408 件 ・ 関連度順
概要と使いどころ
AutoMCM-Pro industrial-grade math modeling agent (DeepSeek Harness binding). Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTeX inclusion, and structured human cross-validation at each pipeline stage. Use for both CUMCM (Chinese) and MCM/ICM (English) competitions.
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。
AutoMCM-Pro industrial-grade math modeling agent (Codex CLI binding). Supports AP (AI-led) and Manual (human-spec-led) dual modes with mandatory GitOps checkpoints, forced self-verification of all solver code before LaTeX inclusion, and structured human cross-validation at each pipeline stage. Use for both CUMCM (Chinese) and MCM/ICM (English) competitions.
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。
Inspect an unfamiliar repository, interpret a broad Markdown user journey at runtime, operate the real product through its supported web, API, CLI, desktop, or mobile surface, and produce an auditable pass, fail, or blocked judgment with screenshots, logs, recordings, and a step timeline when available. Use when asked to run smoke tests, validate an end-to-end user journey, dogfood a product, test a release candidate, or execute a non-deterministic workflow that may include authentication or human checkpoints. Do not use as a substitute for deterministic unit, integration, or scenario tests.
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 machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.
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。
Think and work like an expert Immunotherapy Scientist. Use when a task calls for Immunotherapy Scientist judgment. Reasons from antigen recognition and checkpoint circuits through CAR-T/bispecific design, ASTCT CRS/ICANS grading, flow cytometry release CQAs, iRECIST response assessment, COMPASS/TIDE biomarker modeling, and JACIE/FACT IEC accreditation while treating antigen escape, pseudoprogression, tonic signaling, and step-up CRS as first-class failure modes.
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 and operate Tencent Hunyuan video through the managed TokenHub HY-Video-1.5 API or official local HunyuanVideo repositories. Use for text-to-video, image-to-video, hosted job lifecycle, pricing and region planning, local checkpoint selection, hardware and acceleration, prompt design, licensing, safety, provenance, and delivery QA.
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。
Produce text-to-speech with Alibaba/Qwen Qwen3-TTS through DashScope/Model Studio or open-weight Qwen3-TTS checkpoints. Use when an agent must choose Qwen3-TTS models, voices, realtime versus non-realtime synthesis, voice cloning, voice design, instruction/prosody controls, multilingual or dialect speech, audio artifact handling, regional routing, pricing/privacy/licensing constraints, or production QA for narration, characters, assistants, audiobooks, ads, localization, or voice-enabled media.
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。
Plan, implement, and review Alibaba Wan video generation using Alibaba Cloud Model Studio/DashScope hosted APIs or official Wan 2.1/2.2 open-weight checkpoints. Use for Wan text-to-video, image-to-video, first/last-frame or continuation, reference-to-video, video editing, speech-driven video, character animation, regional deployment, billing, licensing, and production safety.
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 and edit synchronized audio-video with LTX-2.3 using the official hosted LTX API or official local/open-weight LTX-2 repository. Use for text-to-video, image-to-video, audio-to-video, retake, extend, HDR conversion, local inference, checkpoint selection, quantization, and LTX-specific production planning.
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。
Plan, generate, edit, reference, and quality-control still images with Kling AI's hosted IMAGE surfaces or Kuaishou's open Kolors checkpoints. Use for Kling IMAGE 3.0/3.0 Omni/O1/2.1 web, official Kling CLI/MCP or Open Platform integration, and local Kolors text-to-image, image-to-image, IP-Adapter, ControlNet, inpainting, or LoRA work. Do not use for Kling video, avatars, lip-sync, unofficial gateway APIs, or for assuming that current hosted Kling Image models are identical to the 2024 open Kolors weights.
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 in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when "langgraph, langchain agent, stateful agent, agent graph, react agent, agent workflow, multi-step agent, langgraph, langchain, agents, state-machine, workflow, graph, ai-agents, orchestration" mentioned.
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 training models across multiple GPUs or nodes, handling large models that don't fit in memory, or optimizing training throughput - covers DDP, FSDP, DeepSpeed ZeRO, model/data parallelism, and gradient checkpointingUse when ", " mentioned.
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 agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% by step 10. Build for reliability first, autonomy second. 2025 lesson: The winners are constrained, domain-specific agents with clear boundaries, not "autonomous everything." Treat AI outputs as proposals, not truth. Use when "autonomous agent, autogpt, babyagi, self-prompting, goal decomposition, react pattern, agent loop, self-correcting agent, reflection agent, langgraph, agentic ai, agent planning, autonomous, agents, langgraph, react, planning, reflection, guardrails, reliability, checkpointing" mentioned.
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。
AIGC 创作工作流 (AIGC 创作工作流 / AIGC Creative Workflow — 以「生成式 AI 视觉创作（图像 + 视频）的工程化创作流水线」为对象的认知操作系统：从「需求/概念（要做什么画面/镜头/风格）→ 模型与工具选型（Midjourney / Stable Diffusion·SDXL·Flux / ComfyUI / 可灵 Kling / 即梦 Jimeng / Runway / Vidu / Sora）→ Prompt 与参数设计（提示词工程、风格描述、负向、种子、CFG/步数/采样器、参考图）→ 可控生成（ControlNet / LoRA / IPAdapter / inpainting / 图生图 / 局部重绘 / 区域控制）→ 批量出图与筛选 → 精修与合成（放大/超分、修手修脸、PS/AE 后期、抠图合成）→ 图生视频/文生视频（首尾帧、运镜、时长、一致性、对口型）→ 商业交付与迭代复现（参数留存、工作流文件复用、版权与可商用判断）」的完整创作-工程-交付决策链。覆盖 (a) 第一性张力 — **可控性/工程化复现（ControlNet/LoRA/ComfyUI 节点工作流/固定种子与参数/可复现可迭代）⇄ 随机性/抽卡玄学（出图随机、prompt 玄学、抽卡刷图、靠运气）**；**审美/创意/艺术指导主导（人的审美判断、概念设计、构图、镜头语言、艺术总监能力——'模型是地板，审美是天花板'）⇄ 工具/模型/参数主导（堆模型能力、堆参数、堆 LoRA、以为换个大模型就行）**；**开源生态/本地可控（Stable Diffusion / ComfyUI / Flux / civitai / liblib 本地部署可定制可控可商用、显卡门槛）⇄ 闭源商业/易用黑盒（Midjourney / 可灵 / 即梦 / Runway 开箱即用但不可精控、按量付费、黑盒）**；**图像生成（T2I/I2I：Midjourney / SDXL / Flux）⇄ 视频生成（T2V/I2V：可灵 / Runway Gen-3 / Vidu / 即梦 / Sora，2024-2025 前沿从图迁移到视频）**；**生产力/商业量产（替代或增强传统设计/插画/电商/广告/影视分镜流程、降本提效、批量）⇄ 纯艺术创作/作者表达（个人风格、实验性、作品集）**；**效率/批量（一次出几十张筛选、商单走量、自动化 pipeline）⇄ 质量/精控（单张精修、商业可用级细节、修手修脸修穿帮）**。(b) 核心工作流 / pipeline（最标准、最易蒸高质量 + CLI 化）— 单图创作链：概念/参考收集（moodboard/风格定位/竞品）→ 模型工具选型（按可控性/风格/成本/可商用判断 MJ vs SD/Flux vs 国产）→ Prompt 与参数设计（主体/风格/光影/镜头/负向词/CFG/采样器/分辨率/种子）→ 首轮出图与方向筛选 → 可控迭代（ControlNet 控构图/姿态/线稿、LoRA 控风格/角色一致性、图生图重绘、inpainting 局部修）→ 放大超分与精修（高清放大/修手修脸/后期调色合成）→ 交付与参数留存（工作流文件/种子/参数复现）。视频创作链：分镜/脚本→首帧出图（图像链产出关键帧）→图生视频（运镜/时长/首尾帧/动态强度）→多镜头一致性（角色/场景/风格统一）→对口型/配音/配乐→剪辑合成→交付。ComfyUI 工程链：节点工作流搭建（加载器/采样/ControlNet/放大/面部修复节点）→ 参数化与复用→批量队列→工作流分享（civitai/openart workflow json）。(c) 工具栈 — 闭源图像（Midjourney v6/v7、DALL·E 3、Adobe Firefly、Ideogram、Recraft）、开源图像与底座（Stable Diffusion 1.5/SDXL/SD3、Flux.1 dev/schnell（Black Forest Labs）、ComfyUI（节点式）、Automatic1111/Forge WebUI、Fooocus）、可控生成插件（ControlNet、LoRA、IPAdapter、AnimateDiff、inpainting/outpainting、ReActor 换脸、面部修复 CodeFormer/GFPGAN、放大 ESRGAN/SUPIR/Topaz）、模型/资源社区（Hugging Face、Civitai、liblib 哩布、吐司 Tusi、openart）、视频生成（可灵 Kling、即梦 Dreamina/Jimeng、Runway Gen-3/Gen-4、Luma Dream Machine、Pika、Vidu、海螺 Hailuo、Sora、Wan 通义万相、MiniMax）、辅助（Magnific 放大、Krea、Photoshop/After Effects 后期、ChatGPT/Claude 写 prompt、reverse prompt 反推）。(d) 知识正典 — AIGC 创作 canon 横跨论文/工程/社区教程：奠基论文（DDPM、Latent Diffusion/Stable Diffusion（Rombach et al）、DiT、ControlNet（Zhang et al）、LoRA、DreamBooth、Textual Inversion、SDEdit、IP-Adapter、视频扩散 SVD/Sora 技术报告）、官方文档与模型卡（Stability AI、Black Forest Labs Flux、ComfyUI 文档、Midjourney docs、可灵/即梦官方教程、Hugging Face diffusers）、社区教程与工作流（ComfyUI 官方示例、civitai 文章、B站/YouTube 创作者长教程、openart workflow）、prompt 工程资源（Midjourney 风格库、提示词指南）。(e) figures/流派 — 模型/工具创造者（Midjourney David Holz、Stability AI Emad/Robin Rombach、Black Forest Labs（Flux，原 SD 团队）、ComfyUI comfyanonymous、ControlNet 张吕敏 Lvmin Zhang、AUTOMATIC1111、可灵/即梦/快手字节团队）、创作者 KOL 与教育者（Midjourney/SD 头部创作者、ComfyUI 工作流大神、AI 视频创作者、国内 B站/抖音 AIGC 教程作者、独立 AI 艺术家）、行业分析与评测（AI 工具评测、生成式 AI 创作生态观察者）。流派分歧：开源可控派（SD/ComfyUI/Flux 本地精控）vs 闭源易用派（MJ/可灵开箱即用）、工程化派（节点工作流/可复现/参数化）vs 玄学抽卡派（prompt 玄学/堆词/抽卡）、审美主导派（'模型是地板审美是天花板'）vs 工具主导派（堆模型堆参数）、图像派 vs 视频派、艺术创作派 vs 商业生产力派、国产工具派（可灵/即梦/liblib）vs 海外工具派（MJ/Flux/Runway）。(f) 行业话术/黑话 — 出图 / 抽卡 / 刷图 / 炼丹（训练 LoRA）/ 喂图 / 垫图（参考图/图生图）/ 控图 / 锁种子 seed / CFG / 采样器 sampler / 步数 steps / 重绘幅度 denoise / 提示词 prompt / 咒语 / 负向 negative / 权重 / tag / 大模型 checkpoint / 底模 / LoRA / ControlNet / 控线稿/openpose/depth / IPAdapter / inpainting 局部重绘 / outpainting 扩图 / 高清放大 / 超分 / 修手 / 崩手 / AI 味 / 风格 / 角色一致性 / 工作流 workflow / 节点 / 跑图 / 队列 / 文生图 T2I / 图生图 I2I / 文生视频 T2V / 图生视频 I2V / 首帧/尾帧 / 运镜 / 动态强度 / 时长 / 对口型 / 一致性 / 可商用 / 训练集 / 过拟合 / 翻车 / 穿帮。(g) 争议/批判 — 「版权与训练数据」（模型训练用未授权作品、生成图版权归属、可商用风险、洗图/伪原创）、「AI 替代创作者就业」（替代画师/插画师/设计师/摄影、行业冲击与转型）、「AI 味与审美趋同」（生成图同质化、套模板、缺乏原创审美）、「玄学 prompt 神话与割韭菜」（'咒语'神秘化、'7天 AIGC 变现/月入过万'付费课割韭菜、抽卡当能力）、「工具快速迭代与淘汰焦虑」（模型月月换、工作流频繁失效、追新疲劳）、「开源 vs 闭源之争」（可控可商用 vs 易用黑盒）、「质量天花板」（修手修脸穿帮、长视频一致性、可控性仍有限）。(h) 大量隐性创作手艺 + 审美 + 工程 + 沟通软技能（prompt 的描述功底与审美词汇、参数与采样的手感、ControlNet/LoRA 的组合控制经验、节点工作流的搭建与调试、批量筛选的审美眼力、修图合成的后期功底、镜头语言与运镜设计、角色/风格一致性的控制、商业需求的翻译与交付、版权与可商用的判断）是高 tacit、靠大量实操跑图 + 审美积累 + 工程调试经验的核心。水分极高（大量'咒语速成/一键变现/AI 绘画割韭菜'营销
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 the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.
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。
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.
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。
The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.
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 an activity flow / system architecture diagram as ONE self-contained, INTERACTIVE HTML+SVG page (2-pane app layout — left: diagram, default fit-to-view with zoom/pan; right: sidebar with explainer cards), styled like a real hand-drawn enterprise doc (Stripe/AWS-docs style — real brand logos for MongoDB/Odoo/n8n/etc. from a bundled Simple Icons library, neutral white boxes, sans-serif, no "AI neon" look), scroll-to-zoom, auto light/dark with a toggle button — clicking a flow (a legend chip, a line, or a step badge) highlights that flow with traveling dots along the arrows in their direction, a ping at the destination box, and a sidebar panel that slides out, while everything else dims; two-way arrows (OUT = solid blue / RETURN = dashed green) carry numbered step badges, colored by semantic meaning (red = auth checkpoint, purple = scheduled flow, amber = data pipeline), a small "hop" arc where two lines are forced to cross, dashed group regions, one explainer card per flow in the right sidebar. Use this skill ANY TIME the user wants to "draw a diagram", "draw a flow", "draw a system diagram", "redraw this so it's easier to follow", "interactive diagram", "two-way diagram", "request/response flow", "make a free-form HTML diagram" — even if they never say the word HTML. Especially good when both the request direction AND the response direction need to be shown, or when a templated tool (archify, mermaid) is too rigid. Do NOT use for data charts (bar/line/pie), and do not use when the user asks specifically for archify or mermaid.
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。
Plan, smoke-test, execute, checkpoint, publish, audit, and reproduce full ShellBench native benchmark campaigns across OpenClaw, Hermes, Codex, and Claude Code, including model and reasoning identity, pinned harness versions, n=3 qualification through n=6 research runs, S3 trace retention, and task-turn-tool-token-cost exports.
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。
Restore requested code changes or checkpoints.
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。
Preserve rollback before materially risky edits.
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。
Suede-affiliated recurring marketing workflow design for cadence, inputs, decision rules, checkpoints, failure states, and measurable outputs. Use when the user wants repeatable ad-fatigue, content-refresh, churn-watch, ranking-drop, or weekly-review loops. NOT FOR: one-off tactic ideation (use suede-marketing-ideas), experiment design (use suede-ab-testing), or creating a live automation without explicit scheduling authority.
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 phased implementation roadmaps with Epic/Story/Task breakdown, effort estimates, and validation checkpoints. Use when cto-architect needs to create actionable technical roadmaps from architecture designs.
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 writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU
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。