2.4K skills · sorted by relevance
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.
Change DeepChat preferences through conversation, including theme, interface language, font size, sound effects, and whether copied text includes COT details. Dedicated tools apply supported changes, while other requests open the relevant settings section with guidance.
Use DeepChat's bundled command-line interface to compare models, generate media, transcribe audio, and extract text from images. Also inspect runtime status, artifact metadata, public settings, installed Skills, and MCP connections to external tools.
Helps configure and troubleshoot DeepSpeed for training large models across multiple devices. Covers memory optimization, parallel training, and DeepNVMe storage transfers, with examples for tuning data movement and configuring models that divide work among specialized components.
Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.
Automate Deepgram operations through Rube MCP, a connection for agent tools. The skill finds available actions, checks the service connection, and runs tasks using the latest required input fields.
Set up and manage DeepTutor from the command line, a text interface for running commands. Run learning tasks, build searchable document collections, manage sessions and notebooks, diagnose installation issues, and launch the server or Web app.
Automate Deepgram operations through Rube MCP, a connection for agent tools. The skill finds available actions, checks the service connection, and runs tasks using the latest required input fields.
Get documentation-based help with deepsec, an AI vulnerability scanner. Initialize or resume setup, configure scans and model credentials, and create detection rules or plugins using the documentation bundled with the installed version.
Set up Everything Claude Code skills and hooks in DeepSeek Harness. Covers linking skill folders, generating hook settings, checking that hooks run, updating the setup, and investigating missing skills or inactive hooks.
Adapt existing PyTorch training scripts to use multiple GPUs or machines with limited code changes. The skill guides configuration, launch commands, mixed precision, which uses lower-precision numbers, and DeepSpeed or FSDP settings for distributing training work and memory.
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.
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.
Design and improve DeepTutor skills by turning concrete usage examples into reusable instructions. Learn how to write descriptions that signal when to use a skill, structure SKILL.md, and separate supporting reference material.
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.
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
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.
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.
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.
Build third-party tools to inspect, extract, migrate, or analyze DeepChat's local settings and conversations. Work through data locations, database encryption, and table relationships while favoring read-only copies and redacted output.
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.
Adapt PyTorch training scripts for multiple GPUs or machines with Accelerate. This skill guides code changes, configuration, and launch commands, including mixed precision, which combines numerical formats, and DeepSpeed or FSDP integration for distributed training.
Add an LLM provider to DeepChat by choosing a suitable API connection method, updating authentication and model configuration, and making focused source changes with tests for the affected behavior.