A portable agent skill for writing top-conference embodied-AI papers, distilled from 63 papers.
embodied-ai-paper-writer is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
npx skills add OpenGHz/embodied-ai-paper-writerRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This is a skill file that you can load into any LLM agent (like Claude Code or Cursor) to get expert coaching on writing robotics and AI research papers. It contains patterns and rules extracted from 63 real papers from top conferences, covering titles, abstracts, methods, figures, and more. It doesn't run experiments or validate claims—it just helps you write better.
Embodied AI Paper Writer is a portable agent skill (SKILL.md + reference playbooks) that coaches the writing craft of embodied-AI papers. It is distilled from 63 top-conference papers across CoRL, RSS, ICRA, IROS, and Science Robotics (2022–2026). The skill works with any LLM agent that can load markdown context, such as Claude Code, Cursor, Continue, Cline, Aider, or custom agents using Anthropic/OpenAI SDKs. It teaches title patterns, abstract moves, intro arcs, method organization, experiments framing, results paragraph rhythm, ablation narration, figure roles, caption templates, table conventions, conclusion/limitations/future work, section openers, pivots, connectors, and a phrasebook of openers, hedges, and anti-patterns. The skill does not decide which experiments to run, validate technical claims, suggest research directions, translate, or run LaTeX builds. Each rule traces back to observed patterns in the 63-paper corpus, making it quantified and corpus-tuned rather than generic advice.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 9 days ago.
1 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Write or refine the abstract for a CoRL or RSS submission.
Caption figures with proper templates and conventions.
Review and improve the narrative arc of a paper draft.
Fix a Limitations section that sounds defensive.
Get guidance on title patterns and contribution statements.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
The skill does not validate technical claims or experimental results; users must ensure accuracy.
It may produce content that inadvertently plagiarizes if not used with original ideas.
No security risks as it is a static markdown file with no executable code.
1
Stars
1
Forks
0
Issues
MIT
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
5 security/trust notes recorded.
Setup difficulty is 2/5.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.