AI research workflow framework for project setup, GPU experiments, agent collaboration, Feishu remote control, and reproducible paper pipelines.
This repository also configures its own agents. See what Labline tells them →
Skill Claude Code
Manage Feishu/Lark remote Codex or Claude Code access, with lark-channel-bridge as the default transport and Labline phone-session reports as legacy/fallback audit support. Use when user mentions Feishu/Lark control, phone control, mobile takeover, session merge, or wants to start/stop/report a Feishu-controlled…
Skill Claude Code
A tool for turning user-provided patent drawings into formal written descriptions, using the reference numbers shown in the figures.
Skill Claude Code
A diagram generator that turns structured FigureSpec data into precise, editable SVG diagrams.
Skill Claude Code
A guide for turning scattered research assumptions and equations into a clear mathematical derivation. It is intended for building a theory line or producing paper-ready formula notes.
Skill Claude Code
A skill for updating the Labline framework by pulling the latest code and rebuilding symbolic links. A symbolic link is a filesystem shortcut to another file or folder.
Skill Claude Code
Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
Skill Claude CodeCodex
Set up Claude Code or Codex guardrails to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset.
Skill Claude Code
A skill for turning research ideas and related literature into a structured grant proposal. It supports formats used by funding agencies in Japan, the United States, China, the European Union, Germany, Switzerland, Australia and the Netherlands.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Skill Claude Code
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude Code
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Skill Claude Code
A research workflow for robotics and embodied AI, meaning artificial intelligence that acts through a robot or other physical system. It moves from a broad research direction to ideas checked against existing studies and benchmarks.
Skill Claude Code
A workflow for turning a broad research direction into tested ideas. It coordinates research, idea creation, checks for whether ideas are new, and review of the research evidence.
Skill Claude Code
A research-project setup tool that creates a new project with a directory, Git repository, development skills, project instructions, and configuration. It can also push the project to a remote Git repository.
Skill Claude Code
A way to turn a rough invention idea into an invention disclosure, a structured document describing an idea for possible patent review.
Skill Claude Code
A document-formatting tool for preparing patent applications for different countries or patent offices. It supports requests for Chinese, United States, and European filing formats.
Skill Claude Code
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2…
Skill Claude Code
A Chinese-language orchestration workflow that coordinates coding, deployment, writing, and independent review roles.
Skill Claude Code
Generate Mermaid diagrams from user requirements. Saves .mmd and .md files to figures/ directory with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
Skill Claude Code
A tool for studying Labline usage logs and suggesting improvements to its skills, reviewer prompts, and workflow defaults.
Skill Claude Code
Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
Skill Claude Code
A research-checking guide for finding out whether a proposed idea has already appeared in recent academic papers.
Skill Claude Code
Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: