Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
figure-spec
figure-spec is an open-source workflow skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spe…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/figure-spec`.
What figure-spec does
Generate publication-quality **architecture diagrams**, **workflow pipelines**, **audit cascades**, and **system topology** figures as editable SVG vector graphics using a deterministic JSON → SVG renderer.
Installation
Add figure-spec to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/figure-specAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for figure-spec is organised into these sections:
- When to Use This Skill
- Core Properties
- Tool Location
- Workflow
- Step 1: Understand the Diagram Goal
- Step 2: Draft the FigureSpec JSON
- Step 3: Render and Validate
- Step 4: Visual Review
- Step 5: Iterate with Codex Review (Optional, for High-Stakes Figures)
- Schema Quick Reference
- Nodes
- Edges
When to use it
Reach for figure-spec when you want workflow help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does figure-spec do?
- Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
- How do I install figure-spec?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/figure-spec in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is figure-spec free to use?
- Yes. figure-spec is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does figure-spec come from?
- figure-spec ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Workflow →Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
When you can't trust yourself with your code base, trust Arbiter.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.