'deepseek' 검색 결과

网文写作 (网文写作 (Chinese Web Novel Writing) — 中国网络文学的「连载长篇商业小说创作工艺」认知操作系统：从「定方向（频道/流派/题材）→ 立意与金手指设计 → 大纲与人物设定 → 开局黄金三章 → 日更连载与节奏控制（爽点/期待感/钩子/断章）→ 读者数据反馈与调整 → 完本与 IP 改编」的完整创作-连载-变现决策链。覆盖 (a) 第一性张力 — **读者数据驱动/即时反馈（追读率、订阅、追订、月票、收藏、章评、卡点数据）⇄ 作者表达/文学性（个人审美、慢热、留白、文笔）**；**爽文/套路化/工业糖精（爽点密度、装逼打脸、金手指、无敌流、爽感经济）⇄ 慢热/反套路/精品化（铺垫、群像、立意、文青向）**；**男频（玄幻/仙侠/都市/历史/科幻/游戏/系统流/无限流/凡人流，起点/番茄系，重设定与战力体系）⇄ 女频（古言/现言/穿越/重生/宫斗/种田/快穿/无限流/言情，晋江系，重情感与关系/人设）**；**付费订阅模式（起点/晋江，千字几分订阅+全勤+打赏+月票，养老书/精品）⇄ 免费阅读模式（番茄/七猫，平台买断/流量分成，强开局强爽点强节奏，走量）**；**长线连载/养书（百万字+、慢节奏铺世界观）⇄ 强开局/快节奏（黄金三章定生死、前一万字留人）**；**个人风格/品牌作者（大神、IP、粉丝向）⇄ 工业化/编辑导向（迎合榜单/编辑改稿/数据调优/AI 辅助）**。(b) 核心工作流 / pipeline（最标准、最易蒸高质量 + CLI 化）— 通用链：选频道与流派（看平台榜单/读者画像/自身擅长）→ 立意与核心设定（金手指/世界观/主线冲突）→ 人物与关系设计（主角金手指与成长弧、反派、配角、cp）→ 大纲（主线+支线+卷纲+细纲）→ 黄金三章/开局（代入感、爽点前置、悬念钩子、信息密度）→ 签约与上架（编辑沟通、签约合同、上架节奏）→ 日更连载（码字速度、存稿、断章艺术、节奏曲线、卡文处理）→ 读者运营（章评互动、本章说、读者数据看板、追读率分析）→ 调整与救书（数据扑街诊断、改大纲/换爽点/加节奏）→ 完本与变现（完本福利、IP 改编影视/动漫/游戏/有声/漫画）。(c) 工具栈 — 写作软件（壹写作、码字猫、橙瓜码字、墨者写作、汤圆/小黑屋专注码字、Scrivener、WPS/Word）、设定与大纲管理（壹写作设定卡、幕布/思维导图、Excel 人物关系表、世界观 wiki）、平台作家后台与数据（起点作家专区、晋江作者后台、番茄作家助手、追读/订阅/章评数据看板）、AI 辅助（豆包/Kimi/DeepSeek 辅助起名/扩写/查重/灵感、AI 写作工具争议）、查重与敏感词（写作软件内置敏感词检测、防抄袭查重）、灵感与素材（起点点娘/番茄/晋江榜单、龙的天空论坛、设定集/资料库）。(d) 知识正典 — 网文创作 canon 偏少且实践导向，散见于：平台官方写作指南（起点写作学院/晋江写作经验帖）、大神访谈与直播（作者本人谈创作）、网文写作教程书（《网络小说写作指南》类、编辑出的方法论）、网文研究学术（邵燕君《网络文学经典解读》、北大网络文学研究论坛、中国作协网络文学研究）、龙的天空/起点作家交流区的经验长帖、经典传统编剧/小说理论的借用（《故事》Robert McKee、《救猫咪》、《千面英雄》英雄之旅，但须辨明与网文连载工艺的差异）。(e) figures/流派 — 男频大神（唐家三少、天蚕土豆、辰东、我吃西红柿、猫腻、烽火戏诸侯、爱潜水的乌贼、忘语/凡人流、会说话的肘子、爱吃西红柿等）、女频大神（晋江系如 priest、墨香铜臭、藤萍、Twentine、尾鱼、丁墨等，须注意女频一手访谈相对少）、编辑/写作导师/网文研究者（起点/晋江资深编辑、网文培训讲师、邵燕君等学者）、平台与产业观察。流派分歧：付费精品派 vs 免费走量派、爽文工业派 vs 文青慢热派、男频战力体系派 vs 女频情感关系派、套路复用派 vs 反套路创新派。(f) 行业话术/黑话 — 黄金三章 / 开局 / 金手指 / 爽点 / 爽文 / 装逼打脸 / 扮猪吃虎 / 期待感 / 代入感 / 龙傲天 / 玛丽苏 / 杰克苏 / 系统流 / 无限流 / 凡人流 / 种田文 / 穿越 / 重生 / 快穿 / 无敌流 / 升级流 / 后宫 / 单女主 / 群像 / 主角光环 / 世界观 / 设定 / 战力体系 / 力量体系 / 大纲 / 细纲 / 卷纲 / 主线 / 支线 / 伏笔 / 断章 / 卡文 / 太监（弃坑）/ 存稿 / 日更 / 万更 / 码字 / 手速 / 追读 / 追订 / 订阅 / 均订 / 首订 / 全勤 / 月票 / 推荐票 / 打赏 / 盟主 / 收藏 / 上架 / 签约 / 入V / 三江 / 强推 / 上强推 / 扑街 / 仆街 / 数据 / 本章说 / 章评 / 水字数 / 注水 / 毒点 / 爽点密度 / 节奏 / 钩子 / 反转 / 高潮 / 番茄 / 七猫 / 起点 / 晋江 / 飞卢 / 男频 / 女频 / 频道 / IP / 改编 / 网大 / 有声 / 漫改 / 精品 / 老白（老读者）/ 小白文 / 大神 / 萌新作者 / 太监了 / 切书 / 完本 / 番外。(g) 争议/批判 — 「数据/榜单驱动 vs 文学性」（追读率绑架创作、爽文工业糖精化、注水水字数）、「套路化 vs 原创」（流派套路复用是高效还是同质化）、「免费阅读模式对生态的冲击」（番茄/七猫买断+流量分成压低作者收入、走量伤害精品）、「AI 写作工具」（AI 辅助 vs AI 代写、平台对 AI 文的态度、查重与版权）、「抄袭/融梗」（融梗与抄袭边界、调色盘、晋江抄袭风波）、「作者权益与平台」（合同霸王条款、买断 vs 分成、断更违约）、「幸存者偏差」（极少数大神年入千万 vs 绝大多数作者月入几百/扑街/太监，暴富叙事掩盖底层困境）、「快餐化与精品化」（短篇/微短剧化 vs 长线养书）。(h) 大量隐性创作直觉/手艺 + 软技能（爽点设计与节奏感、断章艺术、代入感营造、金手指与成长曲线设计、读者数据解读与救书、码字速度与存稿纪律、抗压与反扑街心态、卡文处理、长线连载的体力与心理耐力、对榜单与流派趋势的嗅觉）是高 tacit、难言传、靠连载实战 + 数据反馈 + 扑街交学费积累的核心。水分较高（大量「网文写作速成班/包月入过万」培训割韭菜、幸存者偏差严重、二手转述与营销号），须强 source 过滤：优先 figure 本人长访谈/直播/作者的话 + 平台官方写作指南 + 网文学术研究 > 二手转述 > 培训机构软文；严防把「写作速成班」「保底月入过万」当知识来源。不含: 传统纯文学/严肃文学创作、纸质出版社流程、影视编剧/剧本创作（借用其叙事理论但工艺不同，重点辨明差异）、剧本杀/互动小说、海外英文原创网文 Royal Road/Wattpad（可少量对比但不深覆盖）、漫画/动画分镜脚本、自媒体/短视频文案。) Master OS — automated mastery of 网文写作 (Chinese Web Novel Writing) — 中国网络文学的「连载长篇商业小说创作工艺」认知操作系统：从「定方向（频道/流派/题材）→ 立意与金手指设计 → 大纲与人物设定 → 开局黄金三章 → 日更连载与节奏控制（爽点/期待感/钩子/断章）→ 读者数据反馈与调整 → 完本与 IP 改编」的完整创作-连载-变现决策链。覆盖 (a) 第一性张力 — **读者数据驱动/即时反馈（追读率、订阅、追订、月票、收藏、章评、卡点数据）⇄ 作者表达/文学性（个人审美、慢热、留白、文笔）**；**爽文/套路化/工业糖精（爽点密度、装逼打脸、金手指、无敌流、爽感经济）⇄ 慢热/反套路/精品化（铺垫、群像、立意、文青向）**；**男频（玄幻/仙侠/都市/历史/科幻/游戏/系统流/无限流/凡人流，起点/番茄系，重设定与战力体系）⇄ 女频（古言/现言/穿越/重生/宫斗/种田/快穿/无限流/言情，晋江系，重情感与关系/人设）**；**付费订阅模式（起点/晋江，千字几分订阅+全勤+打赏+月票，养老书/精品）⇄ 免费阅读模式（番茄/七猫，平台买断/流量分成，强开局强爽点强节奏，走量）**；**长线连载/养书（百万字+、慢节奏铺世界观）⇄ 强开局/快节奏（黄金三章定生死、前一万字留人）**；**个人风格/品牌作者（大神、IP、粉丝向）⇄ 工业化/编辑导向（迎合榜单/编辑改稿/数据调优/AI 辅助）**。(b) 核心工作流 / pipeline（最标准、最易蒸高质量 + CLI 化）— 通用链：选频道与流派（看平台榜单/读者画像/自身擅长）→ 立意与核心设定（金手指/世界观/主线冲突）→ 人物与关系设计（主角金手指与成长弧、反派、配角、cp）→ 大纲（主线+支线+卷纲+细纲）→ 黄金三章/开局（代入感、爽点前置、悬念钩子、信息密度）→ 签约与上架（编辑沟通、签约合同、上架节奏）→ 日更连载（码字速度、存稿、断章艺术、节奏曲线、卡文处理）→ 读者运营（章评互动、本章说、读者数据看板、追读率分析）→ 调整与救书（数据扑街诊断、改大纲/换爽点/加节奏）→ 完本与变现（完本福利、IP 改编影视/动漫/游戏/有声/漫画）。(c) 工具栈 — 写作软件（壹写作、码字猫、橙瓜码字、墨者写作、汤圆/小黑屋专注码字、Scrivener、WPS/Word）、设定与大纲管理（壹写作设定卡、幕布/思维导图、Excel 人物关系表、世界观 wiki）、平台作家后台与数据（起点作家专区、晋

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Product AI Visibility & Ranking — evaluate how AI search engines (ChatGPT, Claude, Gemini, DeepSeek) recommend your product when shoppers ask buying questions. Triggers: AI visibility, product AI ranking, AI recommend, AI search, does AI mention my product.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

🇺🇸 Your dev team ships features nobody asked for while user-reported bugs pile up for months. Operations blames engineering for ignoring users; engineering blames operations for not understanding technical constraints. This gives you the complete Product × Engineering × Operations alignment SOP — from unified backlog to 10-day sprint cadence to veto power rules. What's inside: • Dual-layer Kanban system (master backlog + sprint board with unified tagging) • 10-day sprint standard process (Day 1 dev → Day 6 testable build → Day 10 ship) • Issue template with reproducibility requirements (3x reported = auto-severe) • Tri-party alignment meetings (daily standup / sprint planning / sprint review) • Operations veto power on releases (P0 bug = block shipping) • User feedback → product iteration closed loop (beta testing + interview SOP) • Core metrics framework (acquisition → activation → retention → monetization → referral) • Technical debt management (20-30% sprint capacity reserved) • Ready-to-use templates: Bug Report, Sprint Planning, Responsibility Matrix Built from: Real product strategy meetings + beta testing frameworks. References Supabase sprint model, Manus/DeepSeek commercialization alignment. By @WeiYipei. 🇨🇳 你的研发团队在做没人要的新功能，用户反馈的 Bug 堆了三个月没人动。运营觉得研发不听用户，研发觉得运营不懂技术。这份 SOP 给你从统一看板到 10 天迭代节奏到一票否决权的完整产研运协同框架。 🇯🇵 開発チームは誰も求めていない機能を作り、ユーザーから報告されたバグは何ヶ月も放置。このSOPは、統一バックログから10日スプリント、リリース拒否権まで、プロダクト×エンジニアリング×オペレーションの完全な連携フレームワークを提供します。 🇰🇷 개발팀은 아무도 요청하지 않은 기능을 만들고, 사용자가 보고한 버그는 몇 달째 방치됩니다. 이 SOP는 통합 백로그부터 10일 스프린트, 릴리스 거부권까지 제품×개발×운영 완전 협업 프레임워크를 제공합니다. Triggers: "product ops" | "engineering operations" | "product development SOP" | "sprint planning" | "iteration management" | "cross-functional alignment" | "product engineering ops" | "dev ops collaboration" | "产研运协同" | "迭代管理" | "产品研发运营" | "プロダクト開発運営" | "제품개발운영"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert FinOps guidance for cloud, AI, and SaaS technology spend. Covers AI cost management, agentic FinOps, GenAI capacity planning, self-hosted vs managed inference, Anthropic billing, open-weight vendor APIs (DeepSeek, Qwen, Kimi, GLM), AWS (EC2, Bedrock, SageMaker, Savings Plans, CUR), Azure (reservations, AHB, OpenAI PTUs), GCP (Vertex AI, BigQuery), OCI, Kubernetes cost allocation, data platforms (Databricks, Fabric F-SKUs, Snowflake), tagging governance, SaaS management (SAM, shadow IT), AI coding tools (Cursor, Claude Code, Copilot, Codex), ITAM, allocation, showback, chargeback, anomaly management, KPIs and benchmarking, waste detection playbooks, workload onboarding and M&A, and GreenOps (cloud carbon, CSRD). Use for any question about technology cost or waste in your estate - expiring commitments or RIs, NAT gateway bills, idle VMs, snapshot sprawl - and for commitment sizing, rightsizing, allocation, SaaS sprawl, AI dev tool spend, or connecting spend to business value. Built by OptimNow.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Query foreign LLM for chat. Use this skill if a foreign LLM like OpenAI ChatGPT, Google Gemini, DeepSeek or xAI Grok should be queried with a single chat message.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by the dsh-plugin-guide knowledge base.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

用前端渲染生成图片 —— 不依赖模型的多模态能力，任何能写 HTML/CSS 的模型 (DeepSeek / Claude / Kimi / GPT 等) 都能用。 当用户要「生成/做/画一张图」且属于以下任意一种时使用：头像、图标、公众号封面、 OG 分享图、Banner/横幅、小红书封面、知识卡片、金句卡、代码片段图、数据卡、 功能发布图、对比图、步骤图、视频封面/缩略图、幻灯片单页、活动海报、名片、 二维码卡、配图、题图、缩略图、poster、cover、thumbnail、banner、avatar。 也用于：批量出多个尺寸/多平台的同一张图；把一段文字/数据/代码变成图； 给文章配图；做一套风格统一的系列图。 支持指定视觉风格，共 32 套：手绘/涂鸦/白板、黑板、水彩、拼贴/剪贴、博物图鉴、 瑞士国际主义、杂志编辑部、报纸、工程蓝图、档案手稿/打字机、包豪斯、装饰艺术 Art Deco、 双色印刷 Riso、粗野主义、孟菲斯、美漫波普、像素 8-bit、千禧 Y2K、蒸汽波、霓虹赛博朋克、 街头海报/喷漆、日式侘寂、中式水墨、国潮/新中式、终端 CLI、极光渐变、玻璃拟态、 奢侈品黑金、极简产品、电影海报、复古未来 70s、极简线条。 用户没指定时主动报 3~4 个候选让他选；说了库里没有的风格就按四步法拆成 token。 产出一个可预览的画板工作台页面，多种画幅并排展示，点按钮即可导出 PNG (页内零依赖导出 + 本机 Chrome 精确出图两条通道)。 不适用：需要照片级真实内容的图（人像、风景、材质渲染）—— 那需要真正的图像模型。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when installing Anthropic's Claude Science on a geo-blocked machine (e.g. China) or running it without a Claude account. Downloads the binary from the unblocked downloads.claude.ai CDN, sets up the claude-science-api-bridge local proxy to route requests to ANY OpenAI- or Anthropic-compatible API (Volcengine, DeepSeek, Kimi, Zhipu, OpenAI, local Ollama/vLLM), and applies a no-login patch so no Claude Pro/Max subscription is required.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 78 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "auto research", "switch model", "hand off a session", "session handoff", "switch engine", "continue on codex", "continue on claude", "move this session to another engine", "multi-agent coding", "coding session", "session inbox", "grok session", "grok build", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness", "clawo runs", "run ledger", "session cost", "coding-agent token usage", "spend cap", "budget limit", "maxBudgetUsd", "durable workflow", "resume a run", "verify a coding run", "acceptance contract", "evidence bundle", "did the agent's tests actually pass", "protected tests", "agent edited the tests", "human gate", "repair loop", "clawo workflow", "clawo verify", "clawo solve", "clawo fanout", "fix and verify", "solve from the terminal".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads that one model's official strategy — so the optimization always matches the model that actually runs it. Activate with /prompt-refine. Use when users want better answers without learning prompt engineering.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use cheap, TEE-verified AI models from the 0G Compute Network as OpenClaw providers. Discover available models and compare pricing vs OpenRouter, verify provider integrity via hardware attestation (Intel TDX), manage your 0G wallet and sub-accounts, and configure models in OpenClaw with one workflow. Supports DeepSeek, GLM-5, Qwen, and other models available on the 0G marketplace.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fornece treinamento distribuído de LLM nativo do PyTorch usando torchtitan com paralelismo 4D (FSDP2, TP, PP, CP). Use para fazer pré-treinamento de Llama 3.1, DeepSeek V3 ou modelos customizados em escala de 8 a 512+ GPUs com Float8, torch.compile e checkpoint distribuído.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Treina modelos de linguagem grandes (2B-462B de parâmetros) usando NVIDIA Megatron-Core com estratégias avançadas de paralelismo. Use ao treinar modelos >1B de parâmetros, precisar de máxima eficiência de GPU (47% MFU em H100), ou necessitar de paralelismo tensor/pipeline/sequência/contexto/expert. Framework pronto para produção usado em Nemotron, LLaMA, DeepSeek.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when adding, auditing, pruning, archiving, restoring, or reviewing Agent Notes in deepseek-harness; checks every new note for superseded active records, classifies implemented notes by future decision value, deletes rejected notes that no longer prevent a tempting fallacy, and applies the frozen archived/{kind} triplet and manifest rules.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where should this be documented", or "this doc is too long".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working in the deepseek-harness repo to find non-obvious simplification candidates, write proposed Agent Notes or inline TODO/FIXME/XXX notes, audit or coalesce superseded Agent Notes, or fold worthwhile simplification ideas from another PR; especially for dead, duplicated, speculative, over-built, added-then-removed, or hand-rolled-where-a-dependency-exists surfaces.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing, reviewing, restoring, trimming, or auditing prose in the deepseek-harness repo, including deciding where documentation or comments are required across Markdown, JSDoc, code and test comments, prompts, descriptions, diagnostics, and CLI or UI strings.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.