Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.

Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers on keywords: lint, format, check, validate, types, static analysis.

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

当执行 BD（商务拓展）任务时维护 SQLite 情报采集数据库，记录已采集的信息内容，避免重复采集，支持按日查询已采集情报。

从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF, arXiv PDF, conference paper PDF, journal paper PDF, or local/remote PDF URL.

Reference: DEPRECATED — use `/draft` instead. This skill has been folded into the draft skill, which handles practice-area document generation including form population. Kept as a redirect for migration.

Write or update a handoff document so the next agent with fresh context can continue this work.

Run the infrastructure health check and fix anything that fails

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Use this skill whenever Sales is explicitly invoked or the task involves customer meeting preparation, call follow-up, account prioritization, account signals, deal strategy, business cases, competitive briefs, forecasts, customer evidence, rep coaching, company research, CRM context, or company and contact enrichment.

AI Berkshire skill: 看懂XX公司（深度公司系列）：3-8 篇长文拆一家公司. Source: skills/deep-company-series.md.

Use when asked to run unit tests.

Slate v2 Autoresearch recipe picker. Lists/recommends Codex Autoresearch recipes, produces read-only setup plans, and maps non-perf loops such as test runtime, typecheck, bundle size, memory, command latency, and quality-gap.

Researches and synthesizes external best practices, documentation, and examples for any technology or framework. Use when you need industry standards, community conventions, or implementation guidance.

Use when working with WizTelemetry Logging extension for KubeSphere, including installation, configuration, and log query API

Use when managing credentials in KubeSphere DevOps, including repository credentials, kubeconfig, and API tokens

screenshots, recording, presentation artifacts, validate visually. Supplementary Daytona screenshots and optional videos after testkit validation.

WebAssembly expert for WASI, component model, Rust/C compilation, and browser integration