「ara」の検索結果

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system simultaneously, when establishing file ownership to prevent merge conflicts in a shared codebase, when designing interface contracts so parallel implementers can build against each other's APIs before they are ready, or when deciding whether to use vertical slices versus horizontal layers for a full-stack feature.

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。

Query the Malpedia API to look up malware family aliases and naming (platform.family_name), pull community/vendor YARA rules, link families to threat actors, and map family relationships such as loader-payload chains and shared authorship. Use when researching a malware family's aliases, lineage, or actor attribution, or when sourcing YARA rules for detection.

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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。

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

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 training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

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。

Planificación persistente basada en archivos para tareas multipaso de agentes de IA. Mantiene task_plan.md, findings.md y progress.md en disco; los hooks del ciclo de vida inyectan contexto seleccionado de planificación del proyecto. La recuperación automática solo lee los archivos de planificación del proyecto. session-catchup.py --metadata, solicitado de forma explícita, puede inspeccionar metadatos locales de sesiones del mismo proyecto; --replay puede emitir extractos limitados y enmarcados con nonce. El modo con gate opcional solo puede solicitar que el host continúe si este lo admite y nunca ejecuta comandos declarados en Markdown. El skill no tiene ninguna ruta de carga por red. Úsalo para investigación o trabajo que requiera 5 o más llamadas a herramientas.

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。

Daily reusable-session flaky-test triage for {{target_repo}}. Pulls CI run history from GitHub, scores each test's non-determinism against a persistent per-test ledger, and once a test reaches {{quarantine_threshold}} opens a quarantine PR (skip + reason, never delete) plus a running tracking issue, and posts a summary to {{alert_channel}}. Never merges.

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。

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

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。

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.

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。

Coordinate several coding agents in parallel through Superset, each in its own workspace, with follow-ups, progress reads, dependency tracking, and structured results. Use when the user asks to delegate, parallelize, fan out, or split up coding work across agents, workspaces, or hosts, hand work between agents, or monitor workers, including "spin up agents for each of these", "run these in parallel", "what are my workers doing". Not for ordinary single-agent workspace, task, or automation management.

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。

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

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 training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

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。

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

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。

Trademark clearance first pass — knockout + similar-marks check producing a flag list, not a clearance opinion. Use when a new mark is proposed, when asked whether a mark is available or to run a knockout search, or when assessing likelihood-of-confusion factors before a full professional search. This skill never concludes a mark is clear.

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。

Create data fetching services with circuit breaker pattern for API resilience, including a first-class pattern for building optional query parameters via URLSearchParams. Services handle fetch, cache, retry, optional filters, and expose typed data to panel components.

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。

Design and implement parallax scrolling and scrollytelling data visualizations. Use when the user asks for parallax scrolling, scrollytelling, scroll-driven timelines, sticky graphics, Scrollama, ScrollTrigger, ScrollTimeline, view timelines, rich-media timelines, moviescrollers, scroll-scrubbed charts, staged narrative reveals, or interactive visual stories where scrolling changes a data visualization or media scene.

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。

Draws flat vector illustrations as SVG cards (480x360): slim, long-limbed people acting out one design or coding moment with one hero prop. Identified by no outlines on big shapes, thin white fold strokes as the only shading, navy only for hair, sneakers and a few hairlines, small heads (about 1:7) with big hands and white sneakers, and sparse floating confetti with no ground line, in lavender, indigo, sunshine yellow, coral and mint. Covers the measured palette, stroke numbers, character construction (tapered limbs, separated fingers, thumb side), poses, props, composition and a tested parts kit. Use when asked for flat illustrations, flat vector people, outline-free or no-outline characters, modern or corporate flat art, empty states, onboarding screens, 404 or error pages, coming-soon pages, blog headers, feature spots or marketing cards.

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。

Draws original hand-authored SVG spot illustrations in an outlined cartoon style for design and coding subjects. Identifying traits: a warm near-black ink outline on every flat fill in three weights (2.5 / 2 / 1.5 px), tapered ink slivers for folds, brows and finger splits, big-headed characters with huge white eyes, thick brows, open smiles and pink blush, blob hair with white highlight dashes, and a small decor set of "+" sparkle crosses, outline rings, squares and coloured dots on a transparent card. Covers one character with one hero prop, gripping and holding hands, sneakers, clothing folds and UI props. Use when someone asks for an outlined, inked, comic, sticker or doodle-style cartoon, a friendly character or mascot, or a spot illustration for an empty state, onboarding, 404 or error page, success state, blog header, feature spot or marketing card.

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 extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent should infer three product-relevant directions and propose six independent candidates for 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。

Share state between components that don't have a direct parent-child parameter relationship, using cascading values, scoped services with change events, or CascadingValueSource via DI. USE WHEN the user needs a CascadingParameter or CascadingValue that works across render mode boundaries, a shopping cart or notification count accessible from multiple pages, a theme or user preference cascaded app-wide, or when components in different parts of the tree must react when shared data changes. Also USE WHEN cascading values aren't reaching interactive children in per-page interactivity mode, or when the user needs to understand scoped vs singleton service lifetime for state on Blazor Server. DO NOT USE for direct parent-child parameter passing or EventCallback (see author-component), for persisting state across prerender-to-interactive transitions (see support-prerendering), or for service abstractions for data fetching in Auto/WebAssembly (see fetch-and-send-data).

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。

Polishes academic English paragraph by paragraph, reviewing grammar, word choice, voice, coherence, and sentence structure. Outputs revision suggestions alongside polished text. Triggered by phrases like 'polish this paragraph,' 'check the grammar,' 'rewrite in academic English,' or keywords like manuscript editing, SCI polishing, and journal submission editing.

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。

给任何故事里的角色真出参考图（小说改编、自己原创的故事、单独设计一个角色都行，不需要小说原文）： 一段话描述角色，拆成分层字段、补全后确认， 先出一张正面全身锚点，其余视图（大头照、90° 侧面、背面、细节、45° 大头照）都只参考这张锚点， 按需分档出图。每张图带标识、可单独重出，重出后自动标出哪些图过期。 支持 Qwen Image（ComfyUI）、codex 内置出图、OpenAI Images API（GPT Image 2）和自定义命令，主图与派生图可以使用不同模型。 产出 asset.json + 一组 PNG + 双击就能开的报告。零依赖。 只要提示词、不出图的话使用 novel-characters。 Use when asked to 出角色图、做角色参考图、给我的角色出图、定妆照、真出三视图、character reference images。

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。

Explicit-only last resort. Draws game art from code, with no image model - pixel sprites from a PixelSpec, flat vector props, UI and icons from portable SVG, rigged characters with planted feet, FX with a JS runtime, seam-proven autotiles, playable top-down layouts with collision, stylized parallax and ambient plate motion - palette-exact, with QA and review sheets. Use only when the user explicitly asks for code-drawn art, or when generate2dmedia route_media.py finds no image or video route (no-route, exit 3). Never the default - image generation (generate2dsprite, generate2dmap, video2dsprite) comes first for characters, props, maps and FX. Not for painterly, detailed or likeness art, HD-2D plates or realistic fire, smoke or water. Always disclose the result as code-drawn.

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。

Make game-ready 2D characters, creatures, props, icons and FX as master stills, sprite sheets or animation clips. Plan size, motion and finish; generate the art (image generation is the default, through generate2dmedia route_media.py - the API when a key is configured, else the local Codex or Grok CLI); approve one master still per character; then key, slice, register, scale, palette, QA and export frames for a game engine (Aseprite JSON, Godot SpriteFrames or Sprite3D). HD finish by default, pixel finish on request. Character animation is one image-to-video clip per action from the master (video2dsprite); sheets are for FX, icons and props. Use for sprites, masters, sheets, frame-by-frame animation and packaging frames from any source. Not for maps, tiles or backgrounds (generate2dmap), video clips (video2dsprite), code-drawn art (codeart2d, only on request) or calling an image or video API by itself (generate2dmedia).

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。