'deepseek' 검색 결과

Everything Claude Code의 스킬과 훅을 DeepSeek Harness에 연결합니다. 설정 생성, 동작 확인, 업데이트와 인식 문제 조사를 안내합니다.

• DSH에 ECC 스킬을 설치합니다
• 프로필에 훅을 연결합니다
• 스킬과 훅의 인식 문제를 조사합니다

Send a single request to DeepSeek for summarization, information extraction, or simple classification. Receive the response and token usage as JSON for further processing, with structured status information when the API is unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing text in a single request
• Extracting information from text
• Classifying text into simple categories

Send proofs, planning questions, or difficult debugging tasks to DeepSeek's reasoning model. Receive the final answer and model-provided reasoning text in separate fields, with token usage reported for reviewing responses and costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Requesting a mathematical proof
• Planning work that requires several reasoning steps
• Investigating root causes of difficult bugs

Delegate scoped repository analysis or implementation to DeepSeek Harness without opening its interactive interface. Collect its final text, check the exit status, and inspect repository changes when the task requires read-only work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Diagnose a failing test without editing files
• Delegate a scoped repository investigation
• Request implementation in a specified project

Study a reference adaptation connecting the shared skillopt_sleep cycle to a custom DeepSeek backend for OpenClaw. It provides prototype wrappers, sample tasks, and a porting checklist for developers building an integration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Study a prototype DeepSeek backend for OpenClaw
• Identify changes needed for current engine interfaces
• Review sample tasks and environment-specific settings

Retrieve content from URLs and PDFs, then summarize, quote, convert, or save it as readable Markdown. When built-in search falls short, use DeepSeek as an optional search fallback, with explicit handling of extraction failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing a linked article or PDF
• Extracting passages with source citations
• Converting and saving web content as Markdown

Send prompts to Novita AI models such as DeepSeek and GLM from the command line. Retrieve answers as readable text or structured JSON, stream responses as they arrive, and check available models and API connectivity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Send questions to DeepSeek or GLM
• Display responses as they arrive
• Retrieve AI responses as JSON

Guide multi-step coding tasks with deepseek-v4-pro or deepseek-v4-flash in thinking mode. Verify files and symbols, write plans with confirmed file paths and line numbers, and use a verifier agent before changes spanning three or more files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify that files and functions exist before editing
• Write plans with confirmed file paths and line numbers
• Check assumptions before changes spanning three or more files

Delegate code review, development, and research from OpenCode to DeepSeek Harness. The skill checks service readiness, tracks each task, and returns reports or proposed code changes for the main agent to review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Get a second opinion on code or architecture
• Delegate code changes to an external agent
• Assign research tasks and track progress

Call Gemini and OpenMaaS models such as Llama, DeepSeek, and Qwen through Google Cloud Agent Platform. Prepare authentication and SDK code, run prompts, configure connection endpoints, and troubleshoot common request errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Send a test prompt to Gemini
• Call Llama or DeepSeek with the OpenAI SDK
• Write code to call an existing custom endpoint

Manage mathematical proof projects across Codex runs, keeping sources, attempts, and unresolved steps organized. Prepare manual GPT Pro handoffs for difficult steps, then check returned arguments and edit the proof for clarity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continue a proof from a previous run
• Prepare a manual GPT Pro handoff for a difficult lemma
• Track proof sources and unresolved steps

Use DeepSeek's chat API: list models, run chat completions, check account balance. Trigger phrases: deepseek, deepseek chat, deepseek api.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deepseek 联网搜索工具。一键调用 AI 联网搜索能力，快速获取实时信息。当用户需要使用 Deepseek 搜索、联网搜索、AI 搜索获取实时信息时使用。触发词：Deepseek搜索、deepseek websearch、联网搜索、AI搜索、ds搜索。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add OpenCode as an agent runtime in NanoClaw to use models from OpenAI, Google, OpenRouter, DeepSeek, and other supported services. The skill covers installation, authentication, group selection, and default model changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding OpenCode to an existing NanoClaw installation
• Switching an agent group to OpenCode
• Changing the default model without signing in again

Manage mathematical proof work across separate runs, preserving sources, established results, and unresolved steps. Attempt and audit proofs locally, prepare focused manual GPT Pro handoffs when blocked, and check returned answers before producing a clearer final proof.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing proof work from a previous run
• Preparing a focused GPT Pro handoff
• Checking a returned proof against local sources

Use when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository. Covers reading docs/progress/MASTER.md, following GitHub Issues

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

小红书 AI 自媒体博主 (小红书 AI 自媒体博主 (从业者视角) — 在小红书做『AI 赛道』内容的自媒体博主，重点是**怎么写文案、怎么制作内容**。覆盖: (a) AI 赛道选题 — AI 工具测评 / AI 绘画 / AI 教程与 prompt / AI 副业变现 / AI 资讯解读 / AI 效率，按小红书用户(偏年轻女性 + 泛知识)重构选题; (b) 文案与内容结构(核心) — 封面(第一眼/大字报/对比图)、标题(数字/痛点/好奇缺口/关键词前置)、正文(钩子开头/分点/口语化/emoji/利他价值)、标签与 SEO 关键词、CTA 与互动引导、人设 voice; (c) 内容制作工作流 — 选题(对标爆款/找选题)→标题封面→脚本或正文→制作(图文/口播/录屏/数字人)→标签发布→数据复盘迭代; (d) AI 工具用于内容生产 — 文案(豆包/Kimi/DeepSeek/GPT)、生图(即梦/MJ/可图)、口播数字人、剪辑(剪映)、封面(Canva/创可贴)、选题与 SEO(新红/千瓜/灰豚); (e) 平台机制与起号 — 推荐算法(收藏率/互动率/完播/搜索)、薯条投放、违禁词/限流/避坑、起号与涨粉、垂直度; (f) 变现(次要) — 蒲公英广告 / 知识付费 / 引流私域 / AI 工具带货。学派分歧: 图文 vs 短视频、干货教程 vs 测评种草 vs 资讯搬运、真人出镜 vs 数字人/无人起号、原创 vs 搬运洗稿、AI 全自动批量 vs AI 辅助精做。不含: 通用小红书运营(已有 xiaohongshu-ops skill, 本 skill 聚焦 AI 赛道 + 文案/内容生产)、电商带货全流程、其他平台、AI 工具本身的技术原理。) Master OS — automated mastery of 小红书 AI 自媒体博主 (从业者视角) — 在小红书做『AI 赛道』内容的自媒体博主，重点是**怎么写文案、怎么制作内容**。覆盖: (a) AI 赛道选题 — AI 工具测评 / AI 绘画 / AI 教程与 prompt / AI 副业变现 / AI 资讯解读 / AI 效率，按小红书用户(偏年轻女性 + 泛知识)重构选题; (b) 文案与内容结构(核心) — 封面(第一眼/大字报/对比图)、标题(数字/痛点/好奇缺口/关键词前置)、正文(钩子开头/分点/口语化/emoji/利他价值)、标签与 SEO 关键词、CTA 与互动引导、人设 voice; (c) 内容制作工作流 — 选题(对标爆款/找选题)→标题封面→脚本或正文→制作(图文/口播/录屏/数字人)→标签发布→数据复盘迭代; (d) AI 工具用于内容生产 — 文案(豆包/Kimi/DeepSeek/GPT)、生图(即梦/MJ/可图)、口播数字人、剪辑(剪映)、封面(Canva/创可贴)、选题与 SEO(新红/千瓜/灰豚); (e) 平台机制与起号 — 推荐算法(收藏率/互动率/完播/搜索)、薯条投放、违禁词/限流/避坑、起号与涨粉、垂直度; (f) 变现(次要) — 蒲公英广告 / 知识付费 / 引流私域 / AI 工具带货。学派分歧: 图文 vs 短视频、干货教程 vs 测评种草 vs 资讯搬运、真人出镜 vs 数字人/无人起号、原创 vs 搬运洗稿、AI 全自动批量 vs AI 辅助精做。不含: 通用小红书运营(已有 xiaohongshu-ops skill, 本 skill 聚焦 AI 赛道 + 文案/内容生产)、电商带货全流程、其他平台、AI 工具本身的技术原理。: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on 小红书 AI 自媒体博主 (从业者视角) — 在小红书做『AI 赛道』内容的自媒体博主，重点是**怎么写文案、怎么制作内容**。覆盖: (a) AI 赛道选题 — AI 工具测评 / AI 绘画 / AI 教程与 prompt / AI 副业变现 / AI 资讯解读 / AI 效率，按小红书用户(偏年轻女性 + 泛知识)重构选题; (b) 文案与内容结构(核心) — 封面(第一眼/大字报/对比图)、标题(数字/痛点/好奇缺口/关键词前置)、正文(钩子开头/分点/口语化/emoji/利他价值)、标签与 SEO 关键词、CTA 与互动引导、人设 voice; (c) 内容制作工作流 — 选题(对标爆款/找选题)→标题封面→脚本或正文→制作(图文/口播/录屏/数字人)→标签发布→数据复盘迭代; (d) AI 工具用于内容生产 — 文案(豆包/Kimi/DeepSeek/GPT)、生图(即梦/MJ/可图)、口播数字人、剪辑(剪映)、封面(Canva/创可贴)、选题与 SEO(新红/千瓜/灰豚); (e) 平台机制与起号 — 推荐算法(收藏率/互动率/完播/搜索)、薯条投放、违禁词/限流/避坑、起号与涨粉、垂直度; (f) 变现(次要) — 蒲公英广告 / 知识付费 / 引流私域 / AI 工具带货。学派分歧: 图文 vs 短视频、干货教程 vs 测评种草 vs 资讯搬运、真人出镜 vs 数字人/无人起号、原创 vs 搬运洗稿、AI 全自动批量 vs AI 辅助精做。不含: 通用小红书运营(已有 xiaohongshu-ops skill, 本 skill 聚焦 AI 赛道 + 文案/内容生产)、电商带货全流程、其他平台、AI 工具本身的技术原理。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「小红书 ai 博主」「小红书 ai 自媒体」「小红书 ai 赛道」「小红书爆款文案」「小红书 ai 教程」

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DeepSeek利用時の失敗切り分け、再試行、quota確認、provider選定を支援する。応答停止、tool call欠落、429などの症状で使う。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing MoE models for a limited compute budget
• Implementing Mixtral-style expert routing
• Adjusting expert workloads and training stability

Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a model that activates only selected expert networks
• Balancing workloads across expert networks
• Distributing experts across multiple GPUs

Automate a logged-in Chromium browser using the plugin’s injected tools. Read pages, fill forms, manage tabs, inspect page activity, and investigate website problems or test interfaces while working with the user’s existing browser logins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading pages that use an existing browser login
• Filling forms and navigating between tabs
• Investigating website errors and page activity

Build reusable maps, charts, rankings, diagrams, and opening or ending components for iPolloWork Video. Connect them to shared editing forms, project themes, structured data, AI editing areas, and animation timelines that support jumping to specific playback positions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build reusable map, chart, or ranking components
• Connect component settings to shared forms and tables
• Make visuals follow the project theme

Use when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository. Covers the full workflow from repository-mode and plugin-form selection through separate offline naming validation, optional online registry lookup, and package validation. Routes tool, LLM adapter, hook, service, and configuration forms to their corresponding references while separating upstream-monorepo rules from external-package rules. For an existing plugin crossing Harness versions, use this Skill's built-in version-adaptation workflow before implementing against the exact target contract.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository. Select the minimum sufficient levels from unit tests, coverage, real-API end-to-end tests, snapshots, Web tests, real compositions, and built-artifact smoke tests. For Harness version migrations, use this Skill's built-in seven-touchpoint test workflow and validate the exact target-version runtime.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.