Research Idea and Battle
Engage this skill whenever the user wants rigorous academic discussion about AI/ML research ideas — whether brainstorming new directions, stress-testing a hypothesis, debating novelty and significance, or seeking high-level research mentorship. Trigger on: 'I have a research idea', 'let's battle this', 'is this novel enough', 'what would reviewers think', 'help me think through this direction', 'I want to explore X as a research problem', 'critique my idea', 'what's the contribution here', 'how do I position this', 'is this worth pursuing', 'what are the weaknesses', 'what's happening in this
Install
npx skills add Punktheory/research-idea-and-battle --skill research-idea-and-battlegit clone --depth 1 https://github.com/Punktheory/research-idea-and-battle.git /tmp/research-idea-and-battle
mkdir -p ~/.claude/skills
cp -r /tmp/research-idea-and-battle/. ~/.claude/skills/research-idea-and-battlePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Research Idea & Battle Skill --- ## Who You Are You are a tenured senior professor — the kind who has been in the field long enough to have watched entire research directions rise, peak, and quietly die. You have deep expertise spanning machine learning, computer vision, NLP, generative models, and their intersections with science and medicine. You have reviewed for NeurIPS, ICML, CVPR, ICLR, ECCV, MICCAI, and dozens of workshops. You have advised PhD students who became faculty, and you have seen students chase fashionable ideas into dead ends. Your value is not just knowing what's been done — it's knowing *why* things failed, *when* an idea is premature vs. timely, and *which* kernel inside a flawed idea is worth saving. You are intellectually honest, occasionally blunt, and genuinely invested. You do not perform enthusiasm. You do not crush ideas. You stress-test them because you respect the person enough to tell them the truth. --- ## Step 0: Build the Map Before You Talk (Non-Negotiable) A professor who opines without reading is just an older person with opinions. Before any substantive response, you do three things in parallel: ### 1. Survey the landscape (field-level) ``` WebSearch: "[topic] survey 2023 OR 2024" WebSearch: "[topic] tutorial NeurIPS 2024 OR ICML 2024" WebSearch: "[topic] overview recent advances" ```
Details
- Skill name
research-idea-and-battle- Repository
- Punktheory/research-idea-and-battle
- Repo updated
- 19 May 2026
FAQ
What does the Research Idea and Battle skill do?
Engage this skill whenever the user wants rigorous academic discussion about AI/ML research ideas — whether brainstorming new directions, stress-testing a hypothesis, debating novelty and significance, or seeking high-level research mentorship. Trigger on: 'I have a research idea', 'let's battle this', 'is this novel enough', 'what would reviewers think', 'help me think through this direction', 'I want to explore X as a research problem', 'critique my idea', 'what's the contribution here', 'how do I position this', 'is this worth pursuing', 'what are the weaknesses', 'what's happening in this
How do I install the Research Idea and Battle skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Punktheory/research-idea-and-battle --skill research-idea-and-battle. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Research Idea and Battle popular?
It lives in Punktheory/research-idea-and-battle, which has 100 GitHub stars and 2 forks.
Related skills
Research Innovation Explorer
86foryourhealth111-pixel/research-innovation-explorer
Build literature-grounded research-question candidate landscapes by collecting papers, generating A+B matrices, and dynamically reviewing combinations with traceable evidence, uncertainty, and next checks. Use when an AI agent needs to explore a field, screen research questions, compare paper combinations, inspect prior art, or prepare a provisional shortlist for researcher review.
Paper Format Agent
87zxyasfas/paper_format_agent
Use this skill when a user needs to inspect, score, repair, or regression-test academic paper formatting in DOCX files, especially thesis, journal, or conference documents with a separate format specification. The skill guides Codex through local-first document handling, rule extraction, formatting repair, report review, and contribution-safe validation.
Chinese Reference Formatter Skill
79Zechang-Xiong/chinese-reference-formatter-skill
根据中英文文献题名核验公开元数据，生成通用中文参考文献和 BibTeX。Use for Chinese academic references, GB/T 7714-style bibliography formatting, and citation completion from literature titles.
Luo Ming Color Science
92Ayueh0102/Ronnier-skill
回答色彩科學／色度學問題時使用。涵蓋 CIE 色度學、XYZ 三刺激值、光源與色溫、色彩量測儀器與不確定度、色視覺與對立色理論、心理物理學實驗設計、色序系統（Munsell／NCS／Ostwald／DIN）、色差公式（CIELAB／CMC／CIE94／CIEDE2000）、影像色差與 S-CIELAB、同色異譜、色貌模型（CIECAM02／CAM16）、色適應變換（CAT02）、演色性（CRI／Rf／Rg）。觸發語如「色差公式」「CIEDE2000」「CIECAM02」「Munsell」「NCS」「色貌」「色適應」「演色性」「同色異譜」「亮度跟明度差在哪」「幫我複習色彩學」，或提到羅明（Ming Ronnier Luo）教授的色彩學課程。
Literature Review Skills
75xingtaxueshu/literature-review-skills
Use when the user wants to do a literature review but does not know which step to start with, or asks which of the five literature-review skills (refine question, decompose modules, compare methods, map contradictions, locate research gap) to use. 用户要做文献综述但不知从哪步开始时使用；也用于选题太宽、综述结构、方法比较、文献矛盾、研究空白等综述各阶段的分流。
Paper Deep Reader
108Linwei-Chen/paper-deep-reader-skill
为单篇学术论文生成来源可追溯、图文交错、零背景可进入且具博士级技术深度的中文或英文解读。默认按“一句话总结、背景与动机、核心方法、实验与结果、贡献与影响、结论”六部分成稿，首次出现即解释关键术语，用最小例子讲通机制，并截图、嵌入、逐一解读所有关键图表；兼容有视觉与纯文本环境。用户提供 PDF、URL、DOI、预印本标识、标题或全文并要求论文解读、精读、讲清楚、逐关键图表、方法/公式/实验解释时使用。只问局部问题时可定向回答；不用于全文逐句翻译或多论文综述。
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.