624 件 ・ 関連度順
概要と使いどころ
Use automatically for PDF tasks, including Chinese requests like 查看PDF, 读取PDF, PDF里写了什么, 总结PDF, 分析PDF, 提取PDF文字, 识别PDF内容, or questions about any .pdf file. Prefer text extraction with pdfplumber/pypdf first, then render pages with Poppler when layout, images, tables, stamps, watermarks, or scanned content matter.
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。
ผู้ช่วยจัดซื้อมืออาชีพ — RFP/RFQ template, supplier scorecard, TCO, contract negotiation, e-procurement
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。
Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.
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。
教 Agent 如何发现并调用 A2A B2B Agent 互联平台（能力发现、会话、消息、RFP/提案）。平台根 URL 可配置，默认 https://a2a4b2b.com。
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。
Iterate on a GenAI notebook against the self-hosted stack via the genai-stack CLI (config dirs, auth, subdomains, quantization, GPU/VRAM). Arguments: <notebook|service> [--service comfyui|forge|vllm] [--quant int4|fp8] [--validate] [--bg]
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。
DiT 计算模块（L3）：把**已定位的 DiT 计算瓶颈**落成特性级选档与实施—— 量化档（W8A16 / W4A16 / W8A8 系列 / W4A4 / MXFP8 / FA 量化）、稀疏（rf_v2 / ada_bsa）、 缓存（DiTCache / AttentionCache / 时间步优化）、编译启用（MindieSDBackend / Pattern 融合 / ACLGraph） 的**开不开、开哪一档、怎么开、怎么复验**；依据是 `docs/zh/features/*`（特性真源）+ framework-integration/references/framework-support-matrix.md（支持状态）。 即使用户只说"这个模型怎么加速""量化/稀疏/Cache 怎么选怎么开""要不要开量化、开哪一档""这个档位开了有没有效果" 而未提 profiling，也应触发。 **入口条件**：瓶颈点已明确（用户带一句实测锚点，或编排层交付标签）时由域入口 `performance-optimization` 按标签分发到本技能；**瓶颈未明（"怎么加速 / 跑通 / 采 profile"）先走 `model-auto-optimization` 定位**，不在本技能内做占比分析。 near-miss：多卡并行形态 / 通信掩盖 / TP·offload 选型 → `dit-parallel-opt`；VAE 解码段与 host 固定开销 → 各自模块（VAE / host）；单算子实现级实测选型（mindie_bench）→ `benchmark-dev`； 需要新增 pattern / 算子才能落地本档 → `pattern-dev` / `operator-dev`；框架侧开关与使能验证 → `framework-integration`；量化器位级契约与精度对齐（编码公式 / 舍入 / scale 粒度）→ `quantization-dev`；精度验收判据 → `accuracy-gate`；数字入库口径 → `perf-gate`。
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。
Drafts code-compliant California responses to Requests for Production (CCP § 2031.010 et seq.) for Superior Court. Use when the user mentions California RFP responses, CCP 2031, discovery objections, compliance statements, inability to comply, privilege objections, Bates numbering, verification requirements, or responding to document requests in California state court. California Superior Court only — not for federal court without substantial modification.
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。
Drafts Brownfields Agreements for contaminated-property transactions under CERCLA, EPA brownfields programs, and state voluntary cleanup programs. Structures BFPP liability protections, All Appropriate Inquiries documentation, remediation obligations, institutional controls, cost allocation, and long-term stewardship covenants. Use when drafting brownfields purchase agreements, prospective purchaser agreements, voluntary cleanup MOAs, or environmental covenant frameworks.
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。
Task-sized forensic analysis of Vivado synthesis and routed timing evidence for processor RTL. Use when Codex must trace a named setup or hold path, audit whole-design timing populations, compare implementation runs, map primitive, LUT, CARRY, BRAM, DSP, MUXF, register, and routed-net stages back to Chisel or generated RTL, distinguish logic from routing pressure, identify missing DCP queries, or write an evidence-backed timing report. This skill is read-only by default and stops at ranked modification directions. Use optimize-chisel-fpga-timing for RTL edits and routed A/B implementation closure.
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。
Normalizes and transforms RNA-seq count matrices for DE, visualization, clustering, and ML. Covers between-sample (TMM, TMMwsp, RLE/median-of-ratios, upper quartile), within-sample (TPM, FPKM/RPKM), variance-stabilizing (VST, rlog, log-CPM), GC-content correction (cqn, EDASeq), and single-cell (scran deconvolution, scanpy normalize_total). Encodes the composition-bias rationale, the "most genes not DE" assumption and its catastrophic failure modes (MYC amplification, apoptosis, viral host shutoff, prokaryotic stress), the "lengthScaledTPM is not TPM" naming trap, the "TPM is not for DE" rule, the blind=TRUE vs FALSE decision, ERCC spike-in normalization (SBN), and the single-cell zero-inflation breakdown of TMM/RLE. Use when choosing or applying normalization, debugging shifted-MA-plot diagnostics, handling zero-heavy single-cell data, or correcting GC bias.
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。
Queries myvariant.info BioThings aggregator for ClinVar, gnomAD, dbSNP, dbNSFP, COSMIC, CADD, and CIViC annotations in batched, version-tracked requests. Use when annotating variant lists from multiple databases simultaneously without managing per-source APIs, and when reproducibility-grade analyses require recording source data versions via _meta.
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。
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
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。
Serve LLMs com alta throughput usando PagedAttention do vLLM e continuous batching. Use ao fazer deploy de APIs LLM em produção, otimizar latência/throughput de inferência, ou servir modelos com memória GPU limitada. Suporta endpoints compatíveis com OpenAI, quantização (GPTQ/AWQ/FP8) e tensor parallelism.
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。
Quantização pós-treinamento em 4-bits para LLMs com perda mínima de precisão. Use para implantar modelos grandes (70B, 405B) em GPUs de consumo, quando você precisa de redução de memória 4× com <2% de degradação de perplexidade, ou para inferência mais rápida (aceleração de 3-4×) vs FP16. Integra com transformers e PEFT para fine-tuning QLoRA.
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。
Quantiza LLMs para 8-bit ou 4-bit com redução de memória de 50-75% e perda mínima de acurácia. Use quando a memória GPU é limitada, precisa ajustar modelos maiores ou quer inferência mais rápida. Suporta formatos INT8, NF4, FP4, treinamento QLoRA e otimizadores 8-bit. Funciona com HuggingFace Transformers.
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 tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.
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。
Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY + SET scripts + BucketFS), per-entity federated training with partial_fit and ctx.reset(), batch inference, map-reduce ensemble training, distributed ensemble and SON algorithm for frequent itemset mining (Apriori, FP-Growth, association rules, market-basket analysis), Lua execute script orchestration for iterative algorithms (k-means, SGD, gradient descent), scikit-learn model training, parallel hyperparameter search, per-entity forecasting, anomaly detection, model lifecycle in BucketFS (pickle/joblib/ONNX versioning), GPU acceleration via CUDA SLCs (PyTorch/TensorFlow/RAPIDS), and ML-specific performance tuning (skew, OOM, multi-pass chunking).
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。
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
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。
Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
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。
Spearphishing targets specific individuals using personalized, researched content that bypasses generic spam filters. Email security gateways (SEGs) like Microsoft Defender for Office 365, Proofpoint,
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 user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to devnet", or "explain Solana concepts" (rent, accounts, PDAs, CPIs, etc.). End-to-end Solana development playbook covering wallet connection, Anchor/Pinocchio programs, Codama client generation, LiteSVM/Mollusk/Surfpool testing, and security checklists. Integrates with the Solana MCP server for live documentation search. Prefers framework-kit (@solana/client + @solana/react-hooks) for UI, wallet-standard-first connection (incl. ConnectorKit), @solana/kit for client/RPC code, and @solana/web3-compat for legacy boundaries.
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 Systems Engineering Manual (SEM) v1.0.1. Use for civil-agency systems engineering as the FAA practices it inside the Acquisition Management System (AMS) and the National Airspace System (NAS): the five-phase AMS lifecycle and its decision points; operational concept development and implementation-free functional analysis (ConOps, FFBD/N², CMLs); requirements analysis and architectural design synthesis (PRS→MRS, the PRD ratchet pPRD→iPRD→fPRD, RAM, ISEF/DoDAF views, CPRs); the seven technical management disciplines (Integrated Technical Management/SEMP, Interface Management/IRD-ICD, Risk-Issue-Opportunity, Configuration Management, SE Information Management, Decision Analysis, Verification & Validation); and the specialty disciplines (RMA via Service Threads/STLSC, Life Cycle Engineering, E3/Spectrum, Human Factors, Information Security via the NIST RMF, System Safety via the SMS, and Hazardous Materials/Environmental/EOSH). Scope limits: this is FAA-specific guidance, not policy — it is a tailorable menu that points outward to companion handbooks (FAA-HDBK-006A for RMA, the SMS Manual, the NIST 800-series) rather than restating generic SE theory; it is thin on detailed cost estimating, contracting/FAR law, software-development methodology, named anti-pattern catalogues, and any non-FAA or non-civil-aviation lifecycle. Source has no page numbers in the extracted text (~360 pp.).
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 NASA Digital Engineering Acquisition Framework Handbook (NASA-HDBK-1004). Use for acquiring digital/model-based data under contract: the Data Requirements Description (DRD) instrument and the Appendix A DRD suite (TDP, MBx, CDMP, CSA, CR, FCA/PCA, SDT, EMDAL, REF, MRI); the Data Type 1-5 control scale; SOW/RFP/Cost-Volume contract language and data rights (FAR/DFARS, Table 3 license categories); the Requirements Exchange Format (REF/ReqIF, UUID schema) and Master Records Index; model-based data definition (MBSE, CAD/PMI, M&S credibility, BOM, release-state mapping, PLM); digital data collaboration, the four owned architectures, and interoperability standards (MIL-STD-31000, STEP/ISO 10303, ASME Y14); the four MBE interoperability use cases; and MBE Plan development. Scope is the acquisition and contracting side of digital engineering. Does not reproduce ISO/STEP/ASME/MIL-STD/SAE standard text, and the companion NASA-HDBK-1009A carries the deeper digital-engineering practitioner detail this handbook defers to.
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 MIL-STD-881F (13 May 2022), DoD Standard Practice for Work Breakdown Structures for Defense Materiel Items. Use for Program/Contract/Subcontract WBS construction, 100% rule and dictionary discipline, commodity appendices A–J, Common Elements (K), sustainment CES reporting (L), Government ST&E (M), and RFP/post-award implementation. Technical planning & WBS and PM/measurement focus—not a cost manual substitute for CAPE policy.
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。