Machine learning

Review and propose general-purpose updates to skills used in the current conversation.

Measure Julia performance so that the number means something: allocations, type stability, timings and before/after comparisons, each in a cold process with…

给定 PMID/PMCID 取结构化全文（NLM BioC XML/JSON）。封装 BioC PubMed（标题+摘要）和 BioC PMC OA（开放获取全文）端点，输出按章节切分的段落、表格上下文、RAG 友好 chunk，适合大批量入向量库。Fetches structured fulltext from…

Distributed computing for larger-than-RAM pandas/NumPy workflows.

提供 Android CameraX 相机开发的技术指导。当实现相机功能、处理异步录制生命周期、使用 CameraX 对接底层硬件互操作（hardware interop），或集成 ML Kit 或 Media3 特效时使用。

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

Nine non-negotiable Skill Doctor product invariants.

MLflow 3 (open-source, pinned to 3.15) for classic-ML MLOps — logging and registering models, promoting versions across dev/staging/prod, standing up a…

Guided workflow for taking any ML codebase — including one with no experiment tracking at all, or one full of MLflow 2-era idioms — to a production-grade…

Production Ray (open-source, pinned to 2.57) for classic-ML workloads from training to serving — Ray Train, Tune, Data, Serve, Core, and cluster deployment on…

LLM workloads on open-source Ray (pinned to 2.57) — OpenAI-compatible serving with ray.serve.llm (vLLM-backed LLMConfig + build_openai_app) and batch…

用于诊断、评审或评分整份简历。当用户要求「诊断简历」「简历有什么问题」「看看简历哪里要改」「简历打分」「评审简历」「resume review」，或上传 PDF/DOCX 并要求分析问题、给出评分或修改建议时触发。输出 3 类诊断（NO_DATA / NO_FILL / DESCRIPTION_SUGGEST）和…

This skill should be used when designing, planning, implementing, or reviewing any system that involves LLM agents, tool use, prompt construction, or agentic…

Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.

GitHub issue triage and integration review agent for the b00ty-verse.

Tool for preparing PDF figure files for embedding in LaTeX (e.g., with \includegraphics).

Compute and analyze embeddings for dataset quality, distribution comparison, semantic deduplication, diversity measurement, and similarity-based filtering.

Use locally-hosted LLMs (vLLM/SGLang) for dataset filtering, quality scoring, rewriting, labeling, and synthetic data generation.

Use this skill for web search, extraction, mapping, crawling, and research via Tavily’s REST API when web searches are needed and no built-in tool is…

Set up Actual Computer (actual.inc) inference in Hermes.

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

LLM-обогащение готового architecture.json — память агентов, семантические dataflow-связи, назначение модулей; всё бездоказательное merge сам пометит inferred…

Find and rank datasets for a replication or ML task by requirements, license, and availability.