skills

Collaborative planning using abstract roles (designer + inspiration + reviewer).

Async via ask, end turn immediately; use when user explicitly delegates to any AI provider (gemini/codex/opencode/droid); NOT for questions about the providers themselves.

AutoFlow entry point. Routes to tp (plan) or tr (run).

Attach the newest context-transfer Markdown from the current project's ./.ccb/history/ into Claude using @file. Use when the user types /continue or asks to resume with the latest transfer file in this project.

Diagnose ROS 2 systems with evidence-first checks across nodes, topics, lifecycle states, QoS, and pipeline data flow. Use when debugging ROS 2 node discovery, topic connectivity, lifecycle, message flow, QoS, or CUDA-related suspicions.

Delegate file I/O to Codex via FileOpsREQ protocol. Use when Claude needs Codex to modify files.

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

Report which CCB providers are mounted (session exists AND daemon is online). Outputs JSON.

Generate Excalidraw diagrams from text content for Obsidian, with first-class support for AI model architecture diagrams (VLA, Transformer, Diffusion Policy, multi-system pipelines). Use when user asks to draw, visualize, or diagram concepts. Triggers on "Excalidraw", "画图", "流程图", "思维导图", "架构图", "模型结构", "可视化", "diagram", "architecture".

Insert a completed paper summary (from paper_summary/) into one of the four survey posts (VLA, VLM, World Models, or Spatial Intelligence) based on its theme. Use when the user requests to insert a summary into a survey post, e.g., "把文章插入到 VLA 综述", "add summary to world models survey", "insert paper into survey". Automatically updates heading numbers, anchors, and post date.

通过论文标题或链接快速生成中文摘要。当用户提供论文标题或链接（arXiv、OpenReview、会议论文等）并要求总结时自动触发。自动搜索并总结论文内容，以结构化 Markdown 格式保存到 C:\Users\tingd\.claude\skills\paper-summary\output。适合快速了解论文核心思想。触发词示例："总结这篇论文"、"summarize this paper"、提供论文链接或标题。

Fully automated paper summarization with optimized image extraction. First analyzes PDF to identify key figures, then extracts ONLY relevant images from specific pages (resource efficient). Generates structured Chinese summaries with key takeaways (精华), and processes images with smart renaming and cleanup. Use for VLN, VLA, VLM, RL, and Robotics papers. Just provide PDF path - everything else is automated.

Automatically compress PDF files when they are too large for processing. Use this skill when (1) a PDF file exceeds 10MB and needs compression for efficient processing, (2) user explicitly requests PDF compression, (3) reading a PDF fails with a file size error, or (4) a PDF exceeds the 32MB API limit. Compresses using Ghostscript while maintaining acceptable quality.

Translate an English (academic/research) PDF into a clean Chinese-version PDF. Free-flowing single-column reflow (NOT layout-preserving, since Chinese and English occupy very different space), with figures/tables/equations cropped from the original PDF as pixel-perfect images and inserted near their references. Use when the user provides an English paper PDF and asks for a 中文版 / Chinese version / 翻译成中文 / "转为中文版本pdf". Triggers: "把这篇论文转成中文", "translate this paper to Chinese pdf", "英文论文转中文版", "pdf-e2c".

Extract figures and/or tables from PDF files using the TF-ID model (Florence2-based object detection). Outputs cropped images with a Markdown index. Use when user wants to extract figures, tables, or images from a PDF file — e.g., "extract all figures from this PDF", "get the tables from paper.pdf", "extract images from pages 3-7". Requires conda TF-ID environment with pdf2image, transformers, pillow.

View latest reply from AI provider (gemini/codex/opencode/droid/claude).

Test connectivity with AI provider (gemini/codex/opencode/droid/claude).

Analyze GitHub projects and generate comprehensive architecture documentation (architecture.md). Use when users request project analysis, architecture summaries, or documentation of code structure. Triggers on queries like "analyze this GitHub project", "generate architecture.md", "summarize project structure", or "document the codebase architecture".

Generate or update a high-quality Chinese version (README_CN.md) based on the existing README.md. Triggered when the user asks for a Chinese version, translation, or creation of Chinese documentation. Automatically handles language switcher links, technical term translations, and anchor navigation for long documents.

Dual review with Claude and Codex for quality verification. Use for step or task review.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Create a task plan with collaborative design. Use when starting a new task or running /tp.

Execute current step in AutoFlow workflow. Use when running /tr or continuing task execution.

Extract and save subtitles from video URLs as plain .txt files. Supports Bilibili (B站) and YouTube. Use when the user provides a Bilibili or YouTube video link and asks to extract, download, or save subtitles/captions. Triggers on phrases like "提取字幕", "下载字幕", "extract subtitles", "get subtitles", or when a bilibili.com / youtube.com / youtu.be URL is provided with a subtitle-related request.

Find and analyze key embodied navigation (VLN/VLA/WAM) projects and models from the past week in the user's collected repository. Trigger this skill when the user asks to analyze, summarize, or extract key projects, models, or weekly updates from the ENav repository (e.g., '分析 ENav 里的资料', '提取上一周的具身导航关键项目', '每周具身智能导航项目总结').

Insert a completed paper summary into the VLN Papers blog post (C:/GitHub/Tingde.Liu.github.io/_posts/2026-01-05-VLN-Papers.md). Use after the paper-summary skill completes, when the user says things like "把总结添加到VLN博客", "补充进去", "加到VLN论文列表", or "insert into blog post". Handles five insertion points automatically: main content section (with {#anchor}), TAG_MAP entry, numbered reference entry, the 已发表论文（会议 / 期刊）venue table (published papers only), and (optional) 性能排行榜 rows.

每周工作周报生成助手。帮助用户通过问答式收集本周工作信息，自动读取项目 architecture.md 获取技术背景，结合周报模板和提交规范，生成符合格式的 Markdown 周报文件并保存到正确路径。触发词示例："帮我写周报"、"填写周报"、"生成本周周报"、"协助完成周报"。

Set up a Claude Code custom status line on Windows. Use when the user wants to configure statusLine in settings.json on Windows, especially when bash/jq-based scripts fail due to missing jq or Unicode encoding errors. Provides a ready-to-use Python script showing model name, context usage bar (color-coded), session cost in USD, and 5h/7d rate limit percentages.