「tune」の検索結果

Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI Act + US state patchwork, AI cost economics (API-to-self-hosted breakeven), and AI team org evolution. Use when deciding whether to call an API or fine-tune, classifying AI use cases for regulatory risk, calculating when self-hosting pays off, sequencing AI hires, or when user mentions CAIO, AI strategy, model selection, foundation model, fine-tuning, EU AI Act, NIST AI RMF, AI governance, model risk, or AI economics. Strategic only — does not duplicate engineering AI/ML skills.

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。

Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without one.

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。

Mounts Cloud Storage buckets on Google Cloud as a POSIX file system using Cloud Storage FUSE (and the gcsfuse CLI tool). Use when interacting with the gcsfuse CLI or Cloud Storage FUSE mounts: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune mount flags (--implicit-dirs) or config-file settings, apply workload profiles, keep ML checkpointing safe (rename atomicity, hierarchical namespace/HNS, close-time finalization, concurrent writers), or diagnose slow training, low throughput, or bill spikes with gcsfuse metrics. Covers mount semantics, gcsfuse CLI and config files, GKE gcsfuse CSI driver (Workload Identity principal:// bindings, profile StorageClasses, sidecar sizing), and Cloud Run volume mounts. Don't use for bucket administration or data management without a mount (google-cloud-storage-basics) or fully POSIX-compliant shared file systems (Filestore, Managed Lustre; use gke-storage).

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 wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.

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。

Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.

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。

Used for finetuning NV-Generate-CTMR MR-Brain v1 for T1, T2, FLAIR, SWI, or MRA data from a NIfTI datalist. Not for clinical or production data approval.

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。

Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or language", it scopes the task, picks the cheapest sufficient path (word boosting → n-gram LM → fine-tuning), delegates each stage to the right sub-skill (data generation, training, evaluation, deployment), and answers cost/time/data questions along the way.

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。

Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.

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。

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).

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。

Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Write model bundles, prepared data, logs, and trained models to user-selected host directories.

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。

Check progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).

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。

Analyze and tune AssemblyAI model choice, audio delivery, polling, Streaming v3 turns, concurrency, and downstream work. Use when pursuing measured latency or throughput goals. Trigger with "tune AssemblyAI" or "AssemblyAI latency".

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, deploy, run, monitor, tune, and stop Simulink Real-Time applications. Use when the user wants to build a Simulink Real-Time model, load/start/stop an `.mldatx` on a target, set stop time or start options, drive root inports/playback/parameter stimulation, inspect installed or running apps, tune parameters with `getparam`/`setparam`, read ad hoc signal values with `getsignal`, manage parameter sets, control recording, or choose between file logging, live streaming, and file-log import. Covers `slbuild`, `install`, `load`, `start`, `stop`, `setStopTime`, `tg.Stimulation`, `startRecording`/`stopRecording`, `tg.FileLog.import`, `slrealtime.exportRun`, `getparam`/`setparam`, `getsignal`, and installed app management for Speedgoat targets and Simulink Real-Time Linux devices.

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。

Generates code that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, RLVR, and RLAIF trainers, including RLVR Lambda reward function and RLAIF custom prompt creation.

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。

Provide theatrical fortune themed entertainment without claiming prediction ability. Use for this Bot Generator Bot template; creates drafts or simulations within its declared scope.

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。

音乐制作 / 混音 (音乐制作 / 混音 (Music Production & Mixing) — 录音棚与卧室工作室里把一首歌从编曲/录音/编程做到混音/母带成品的工程+艺术认知操作系统，面向制作人(producer)、混音师(mixing engineer)、母带工程师(mastering engineer)、beatmaker、唱作人/bedroom producer，以及想入行/服务这行(录音棚、plugin 厂商、sample 公司)的视角。覆盖: (a) 第一性张力 — **服务歌曲/情绪 (serve the song / emotion-first: 技术只为打动人，'if it sounds good it is good'，用耳朵不用眼睛) ⇄ 技术正确/工程纪律 (technical correctness: gain staging 增益结构、headroom 余量、相位 phase、监听校准、LUFS 响度规范)**; **黄金耳朵/直觉混音 (mix by ears, reference-driven, 不看分析仪) ⇄ 看表/分析仪/规则 (mix by metrics: EQ 曲线、频谱仪 spectrum analyzer、相关计 correlation meter)**; **少即是多/减法混音 (subtractive, 'less is more', 录好源头 = 混音成功一半) ⇄ 重度处理/'we'll fix it in the mix' (heavy processing, 后期补救)**; **In-the-box 全数字 (ITB: DAW + 插件，召回方便，bedroom 可达专业) ⇄ 模拟硬件/outboard (analog console + 硬件，'mojo'/谐波染色 vs 召回噩梦)**; **人性化/groove/不完美 (humanize, push/pull, 'the feel') ⇄ 量化/网格/修音 (quantize to grid, pitch-correct, 'in the pocket' 靠编辑)**; (b) 核心工作流 / pipeline (最标准、最易蒸高质量+CLI 化) — 编曲制作 arrangement/production → 录音/编程 tracking/programming → 编辑 editing (comping 选段/quantize/pitch-correct/time-align) → 混音 mixing (gain staging → balance 平衡 → EQ → compression → 空间 reverb/delay → 自动化 automation → 总线/母线处理 bus/mix-bus) → 母带 mastering (响度/EQ/限制 limiting/dither/排序+间隔) → 交付 delivery (DDP/streaming spec/stems); (c) 工具栈 — DAW (Pro Tools 录音棚标准/Ableton Live 电子+现场/Logic Pro Mac 性价比/FL Studio beatmaker/Cubase/Studio One/Reaper); 插件 (EQ: FabFilter Pro-Q/SSL/API; 压缩: 1176/LA-2A/SSL bus comp 及其复刻 Waves/UAD/Plugin Alliance; 混响: Valhalla/Lexicon/Bricasti; 调音: Auto-Tune/Melodyne; 限制器 limiter: Pro-L 2/Ozone); 硬件 (监听音箱 monitors: Yamaha NS-10/Genelec; 声学处理 acoustic treatment; 转换器 converters: Apollo/RME; 话筒 mics: U47/SM7B/57); 采样/音色 (Splice/sample packs/Kontakt/Serum 合成器); (d) 知识正典 — Mixing Secrets for the Small Studio (Mike Senior)、The Mixing Engineer's Handbook / Recording Engineer's Handbook (Bobby Owsinski)、Zen and the Art of Mixing (Mixerman)、The Art of Mixing (David Gibson 可视化)、Modern Recording Techniques、Sound on Sound 杂志、Mix With The Masters 大师课、Pensado's Place; (e) figures/流派 — 混音大师 (Chris Lord-Alge CLA 摇滚/Andrew Scheps 'Stadium' 3-bus/Tony Maserati/Manny Marroquin/Serban Ghenea 流行隐形混音/Michael Brauer multing); 制作人 (Rick Rubin 减法/氛围、Quincy Jones、Dr. Dre 完美主义、Max Martin 流行结构、Jack Antonoff、Finneas bedroom→Grammy、Metro Boomin/trap、Timbaland、Pharrell); 母带 (Bob Katz K-system/响度战争批判、Bob Ludwig、Greg Calbi); 教育者 (Mike Senior、Pensado、Warren Huart Produce Like A Pro、Dan Worrall 技术深挖); (f) 行业话术/黑话 — gain staging/headroom/LUFS/true peak/comping/bouncing/printing/stems/DI/reamp/sidechain/parallel compression 并行压缩/mid-side/bus/aux/send-return/dry-wet/transient/sibilance/de-ess/pumping/mud 浑浊/harsh 刺耳/boxy/muddy/in the pocket/the pocket/quantize/swing/groove/vibe/mojo/reference track/A/B/recall/print/glue 胶水; (g) 争议/批判 — 响度战争 loudness war (Bob Katz/Loudness Penalty/streaming 归一化 LUFS 终结了吗)、修音/Auto-Tune 之争 (artistic vs cheating)、ITB vs 模拟玄学 (硬件 'warmth' 是否安慰剂、null test 盲测)、preset/AI 混音 (iZotope/LANDR/sample-based 是否毁了 craft)、bedroom producer 民主化 vs 录音棚消亡、'loudness'/over-compression、plugin 复刻 vs 真硬件、Spotify normalization 对母带的影响、过度依赖 reference/抄袭; (h) 创意 vs 技术张力是本行业 deep tacit 知识的核心 — 大量隐性 '听感' 知识难以言传，靠 reference/学徒/千小时积累。不含: 现场扩声 live sound/PA、音乐理论/作曲 composition (虽相关但聚焦录音棚后期制作)、配乐/film scoring (虽相关但聚焦歌曲制作)、纯硬件电子工程/合成器 DIY、音乐商业/版权/发行 (虽相关但聚焦制作技艺本身)。) Master OS — automated mastery of 音乐制作 / 混音 (Music Production & Mixing) — 录音棚与卧室工作室里把一首歌从编曲/录音/编程做到混音/母带成品的工程+艺术认知操作系统，面向制作人(producer)、混音师(mixing engineer)、母带工程师(mastering engineer)、beatmaker、唱作人/bedroom producer，以及想入行/服务这行(录音棚、plugin 厂商、sample 公司)的视角。覆盖: (a) 第一性张力 — **服务歌曲/情绪 (serve the song / emotion-first: 技术只为打动人，'if it sounds good it is good'，用耳朵不用眼睛) ⇄ 技术正确/工程纪律 (technical correctness: gain staging 增益结构、headroom 余量、相位 phase、监听校准、LUFS 响度规范)**; **黄金耳朵/直觉混音 (mix by ears, reference-driven, 不看分析仪) ⇄ 看表/分析仪/规则 (mix by metrics: EQ 曲线、频谱仪 spectrum analyzer、相关计 correlation meter)**; **少即是多/减法混音 (subtractive, 'less is more', 录好源头 = 混音成功一半) ⇄ 重度处理/'we'll fix it i

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。

当用户提出六爻占卜、六爻排盘、文王纳甲、京房八宫、三枚硬币起卦、手动输入六次爻值，或询问事业、感情、财富、学业等六爻问题时使用；英文 Liuyao、Six Lines Divination、Wenwang Najia、I Ching coin casting 也应触发。完成确定性排盘、领域方法加载、当前对话中的完整综合解读、包含卦盘与解读的 HTML 完整报告、标准分享图及事实一致性检查；对高风险医疗、生死、胎儿性别、失踪定位等问题只提供现实帮助。

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。

Measure and raise the precision of `bun run simplify`, the simplify census, shape by shape. Harvests every recorded census reading and not-slop answer, replays the current scans over history, has blind judges label a seeded sample, scores each shape with a Wilson interval, and tunes a scan's source until the sites it prints are ones a reader would act on (target 0.8). Use when asked how good the census is, why it flags the wrong things, or to tune a tree scan or a staged catcher.

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。

Analyze and tune a running llama.cpp server for local coding agents: propose config (ctx, prompt cache, MTP), benchmark before/after, report deltas. Use to optimize llama-server for Claude Code or Aider. Don't use for vLLM, ollama, or non-llama.cpp.

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 profiling with Intel VTune or AMD uProf for hotspots, top-down pipeline stalls, memory-bound analysis, or roofline data. Not for raw perf stat counters: use linux-perf.

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。

Tunes noisy detections by analyzing historical alert data to quantify false-positive sources, recommend allow-list filters and threshold adjustments, and measure precision impact. Activates for requests to tune a detection, reduce false positives, or analyze alert noise and recommend filters.

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。

Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when interacting with gcsfuse: decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size file, stat, and list caches, tune mount flags or config-file settings, apply workload profiles, keep ML checkpointing safe (rename atomicity, hierarchical namespace/HNS, close-time finalization, concurrent writers), or diagnose slow training, low throughput, or bill spikes with gcsfuse metrics. Covers mount semantics, gcsfuse CLI and config files, GKE gcsfuse CSI driver (Workload Identity principal:// bindings, profile StorageClasses, sidecar sizing), and Cloud Run volume mounts. Don't use for bucket administration or data management without a mount (google-cloud-storage-basics) or fully POSIX-compliant shared file systems (Filestore, Managed Lustre).

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。

四柱八字命理分析。通过交互式步骤收集出生信息（姓名、曾用名、阳历/农历生日、时辰、性别、出生地）， 排出四柱八字，参照经典命理典籍（穷通宝典、三命通会、滴天髓、渊海子平、子平真诠等）进行专业分析。 Use this skill whenever the user asks for 八字、四柱、命理、算命、Bazi、fortune telling、 birth chart analysis, or wants to know about their 八字命盘、运势、大运、流年. Triggers: "算八字", "看八字", "批八字", "排八字", "四柱", "命盘", "算命", "帮我看看八字", "我想算八字", "分析八字", "排盘", "bazi", "bazi analysis", "fortune telling", "birth chart", "算一卦", "看运势", "命运分析". 即使只是提到"算命"、"八字"而没有明确说要用skill，也应该使用此skill。

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。

Control Apple Music on macOS via the `clawtunes` CLI.

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。