。共有code-review-guidanceと担当referenceを読み、結果を親へ返す。
LLM-judge stage of an alpha-mining pipeline: take a miner's deterministic candidate list, keep only real signal, drop noise, and propose additions to that miner's curated note. Use after any zero-token detector run. Reads only the candidate digest and the home note, never the corpus. Triggers: "/alpha-judge <miner>", "judge the candidates".
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。
Author and validate nvoos-chart fenced-JSON chart blocks for NV oOS chat surfaces — 29 chart types across distribution, part-to-whole, ranking, change, special and grid families. Covers type selection, the v2 schema (values/series/data.items, mode, sort, direction, unit, animate, table, target), data-shape rules, the create_chart_fence server validator, the a11y checklist, and copy-paste JSON templates. Use when writing chart fences in assistant responses, choosing a chart type for data, validating chart JSON, or deciding between nvoos-chart, create_chart, generate_chart and generate_mermaid.
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。
Customize WP Rocket behavior from a third-party plugin / theme via filter hooks — exclude URIs / cookies / user agents / REST API namespaces from caching, configure CDN URL rewrites, extend lazy load handling, override capability requirements, hook into Action Scheduler integration. Critical guidance — rocket_cache_reject_uri takes URI patterns (regex-like), NOT full URLs; rocket_cache_reject_* filters all expect arrays. The rocket_buffer filter is the FULL HTML output filter — extremely powerful but dangerous; one fatal error in the callback breaks every cached page until WP Rocket is disabled. Use when extending WP Rocket's default rules, NOT for cache invalidation (see wp-rocket-cache-invalidation). Triggers on rocket_cache_reject_, rocket_cdn_, do_rocket_lazyload, rocket_buffer, rocket_capacity, "exclude from WP Rocket cache".
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。
Programmatically clear WP Rocket cache from a third-party plugin / theme when data changes — the public rocket_clean_* function family (rocket_clean_post, rocket_clean_files, rocket_clean_term, rocket_clean_user, rocket_clean_home, rocket_clean_minify, rocket_clean_cache_busting, rocket_clean_domain, rocket_clean_cache_dir). Critical detection rule — WP Rocket is a PAID plugin not on Packagist; always feature-detect via function_exists('rocket_clean_post') OR defined('WP_ROCKET_VERSION') before calling, since not every site has it. Never raw-unlink the cache directory or call wp_cache_flush() expecting it to clear WP Rocket — wp_cache_flush is WP object cache, WP Rocket is FILE cache. The before_*_clean_* / after_*_clean_* action lifecycle hooks fire around every clean — useful for audit logging, monitoring, custom invalidation chains. Use when integrating cache invalidation in a companion plugin, WC integration, custom data plugin. Triggers on rocket_clean_, before_rocket_clean, af...
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。
Detect missing validation plans (how to verify the design is correct) in design documents and ADRs.
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。
Execute production-readiness gates with applicability control, consolidate validation report, and issue final readiness 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。
Zod 4 — TypeScript-first schema validation with static type inference. Use when writing Zod schemas, validating data, defining types with Zod, parsing input, creating form validation schemas, defining API request/response schemas, working with z.object, z.string, z.number, z.enum, z.array, z.union, z.discriminatedUnion, z.file, z.jwt, z.email, z.uuid, z.url, z.codec, z.toJSONSchema, z.fromJSONSchema, z.int, z.stringbool, z.templateLiteral, z.record, z.partialRecord, or any other Zod API. Also use when migrating from Zod 3 to Zod 4, or when the user's package.json shows zod@^4. CRITICAL: Always use Zod 4 APIs. Never use deprecated Zod 3 patterns unless user explicitly requests Zod 3 compatibility.
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 100-point QA validation of all skills + auto-fix + report.
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。
Cache dynamic and static responses on Netlify's CDN from Functions, Edge Functions, and proxies. Use when you add caching or cache-control headers to a function response, tune cache TTL or stale-while-revalidate, set up the durable cache, vary a cache key by query/header/cookie/country/language, purge or invalidate the cache by site or cache tag, use the programmatic Cache API (caches.open/match/put) or @netlify/cache helpers (fetchWithCache/cacheHeaders/getCacheStatus), speed up an expensive API call, add ISR or on-demand revalidation, or debug why a response is or isn't cached via the Cache-Status header.
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。
Validates custom dotnet new templates for correctness before publishing. Catches missing fields, parameter bugs, shortName conflicts, constraint issues, and common authoring mistakes that cause templates to fail silently. USE FOR: checking template.json files for errors before publishing or testing, diagnosing why a template doesn't appear after installation, reviewing template parameter definitions for type mismatches and missing defaults, finding shortName conflicts with dotnet CLI commands, validating post-action and constraint configuration. DO NOT USE FOR: finding or using existing templates (use template-discovery), creating projects from templates (use template-instantiation), creating templates from existing projects (use template-authoring).
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。
Guides creation and validation of custom dotnet new templates. Generates templates from existing projects and validates template.json for authoring issues. USE FOR: creating a reusable dotnet new template from an existing project, validating template.json files for schema compliance and parameter issues, bootstrapping .template.config/template.json with correct identity, shortName, parameters, and post-actions, packaging templates as NuGet packages for distribution. DO NOT USE FOR: finding or using existing templates (use template-discovery and template-instantiation), MSBuild project file issues unrelated to template authoring, NuGet package publishing (only template packaging structure).
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。