2,484 件 ・ 関連度順
概要と使いどころ
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。
Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries. Use this skill whenever the user wants to create, generate, or design AWS architecture diagrams, cloud infrastructure diagrams, or system design visuals. Also triggers for requests to visualize existing infrastructure from CloudFormation, CDK, or Terraform code. Supports two modes: analyze an existing codebase to auto-generate diagrams, or brainstorm interactively from scratch. Exports .drawio files with optional PNG/SVG/PDF export via draw.io desktop 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。
把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条流）， 隐私保证来自结构，不来自枚举。 难点不在容器 tag，在**看不见的那几层**：x264 把完整编码参数写成 SEI 塞在码流里、 AAC 把版本号写进 DSE、avc1 的 compressorname 里还有一份——`ffprobe` 一个都看不见。 五个藏身处逐一堵死，每一处都有实测。 默认 `--mode copy`：**画面逐字节照搬**（cmp 验证过），只重编音频，53 秒的片子 1.3 秒跑完； `--mode encode` 完整重编码，多杀掉码流域的东西。 验收不靠声称：把源片所有元数据字符串当「针」，在输出文件里做**字节级扫描**， 扎到一根就红。12 道门全部由脚本确定性检查。 零依赖、零 API key，只要 node 和 ffmpeg。 Use when asked to 清元数据、去元数据、抹掉视频信息、视频隐私、去水印信息、 strip video metadata、remove exif from video、scrub video。
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 AWS solution architecture for startups focusing on serverless, scalable, and cost-effective cloud infrastructure with modern DevOps practices and infrastructure-as-code
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。
When you want to create, adapt, or update an Agent Skill (Claude Code, Codex, Cursor, and other hosts) in one of your repos (listed in ~/.config/makerskills/skillify/repos.yaml; defaults to makerskills). Modes — CREATE (from chat, video, dump, or scratch) turns a workflow into a new skill. ADAPT ports an external skill with keep/adapt/add classification, license check, and attribution. UPDATE improves existing skills from learnings with cross-skill propagation, memory-vs-skill triage, and semver. Checks new skills for host portability. Triggers on "/skillify," "create a skill," "make this a skill," "skill from this chat," "adapt this skill," "port this skill," "fork this skill," "update X skill," "apply this to the relevant skills," "propagate this learning," "improve [skill]," "fix [skill]." Part of the -ify trifecta (skillify / toolify / loopify).
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。
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDE_DECK_REPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand gradients, optional sections for "where am I" context, and speaker notes. Inspired by zarazhangrui/frontend-slides — "show, don't tell" for narrative (presents 3 angles, you pick) plus density modes (speaker-led vs reading-first). Four modes — new (draft from brief), update (modify existing, with overflow guards), ppt (convert legacy PPTX → React deck), export (Playwright snapshot existing React deck to standalone HTML, PDF, or Vercel URL — keeps brand). Triggers on "/slide-deck," "/slides new," "/slides export," "/slides update," "/slides ppt," "draft a deck," "deck for [topic]," "talk on [topic]," "keynote on [topic]," "internal deck for [audience]," "convert this pptx," "export this deck."
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 patterns for multi-platform exports including export templates (Windows/Linux/macOS/Android/iOS/Web), command-line exports (headless mode), platform-specific settings (codesign, notarization, Android SDK), feature flags (OS.has_feature), CI/CD pipelines (GitHub Actions), and build optimization (size reduction, debug stripping). Use for release preparation or automated deployment. Trigger keywords: export_preset, export_template, headless_export, platform_specific, feature_flag, CI_CD, build_optimization, codesign, Android_SDK.
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 patterns for multi-platform exports including export templates (Windows/Linux/macOS/Android/iOS/Web), command-line exports (headless mode), platform-specific settings (codesign, notarization, Android SDK), feature flags (OS.has_feature), CI/CD pipelines (GitHub Actions), and build optimization (size reduction, debug stripping). Use for release preparation or automated deployment. Trigger keywords: export_preset, export_template, headless_export, platform_specific, feature_flag, CI_CD, build_optimization, codesign, Android_SDK.
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。
Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and temporal-aware super-resolution (SeedVR2, the newer FlashVSR) with the downscale-first restore pipeline; RIFE/FILM frame interpolation via the BUILT-IN ComfyUI 0.26 FrameInterpolate (rife_v4.26 in models/frame_interpolation/) or the ComfyUI-Frame-Interpolation pack; 2x/4x scaling, VRAM tiers, VHS encode. Captures the classic downscale→SeedVR2→RIFE recipe and the current 2026 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。
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.
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。
Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, gotchas, and the extend→upscale handoff.
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。
SwiftData class inheritance patterns for hierarchical models with type-based querying, polymorphic relationships, and when to choose inheritance vs enums. Use when designing SwiftData model hierarchies.
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。
SwiftData skills — class inheritance patterns for hierarchical models, type-based querying, polymorphic relationships, and inheritance-vs-enum decisions. Use when designing SwiftData model hierarchies.
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。
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
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。
Swift language patterns and best practices including concurrency, performance, and modern idioms. Use for Swift language-level code review or architecture guidance.
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 ONLY when calling the `browser_execute` tool or driving a real browser via the Chrome DevTools Protocol. Required reading before the first `browser_execute` call in a session. Covers the three connection methods (local Chrome with remote debugging, isolated debug-port profile, Browser Use cloud), the in-process `session` / `console` snippet model, attaching to a page target, common CDP commands, the per-project `.bcode/agent-workspace/` for reusable scripts, and screenshot auto-attachment.
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。
Start a substantial build with Codex on Crack. Inspect the user's own configured models and readiness, recommend a lead/worker/tool shape with reasons, and let the user decide before work starts. Use before delegating; keep small or solo tasks direct.
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。
Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project rules, Agent system prompts, Skills, delegation briefs, and Task and Watch messages — using real run evidence. Use when an Agent misbehaves (stalls, over-asks, over-reaches, ignores or over-applies a rule), after a model or backend change, or when the user asks to review, clean up, or tighten prompts.
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。
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full ASM JSON, flattened CSV for easy import, and exportable Python code for data engineers. Common triggers include converting instrument files, standardizing lab data, preparing data for upload to LIMS/ELN systems, or generating parser code for production pipelines.
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 responsive HTML email has to render correctly in every client — table-based structure, inline CSS, 600px max width, dark mode handling, quirks for Gmail, Apple Mail, Outlook and Yahoo, bulletproof buttons, and a pre-send test checklist, shipping a self-contained .html file to paste into Klaviyo, Mailchimp, HubSpot, or Brevo. Trigger on 'HTML email', 'code an email template', 'responsive email', 'why does my email break in Outlook', 'email dark mode is broken', 'the newsletter looks wrong on mobile'. Not for — sequence strategy and subject lines, see `14-email-marketing-global`; a web page, see `12-landing-page-brief-global`; brand colors and fonts, see `46-brand-guideline-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。
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
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。
Modern JavaScript (ES2022+) patterns for clean, maintainable code. Use when working with modern JavaScript features like optional chaining, nullish coalescing, or ESM.
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。
Configure ViewModel state emission with StateFlow, SharedFlow, and sealed UiState classes in Android. Use for state modeling and sharing policies; defer generic lifecycle collection, navigation-event plumbing, Hilt injection, test code, and configuration-change recipes to their specific 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。
Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.
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。