剪映 (JianYing) AI自动化剪辑的高级封装 API (JyWrapper)，提供开箱即用的 Python 接口，支持录屏、素材导入、字幕生成、Web 动效合成及项目导出。全面适配 MacOS (Apple Silicon/Intel) 与 Windows，支持 v5.9+ (draft_info.json) 架构、工程自修复、智能配音字幕及录屏变焦。

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Agent-driven YOLO fine-tuning — annotate, train, export, deploy

Activate the AIOX Master Orchestrator & Framework Developer agent (Orion). Use when you need comprehensive expertise across all domains, framework component creation/modification, workflow orchestration, or running tasks that don't require a specialized persona. Trigger when user asks to aiox-master, or says 'activate aiox-master', 'switch to aiox-master', '@aiox-master'.

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.

根据数据量自动选择读取策略（大文件转Parquet），提取关键指标进行单位一致性验证与排序分析，并输出可下载的结果表格。

根据数据规模动态选择处理策略，对多表数据进行合并、统计筛选，并利用 openpyxl 实现关键指标的自动化样式高亮与格式化导出。

Read release notes/changelogs, update a defined dependency scope, handle breaking changes, and verify. Explicit-only; no broad update-everything by inference.

Choose and produce an appropriate chart/dashboard/visual explanation from data, with legible encodings and source/assumption notes.

Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify. Explicit-only.

DNP3 attack — TCP/20000 (or 19999 serial-over-TCP) outstation enumeration, binary input / analog input poll, control relay output block (CROB) actuation, unsolicited reporting abuse, DNP3 Secure Authentication (DNP3-SA) downgrade, vendor-specific objects.

Extract a functional clone of a black-box ML model via prediction API queries, and infer whether specific records were in the training set (membership inference).

Guide for game-hacking technique taxonomy and threat modeling relevant to game security. Use this skill when researching memory access, code injection, overlays, input simulation, engine-specific attack surfaces, or how modern anti-cheat systems constrain user-mode, kernel-mode, hypervisor, and DMA-based cheat implementations.

Re-derive your knowledge system from first principles when structural drift accumulates. Analyzes dimension incoherence, vocabulary mismatch, boundary dissolution, and template divergence. Preserves all content while restructuring architecture.

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

AATMF T3 — Reasoning & Constraint Exploitation. System prompt override, constraint negation, role-reversal, instruction conflict exploit.

Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.

在实现任何功能或修复 bug 时使用，在编写实现代码之前