Results for “deep”

Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021 Nat Genet 53:354; soft motif syntax from ChIP-nexus), chromBPNet (Pampari A et al 2025 Nat Genet; bias-factorized base-resolution profiles), EnFormer (Avsec 2021 Nat Methods 18:1196; 196 kb input, ~100 kb effective receptive field), DeepSEA (Zhou 2015; multi-task CNN), and JASPAR 2026 deep-learning collection (1259 BPNet ChIP models). Performs in silico mutagenesis for variant-effect prediction, DeepLIFT/Grad attribution, and TF-MoDISco motif discovery from attribution scores. Use when predicting variant effects on TF binding, discovering soft motif syntax / cooperativity, integrating ChIP-seq with sequence-only predictions, or applying precomputed JASPAR Deep Learning models to new variants.

The English summary is being prepared. Showing the original description.

Trains and applies base-resolution deep learning models on ChIP-seq / ChIP-nexus / CUT&RUN data. Uses BPNet (Avsec 2021 Nat Genet 53:354; soft motif syntax from ChIP-nexus), chromBPNet (Pampari A et al 2025 Nat Genet; bias-factorized base-resolution profiles), EnFormer (Avsec 2021 Nat Methods 18:1196; 196 kb input, ~100 kb effective receptive field), DeepSEA (Zhou 2015; multi-task CNN), and JASPAR 2026 deep-learning collection (1259 BPNet ChIP models). Performs in silico mutagenesis for variant-effect prediction, DeepLIFT/Grad attribution, and TF-MoDISco motif discovery from attribution scores. Use when predicting variant effects on TF binding, discovering soft motif syntax / cooperativity, integrating ChIP-seq with sequence-only predictions, or applying precomputed JASPAR Deep Learning models to new variants.

The English summary is being prepared. Showing the original description.

Design modules that offer substantial behavior through a small interface, the rules callers must understand. Use shared design terms to simplify usage, contain complexity, choose where implementations can vary, and make behavior easier to test.

• Simplifying a module's interface
• Bringing scattered complexity into one module
• Choosing where implementations can be swapped

Predict spatial gene expression from H&E-stained tissue images using DeepSpot-M. Query a released panel of about 19,000 genes and combine predictions from small image tiles into slide-wide maps for research analysis.

• Mapping predicted marker-gene expression across a tumor section
• Predicting expression across slides without matching gene-expression assays
• Adding predicted expression to a histology image analysis pipeline

Create an implementation plan grounded in code relationships and verified source files, with proposed changes, test scenarios, risks, and a structured handoff for an implementation agent. It can also revisit and strengthen an existing plan.

• Planning a new feature
• Assessing a shared API change before implementation
• Strengthening and rechecking an existing plan

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.

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

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.

The English summary is being prepared. Showing the original description.

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

The English summary is being prepared. Showing the original description.

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.

The English summary is being prepared. Showing the original description.

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。

The English summary is being prepared. Showing the original description.

Deep learning-based variant calling with Google DeepVariant. Provides high accuracy for germline SNPs and indels from Illumina, PacBio, and ONT data. Use when calling variants with DeepVariant deep learning caller or when highest germline calling accuracy is required.

The English summary is being prepared. Showing the original description.

GTM prospecting, enrichment, outreach, and Deepline Play work/audits. Providers: adyntel,affinity,ai_ark,akta,allegrow,amplemarket,apify,attention,attio,aviato,bettercontact,bigquery,bluesky,bounceban,brave,browserbase,builtwith,cbinsights,clay,clickhouse,cloudflare,contactout,contextdev,crunchbase,crustdata-v3,customer_db,databricks,dataforseo,datagma,dealroom,deepline_ip_to_company,deepline_native,deeplineagent,discolike,dropleads,edges,emailbison,emailguard,enformion,enigma,exa,findymail,firecrawl,fireflies,firmable,forager,fullenrich,fundable,generic_http,getleads,gong,google_ads_audiences,google_workspace,govfiles,grain,hackernews,harvestapi,heyreach,hubspot,hunter,icypeas,instantly,intercom,ipqs,kaspr,kernel,leadmagic,lemlist,limadata,linkedin_ads_audiences,luma,lusha,meta_audiences,millionverifier,nooks,notion,openmart,opensosdata,openwebninja,outreach,parallel,peopledatalabs,pitchbook,podscan,polymarket,postgres,predictleads,prospeo,quickenrich,rapidapi,redshift,rocketreach,salesforce,salesforge,….

The English summary is being prepared. Showing the original description.

Use when surfacing architectural friction and proposing deepening refactors (shallow modules → deep modules) for testability and AI-navigability. Triggers on "improve architecture", "find deepening opportunities", "where is this codebase shallow", "architecture review". Emits structured candidates + precise patches; delegates ALL rendering to mk:preview. NOT for diagram/HTML rendering (see mk:preview); NOT for trade-off deliberation (see mk:party); NOT for plan critique (see mk:plan-ceo-review).

The English summary is being prepared. Showing the original description.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

The English summary is being prepared. Showing the original description.

Document a project's structure, commands, and specific conventions in a hierarchy of AGENTS.md files. Analyze directory complexity to choose useful locations, update existing guidance, and check that child files avoid repeating their parents.

• Create project guidance for coding agents
• Refresh existing AGENTS.md documentation
• Document rules specific to complex directories

Design modules that hide complex behavior behind a small, clear interface. Use shared design principles to review dependencies, choose where behavior can be swapped, and make code easier to test and maintain.

• Simplifying a module's interface
• Reviewing where to separate responsibilities
• Designing code that is easier to test

Examine recorded calls and voicemails for signs of AI-generated speech. Extract acoustic features, classify samples with machine learning, and prepare reports with confidence scores and sound visualizations to support voice impersonation investigations.

• Investigating calls impersonating executives
• Checking suspicious voicemails
• Comparing suspect recordings with genuine voice samples

Build voice applications and phone agents with guidance on OpenAI Realtime API, Vapi, Deepgram, ElevenLabs, and LiveKit. Choose services for speech recognition, voice generation, and live communication, while addressing response delays and interruptions.

• Build a voice assistant that responds in real time
• Create a phone support agent with Vapi
• Connect speech recognition and voice generation

Research markets, competitors, companies, and technical topics using multiple sources in Google NotebookLM. Produce a structured brief with key findings and recommended actions, with optional slides, podcasts, videos, infographics, reports, or mind maps.

• Researching market trends and business opportunities
• Comparing competitors and their positioning
• Researching prospects before a proposal

Process large email, document, and transcript archives by routing items to AI models according to their importance. Rule-based privacy checks run before model calls, while extracted information becomes linked knowledge pages with progress checkpoints.

• Extract useful information from large email archives
• Organize decisions and advice from meeting transcripts
• Route reports to suitable models by importance

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.

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

Review changes of 1,000 lines or more by dividing work across files, focused areas, and commits. Combine several review methods, check consistency across subsystems, verify bug fixes, and report validated findings alongside a checklist showing review coverage.

• Reviewing feature branches with 1,000 or more changed lines
• Checking a large change before merging
• Finding inconsistencies across commits and subsystems

Review selected files for bugs by reading full source code, callers, and related implementations. Apply detailed checklists and investigate suspected issues, then report evidence, confidence levels, and suggested fixes.

• Review selected files in a critical code change
• Investigate concerns raised by an initial review
• Check complex state transitions and object lifecycles

Connect streaming APIs to Ant Design X by implementing a Chat Provider, an adapter for request and message formats. Choose built-in providers where suitable, transform custom responses, and configure authentication, retries, and stream parsing.

• Connect a private streaming API to Ant Design X
• Choose a provider for OpenAI or DeepSeek
• Convert responses containing multiple fields