Documents

亚马逊品类自动化选品分析技能。通过五维评分模型对亚马逊品类进行深度市场调研，生成Markdown分析报告。当用户使用 /category-selection 命令或提出'分析XX品类'、'XX品类市场调研'、'XX品类选品'等需求时触发此技能。支持配置分析数量，默认Top20。

Deterministic read-only Paperclip issue, document, and approval-link verification with strict JSON output.

Fetch page content as agent-readable markdown — articles, docs, READMEs, blogs, social posts, and academic papers.

Automated content aggregation from multiple APIs (arXiv, Hacker News, RSS feeds, etc.) into curated digests.

Fetch a page or produce a one-shot screenshot, PDF, or structured extraction without interactive browser control.

Fast persistent headless browser CLI for navigation, research, one-off page interactions, screenshots, downloads, and ad-hoc automation (~100ms per command…

Reverse-engineer a company's sales and marketing tech stack from public signals.

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

Automatically downloads LaTeX source from arXiv, translates it to a target language (default Chinese), and compiles it to PDF using xelatex.

Search 11 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance.

Create, run, diagnose, and iteratively improve Agent Skill evaluations (evals) with the skill-up CLI / 使用 skill-up CLI 创建、运行、诊断并持续改进 Agent Skill 评测.

Run the client website audit, an end-to-end SEO plus AEO/GEO review of a company site that ends in a six-section report delivered as markdown and .docx, plus…

撰写或修订中文学术论文、docx 短汇报和演示文稿时使用。核心是分阶段核对结构、数据与一手来源，并统一处理引用规范、查重、AI 标注和配图。

Build the "vibe check" page a DJ wakes up to before a gig — a single dark HTML page with a verdict, stats, every playlist in play order with key/BPM/energy…

Generate chart images for markdown documents using the QuickChart API.

Subskill of site-health — AI/agent indexing audit (llms.txt, /api/ai, markdown negotiation, robots vs AI crawlers, SPA-fake detection).

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool.

Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers.

A Codex Canvas is a live React app that the user can open beside the chat.

Fetches web content as clean markdown by preferring markdown-native responses and falling back to selector-based HTML extraction.

Build, run, and drive the skogai-routing-v2 plugin's channel MCP server and SessionStart hook.

Use when a task requires systematic multi-round research across multiple angles, sources, and validation steps before producing a conclusion or report.

A method to instantly internalize document contexts into language models using LoRA without fine-tuning.

Use when needing to look up book content, find a book by title/author, download an ebook, or reference material from a published book.