'fuse' 검색 결과

Normalize read-depth copy-ratio profiles and segment them into copy-number regions using circular binary segmentation (CBS, DNAcopy), hidden Markov models, HaarSeg, and fused-lasso methods. Covers GC-content, mappability, and replication-timing (wave-artifact) bias correction, panel-of-normals/PCA denoising, diploid-baseline centering, and algorithm selection by sequencing depth and event size. Use when choosing a segmentation algorithm, correcting depth bias, diagnosing oversegmentation or a mis-centered baseline, tuning CBS or HMM parameters, or understanding why a downstream CNV caller produced fragmented or shifted segments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Block a sender so their messages are dropped before decryption (and the relay is told to refuse their resends); re-allow one with `--remove`, or list blocked senders with `--list`. Use to stop unwanted or abusive mail from a specific sender, undo a block, or audit your block list. If the sender is not specified, ask with AskUserQuestion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Refuses "flaky" as a diagnosis. Turns an intermittent failure into a reproduction by isolating it from the environment, naming the variable that controls it, forcing that variable, and measuring before and after with enough runs to count. Separates real defects from environment contention with evidence, and never retries to green or widens a threshold. Use when a test, performance check, or deploy step fails intermittently or passes on rerun.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Explain a configuration file and its key options. Use when a junior developer is confused by a config file.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use before and after calling rollback_release - what a rollback restores per delivery mode, when a schema change makes a code rollback unsafe, how to work and report manual_steps, and what to do when rollback_release refuses

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off a reference identity, garbles audio after a latent upscale, or refuses to run on a build that looks current.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Hybrid search — BM25 keyword + dense vector fused with Reciprocal Rank Fusion. Use when queries have specific identifiers, code symbols, or proper nouns that pure semantic search might miss.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design a variation theory task using contrast, separation, and fusion to teach critical features of a concept. Use when students confuse similar concepts or fail to discern key distinctions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Find, evaluate and install a ForgeCat profile. Use when the user wants to browse the registry, compare profiles, install one into a project or a home-target agent, or when an install is refused.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis, prompt/completion logging, model comparison dashboards, and AI-specific tracing (Langfuse, Helicone, Lunary, OpenTelemetry GenAI) / Panduan ahli observabilitas LLM di produksi — pelacakan biaya token, pemantauan tingkat halusinasi, analisis latensi, logging prompt/completion, dashboard perbandingan model, dan tracing khusus AI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Stop the background HTTP registry server started by /start-http-registry — TaskStop / KillShell by the recorded task ID, plus a /proc cmdline-scan fallback for minimal-tool sandboxes with no ps/lsof/pkill/fuser. Referenced by every warp deploy/update skill that starts the registry.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Start, continue, keep, pause, copy, watch and stop authorised Anabasis v2 campaigns through `bun run runs`: launch a campaign under a name, go on with one from its log on another login or commit, keep one going across logins until it ends on its own terms, pause one at a clean point, copy a stopped one to another worktree, move one to another host, read each run's status and each login's room, reach the other hosts, and stop one and release what it held. Use when the operator asks to start, launch, resume, continue, move, keep, pause, copy or stop a campaign or a run, which logins have room, how the runs stand on any host, whether a campaign is ready for its next move, or why a move was refused. Owns the run's life on the host; run-improvement-campaign reads the table, and whole-run-investigation reads what a run did.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Put a change on the one open stack of Anabasis v2 pull requests: find the real top, keep local work while moving to it, decide between appending and a new pull request, shape commits that each pass alone, run the checks CI runs (by hand where the runners do not), publish through the gating pre-push hook, write the body, repair your own children when a parent moves, and land a stack with `bun run land`. Use when asked to open, append to, stack, restack, rebase, hop to the latest head, sanitize or land a pull request, or when a push, a hook or a base refuses. v1's stack-hop and setup-pr in one.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against references/review-rules.md, traces call paths for dead code). Reports findings grouped by severity, flagging what to fix before submitting (blocking issues + dead code) vs what to leave for the actual review. Report-only — does not edit files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format, or converting weights for a new version of an already-supported model.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and maintain a provenance-clean proof library — inventory every real proof asset (analytics, reviews, permitted testimonials, case studies, press, certifications), categorize it, rewrite each cleared item in 3 lengths, fuse top assets with narrative, and gate everything through FTC testimonial rules before it can ship. Use when "proof library", "gather our proof", "authority builder", "collect testimonials", "social proof assets", "proof points for the sales page", "what results can we claim", or any request to assemble evidence for marketing claims. NEVER invents proof — missing proof is reported as a gap.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

当用户想要在 WorkBuddy 上完成每日签到（获取签到积分）时使用此技能。若 WorkBuddy 未运行则自动启动，使用 Playwright 通过 CSS Selector 定位 DOM 元素并点击：先点击左下角用户菜单（class="user-menu"），等待 2 秒后，再点击「立即领取 →」按钮（class="daily-checkin-banner-action"）完成签到。触发关键词包括"签到"、"WorkBuddy签到"、"每日签到"、"打卡积分"等。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate methods.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to flatter. Use to ideate, validate, scope, architect, or plan a product, feature, startup, or app before any code is written. Invoke by persona name or acronym to summon one expert, or with no argument to run the full lifecycle end to end.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Clean and normalize messy CSV/TSV files - fix malformed rows, inconsistent headers, mixed encodings, stray delimiters, and duplicated records - and deliver a valid, verified file. Use when the user mentions a broken, messy, or malformed CSV, a file a spreadsheet tool refuses to open, or asks to deduplicate or normalize tabular data. Do not use when the deliverable is analysis or a chart rather than a cleaned file, or for Excel-native features like formulas and pivot tables.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implement a generative diffusion model (DDPM or score-based) with noise scheduling, U-Net architecture, training loop, and sampling procedures including DDIM acceleration. Use when building a generative model for image, audio, or molecular synthesis; implementing DDPM from a research paper; adding a custom noise schedule or conditioning mechanism; replacing a GAN-based generator with a diffusion alternative; or prototyping before scaling with production frameworks like diffusers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Coordinate safely with a peer interactive session sharing the same git worktree — check first whether a separate worktree removes the problem, then declare path and branch scope before the first edit, survive a contended index lock, and review the whole branch before opening a PR. Activate when starting work in a repository that may already be occupied, when a git command fails with `index.lock: File exists`, when `guard:snapshot` refuses because a snapshot already exists, or when a commit turns out to contain a file this session never edited. When one session leads and the other supports, divide the labour by shape and re-derive every reported number against a named revision before citing it. Distinct from subagent concurrency: a peer session cannot be bracketed, because no baseline exists from before its edits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.