Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.

Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.

Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.

AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.

Build image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.

Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.

When a founder needs demo scripts, discovery call frameworks, objection handling, RFP/RFI responses, competitive feature matrices, POC planning, or closing playbooks. Activate for sales calls, demo prep, talk tracks, bid responses, competitor comparisons, or pre-sales engineering.

When a founder needs to create a sales proposal, statement of work, contract, NDA, or master service agreement. Activate when the user mentions proposal, SOW, quote, contract, NDA, MSA, or needs to formalize a deal.

When the user needs to design an interview process, create interview questions, build scorecards, calibrate interviewers, or evaluate candidates for a role.

When the user needs to plan, prioritize, or structure a content program -- including identifying content pillars, mapping content to the buyer journey, choosing content types, or building an editorial calendar.

Use when writing or reviewing Go code in this repo that runs a Deepgram Voice Agent session over WebSockets, including runtime settings, prompt updates, speak updates, injected messages, and event handling. Route standalone STT/TTS work to deepgram-go-speech-to-text or deepgram-go-text-to-speech.