「sam」の検索結果

Use when a PERSONAL brand needs AUDIO — voice cloning with ElevenLabs, Murf, or PlayHT, podcast production, audiobooks, and voiceover: short voiceover for TikTok and Reels, a 30 to 60 minute podcast format, and a 1-to-10 repurpose turning one episode into ten clips, in English with US, UK, AU, and SG accents. Trigger on 'voice clone', 'ElevenLabs', 'start a podcast', 'audiobook narration', 'AI voiceover for my videos', 'I hate re-recording the same intro'. Not for — video with a talking-head avatar, see `24-ai-avatar-production-global`; the script being read aloud, see `04-script-video-global`; written long-form posts, see `26-thought-leadership-content-global`.

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 positioning needs defining or sharpening — a statement built on Promise, Proof, and Path, a differentiation matrix against competitors, category entry points, a three-level message hierarchy, and tagline directions. Trigger on 'positioning', 'positioning statement', 'what makes us different', 'USP', 'why should customers choose us over them', 'we sound the same as everyone else'. Also use when the user can list features but not a reason to pick them. Not for — competitor teardown research, see `08-competitor-research-global`; how the brand sounds in writing, see `35-brand-voice-global`; the offer and its value stack, see `31-offer-design-global`; the launch built on it, see `59-go-to-market-global`.

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。

Dung khi can test co ky luat de biet phuong an nao thang that — chon dung mot bien de test, viet gia thuyet, tinh sample size, setup tracking, doc y nghia thong ke va ghi test log cho ads, landing page, email hoac gia. Kich hoat khi user nhac 'A/B test', 'split test', 'test creative', 'test copy', 'test landing', 'chay bao lau moi du ket luan', 'ban nao thang', 'test xong khong biet doc ket qua', 'ket qua co dang tin khong'. Khong dung cho — so dang xau va can chan doan nguyen nhan thi dung skill 03-danh-gia-hieu-suat; nhan ngan sach cho creative da thang thi dung skill 55-scaling-ads; ra soat toan bo trang khong ra don thi dung skill 68-cro-audit-trang.

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 a VALID experiment instead of a guess — hypothesis, one variable, sample size and runtime math, statistical significance, primary versus secondary metrics, multi-arm designs, and a results template, across Optimizely, VWO, and native Meta and Google tests. Trigger on 'A/B test', 'split test', 'how long should I run the test', 'is this result significant', 'test two versions', 'which creative is actually better'. Also use when a winner was declared after two days on tiny numbers. Not for — scaling the proven winner, see `55-scaling-ads-global`; analyzing data already collected, see `13-data-analysis-global`; auditing the account, see `21-ads-audit-global`.

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 ONE static image needs a full brief for a designer or photographer — visual objective, concept and mood, composition, overlay copy, colors and fonts read from the brand guideline, per-channel dimensions, deliverables, and approval criteria. Trigger on 'image brief', 'banner brief', 'thumbnail brief', 'brief for the designer', 'how should this graphic look', 'the design came back wrong again'. Also use when the user has a post idea and needs to explain the visual. Not for — a multi-slide sequence, see `43-carousel-brief-global`; tool-level production steps in Canva or Figma, see `45-design-tool-brief-global`; generating the image with AI, see `30-design-master-global`; an urgent same-day swap, see `48-quick-visual-brief-global`.

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 LIVE campaign needs a new asset the same day — creative fatigue, CTR decay, climbing frequency, or a new angle to test: stripped-down input, duplicate the winning creative and change only what is listed, a one-page template, and a hard SLA so the designer ships in 2-4 hours. Trigger on 'quick brief', 'need an asset fast', 'creative fatigue', 'swap the creative today', 'frequency is too high', 'the ad is dying and we need a new one'. Not for — planning assets before launch, see `41-campaign-asset-list-global`; a full concept brief with time to spare, see `42-image-brief-global`; resizing an existing master, see `50-asset-resize-global`; raising budget on a winner, see `55-scaling-ads-global`.

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 bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

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。

Transform a user-uploaded photograph into one horizontal collectible memory card with a large quiet editorial illustration, six integrated journaling-sticker motifs, three small English keywords beneath the left illustration, tactile paper grain, and deliberately clumsy flat color fields. Use when Codex needs to P图, edit, redraw, stylize, or turn a travel, street, landscape, lifestyle, portrait, or pet photo into a minimalist postcard-like card or sticker-card in this visual language. Preserve recognition through one same-medium identification anchor and optionally one exact place-defining landmark text shown once; never retain an unintended photorealistic patch, signature, or watermark.

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。

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

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。

Operately frontend data fetching with TanStack Query. Use when adding or changing page loaders, model hooks, Api.* calls, mutations, useLoadedData, Pages.useRefresh, or any web UI backend request. New code must use TanStack. When fixing or extending an existing surface, migrate that surface's API calls to TanStack in the same change.

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 Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper…

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 Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.

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 Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.

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。

Easter-egg alias for /catchup. Same return-from-absence briefing, squeezier name. Use exactly like /catchup — all flags pass through unchanged.

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。

加权采样算子。读取JSONL记录，按数值型权重字段执行随机采样，支持有放回和无放回两种模式。当用户提到加权抽样、按权重抽样、优先级采样、重要性重采样等需求时使用此skill。即使用户没有明确说出“加权采样”，只要任务涉及按记录权重选择样本，就应该使用此skill。不负责按类别分层均衡、普通随机采样或文本内容过滤。

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。

系统采样算子。按照固定间隔从数据中进行系统采样，适用于时间序列数据或需要均匀分布样本的场景。 当用户提到系统采样、等距抽样、按间隔取样、均匀抽样等需求时使用此skill。 即使用户没有明确说出"系统采样"，只要任务涉及从有序数据中按固定步长抽取样本，就应该使用此skill。 不负责分层采样或随机采样。

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。

时间窗口采样算子。读取JSONL时间序列记录，按指定时间窗口分组后在每个窗口内均匀抽取样本。 当用户提到按天抽样、按小时抽样、周期性抽样、时间窗口采样等需求时使用此skill。 即使用户没有明确说出"时间窗口采样"，只要任务涉及按时间粒度分组后抽样，就应该使用此skill。 不负责时间字段清洗、时间聚合统计或异常检测。

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 needs to plan, de-risk, or ground a software engineering / computer science undergraduate thesis from a real codebase before final writing. Trigger for requests such as "根据项目写毕业论文", "先做论文大纲", "用真实项目材料规划论文", "检查论文是否脱离代码", "根据检测报告降查重", "根据AIGC报告改写定稿", "继续在手改初稿上改", or when an existing draft thesis must be reworked against a school format sample. Produces an evidence-backed outline, chapter rewrite plan, figure plan, and handoff package for academic-paper-composer.

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。

Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for 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。

Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.

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。

OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries

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。

Otonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla. Budget ve zaman limiti ile kontrol altinda tutulan tam otonom PR pipeline'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。

Time-series database implementation for metrics, IoT, financial data, and observability backends. Use when building dashboards, monitoring systems, IoT platforms, or financial applications. Covers TimescaleDB (PostgreSQL), InfluxDB, ClickHouse, QuestDB, continuous aggregates, downsampling (LTTB), and retention 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。

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

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。