Machine learning

Perform a decision-focused ML architecture investigation with evidence, alternatives, trade-offs, risks, and a leading recommendation.

Retrieve relevant excerpts from a project's text files without loading entire files into context.

Designing conversational flows for website chatbots and AI agents.

LLM-assisted literature review for HDD (Phase 0)

Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI…

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use this skill when designing, cleaning, deduplicating, or documenting datasets for model training and evaluation including schema design, class imbalance…

Programmatic video with Remotion in React.

Apply hugging face datasets in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation.

Plan, implement, or review hugging face gradio work in an existing codebase with compatibility, security, and verification controls.

Apply pytorch geometric in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation.

Corrects outdated LLM knowledge about the Vercel platform and introduces new products.

Proactively suggest the right Convex component when the user hand-rolls what already exists: setInterval polling → crons, counter increments →…

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

AI 与 MCP 安全评估 — Prompt 注入、工具滥用、MCP 信任边界、Agent 权限逃逸、数据泄露、模型风险、GAARM 风险矩阵。Use when testing LLM-based applications, MCP servers, agent orchestration systems, AI…

A measurement-first workflow for slow inference, startup, UI rendering, file processing, memory pressure, throughput, latency, or suspected bottlenecks.

Use when adding LLM/chat/RAG features to a Unity game or tool: API keys, prompt assets, safety, latency, and server-side vs client-side calls.

Use when working on Unity ML-Agents: training configs, BehaviorParameters, sensors, actuators, inference in builds, or com.unity.ml-agents packages.