В каталоге 183 730 навыков в 14 категориях.
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling i...
Use this skill in the scenario of deep learning project development.
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Fa...
Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse...
Use for CRM audits, duplicate detection, missing or stale fields, job changes, domain checks, acquisitions, parent-child...
Build, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pi...
Send feedback or bug reports to the Deepline team, including session transcript and environment info.
GTM prospecting, enrichment, outreach, plays. Providers: adyntel,affinity,ai_ark,akta,allegrow,amplemarket,apify,attenti...
ACCESS-GATED beta. Deepline Monitors (dashboard name: Signal Radars) — provider event feeds (job posts, email replies, f...
Build an interactive account org chart, leadership map, buying committee, or manager/report neighborhood around a person...
Use for Deepline Plays/CLI V2 work: get started, find/describe/run prebuilts, process CSVs, bootstrap/wrap/fork plays, a...
Send Deepline SDK/V2 CLI feedback or bug reports, including environment info and the current Claude/Cowork session trans...
Use this skill when a Deepline Play needs human review, evaluation against golden labels, or bounded iterative improveme...
Run a quick Deepline demo recipe on the V2 CLI using prebuilt plays.
Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the ag...
Use when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, private, CRM, wo...
Run a quick Deepline demo recipe to show the user how Deepline works.
Use when discovering niche signals, auditing ICP or won/lost evidence, rescoring accounts, or building account and lead...
Use this skill for any GTM Engineering work in Deepline — prospecting, list-building, account research, contact enrichme...
Interview a user to discover a concrete GTM problem or manual task, recommend the right installed Deepline skill, prebui...
Diagnose failing, stuck, partial, or incorrect Deepline Plays, including when no Play is named. Use deepline-gtm for the...
Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 mode...
Route DeePMD-kit requests to training or inference sub-skills. Use when the user requests machine learning potentials, D...
Train DeePMD-kit machine learning potentials. Covers DPA-3 (recommended), se_e2_a (legacy), and fine-tuning from pretrai...
Train DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential, prepare an...
Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the use...
Atlas skill for Manus AI-inspired persistent planning. USE WHEN complex multi-step task, research project, extended impl...
Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowle...
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, se...
Deep research assistant that transforms user questions into high-quality queries, calls Google Deep Research, and delive...
Integrate Hunyuan DeepResearch for deep reasoning and search-enhanced conversations. Use this skill when the application...
Thorough codebase search
基于 LLM 的深度迭代搜索与推理服务。擅长处理复杂问题，通过自动分解查询、多轮迭代检索、信息评估与验证，最终生成全面且结构化的深度分析报告。
Deep internet research agent for training domain-specialist agents. Use when: researching a technical domain to create a...
Drive the `oma-deepsec` skill end-to-end. Installs `.deepsec/`, calibrates cost, runs the right scan/process/triage/reva...
Reasoning guidelines optimized for DeepSeek-V3 and DeepSeek-R1.
DeepSeek API 使用模式 — ReAct Agent、Function Calling、中文交互的坑和最佳实践
DeepSeek DeepSeek-Coder — run DeepSeek-V3, DeepSeek-R1, DeepSeek-Coder across your local fleet. 7-signal scoring routes...
Let the OpenCode host delegate code review, development, and research tasks to DeepSeek Harness.
Use for DeepSeek Harness (`dsh`) installation, operation, configuration, automation, extension, troubleshooting, or sour...
DeepSeek Harness (dsh) CLI 安装、启动、launcher flag 坑、WSL 后台保活。
Адаптирует SKILL.md и связанные ресурсы, написанные для другого ИИ-агента, под DeepSeek Harness с сохранением назначения...
当用户要求"DeepSeek API 集成"、"AI 服务"、"生成回复建议"、"调用 LLM"、"HTTP 请求"、"流式响应"、"连接池优化"、"重试策略"，或者提到"DeepSeek"、"API 调用"、"reqwest"、"stre...
DeepSeek special model reasoning bridge - Advanced multi-step reasoning via MCP, bridging devuser to deepseek-user for c...
Leveraging thinking tokens with DeepSeek R1.
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、A...
Two-phase daily memory persistence for AI agents. Nightly pack at 23:40 plus morning dispatch at 00:10. Auto-discovers s...
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8,...
Partitioning weights, gradients, and optimizer states.
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1...
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatia...
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStre...
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer...
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Mi...
Use when running parallel AI workers for any long-running or multi-turn batch API task. Auto-calculates optimal workers...
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for...
Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Il...
Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.
AI-generated documentation for GitHub repositories
Query any public GitHub repo's documentation via DeepWiki. Use when needing to understand a library, framework, or depen...
Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and ex...
DeepWiki MCP server for AI-powered GitHub repository documentation and
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and autom...
High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review...
Start or continue DeepWork workflows using MCP tools
Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.
Creates a job.yml specification by gathering workflow requirements through structured questions. Use when starting a new...
Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review pass...
Creates file-change rules that enforce guidelines during AI sessions. Use when automating documentation sync or code rev...
Creates a rule file that triggers when specified files change. Use when setting up documentation sync, code review requi...
Analyzes conversation history to improve job instructions and capture learnings. Use after running a job to refine it.
Reviews job.yml against quality criteria using a sub-agent for unbiased validation. Use after defining a job specificati...
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heat...
Track deep work sessions and productivity metrics.
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access,...
Search, inspect, and progressively read open-access academic papers with the deepxiv CLI. Use when the user wants arXiv...
Sense accessibility barriers with gentle awareness. Listen to the forest, scan for obstacles, test the paths, guide towa...
ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term...
Locate symbol definitions quickly (precise for Python via AST; conservative candidates for other languages) and print a...
Respond to false, damaging statements about you or your business — decide what actually counts as defamation, preserve e...
Prepares indicators of compromise for safe sharing: defanging URLs, domains, IPs, and emails so they cannot be accidenta...
Switch back to Anthropic Claude default
A clean, product-oriented default. Use when the brief doesn't call for a specific mood — good for B2B tools, dashboards,...
Create artifacts from NewBrain default document, spreadsheet, presentation, and report templates.
Turn a transcript into grounded, structured notes for deep study.
Defeats control-flow-flattening obfuscation by identifying the dispatcher/state- variable structure and reconstructing t...
Recovers obfuscated strings and resolves dynamically loaded APIs in malware: reversing XOR/stack-string/encoding schemes...
Turn a selected Radar defect cluster into a bounded discovery specification using existing ATE, fuzz, oracle and replay...
Classifies a defect that reached production into one of three root gap categories (test gap, process gap, tooling gap) a...
缺陷修复的闭环流程：分级与范围锁定、先有失败测试再改代码、最小改动、按影响面推导回归范围、验证证据、修复记录与关闭条件。当用户要修某个缺陷、按缺陷单修复、修复后要验证与回归、判断缺陷严重度与优先级、控制修复范围、要写修复记录、判断这个缺陷能...
Use when the user asks to create point defects such as vacancies, substitutional defects, or interstitial atoms in a cry...
Triage defects by establishing reproducibility, user/system impact, severity, scope, regression status, ownership, dupli...
Guide for implementing DefectDojo - an open-source DevSecOps, ASPM, and vulnerability management platform. Use when quer...
This skill group covers calculations involving crystallographic defects and chemical reaction pathways in solid-state ma...
Cross-check a targeting figure against outside data and write its defence. Use before a number reaches a funder or a pub...
Implement layered collective defense using alarm signaling, role mobilization, and proportional response. Covers threat...
Microsoft Defender for DevOps integration with Azure Pipelines (2025)
Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assi...