Loading...
Loading...
Found 41 Skills
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend at up to 17x lower cost.
Expert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.
Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs optimization events to chat.
Command-line interface for Novita AI - An OpenAI-compatible AI API client for DeepSeek, GLM, and other models.
Terminal AI coding assistant optimized for DeepSeek v4 with deep thinking, reasoning control, Agent Skills, and MCP integration
DeepSeek AI large language model API via curl. Use this skill for chat completions, reasoning, and code generation with OpenAI-compatible endpoints.
DeepSeek integration. Manage Organizations. Use when the user wants to interact with DeepSeek data.
Only use this when the user requests to configure, check, test, repair, disable, or uninstall the DeepSeek native sub-Agent of Codex; do not trigger it for ordinary DeepSeek API issues or daily coding tasks after configuration.
Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode, Goose, Cursor, Antigravity, and Amp logs. Use when the user asks about AI-agent sessions, tokens, tool/search calls, model usage, estimated cost, budgets, forecasts, health checks, reports, setup diagnosis, web/API/metrics exports, or MCP integration.
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 you need to 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.
Code review closeout for Claude Code, Codex, OpenCode, and DeepSeek TUI: local dirty changes, branch vs main, parallel tests.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.