Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
Analyze connections across read papers and generate actionable research ideas.
Install Idea Generator
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/idea-generator .claude/skills/idea-generator && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .claude/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/idea-generator .agents/skills/idea-generator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .agents/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/idea-generator .cursor/skills/idea-generator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .cursor/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AlphaLab-USTC/ResearchClaw.git --path skills/idea-generator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/idea-generator .gemini/skills/idea-generator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .gemini/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/idea-generator .github/skills/idea-generator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .github/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AlphaLab-USTC/ResearchClaw idea-generator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AlphaLab-USTC/ResearchClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/idea-generator .opencode/skills/idea-generator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "idea-generator" agent skill from https://github.com/AlphaLab-USTC/ResearchClaw/tree/main/skills/idea-generator into .opencode/skills/idea-generator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
idea-generator- GitHub stars
- 134
- Token cost
- ~1.1k tokens
- SKILL.md length
- 409 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Analyze connections across read papers and generate actionable research ideas.
- Works in 4 steps: Gather paper corpus → Identify research gaps → Generate idea proposals → …
- User says: 给我一些研究灵感
- SKILL.md covers ⚙️ Step 0 — Read the Research… and ⚠️ Error Handling
- Reaches ar5iv.labs.arxiv.org
What it does
Idea Generator is an agent skill from AlphaLab-USTC/ResearchClaw. Analyze connections across read papers and generate actionable research ideas. Use when user says: 给我一些研究灵感, idea generator, 跨论文分析, research ideas.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Hypothesis generation. The repository describes itself as: 上朝式科研：AI-powered research workflow showcase. The licence is MIT.
When your agent uses it
- User says: 给我一些研究灵感
- Tasks that involve Hypothesis generation
Example prompts
- “/idea-generator”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9d64c4b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
ar5iv.labs.arxiv.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Idea Generator loads about 1.1k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 409 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from AlphaLab-USTC/ResearchClaw at commit 9d64c4b, republished under its MIT licence (© AlphaLab-USTC). 409 words, ~1,113 tokens.
Download SKILL.mdSave it as
.claude/skills/idea-generator/SKILL.md (or your agent's skills folder).- name
- idea-generator
- description
- Analyze connections across read papers and generate actionable research ideas. Use when user says: 给我一些研究灵感, idea generator, 跨论文分析, research ideas.
Idea Generator — Cross-Paper Insights
⚙️ Step 0 — Read the Research Profile (Always First)
Before running any capability, load the user's research profile.
Location: ~/.openclaw/workspace/research-claw-config.md
If this file does not exist, use these defaults silently and mention at the end:
💡 想定制推荐兴趣？试试说「更新我的研究画像」
# Default profile (used when no config found)
research_direction: "Large language models, reinforcement learning, agentic AI"
seed_papers: []
keywords:
- large language models
- reinforcement learning
- agentic AI / AI agents
- retrieval-augmented generation
- multimodal models
whitelist_authors: []
learned_preferences:
accept: []
reject: []Config fields reference:
research_direction— free-text description of the user's research focusseed_papers— list of arXiv IDs the user considers gold-standard referenceskeywords— interest topics used for Paper Scout search querieswhitelist_authors— researcher names to prioritize in recommendationslearned_preferences.accept— keywords/topics user has explicitly likedlearned_preferences.reject— keywords/topics user has skipped or disliked
Goal: Analyze connections across the user's read papers and generate 3–5 actionable research ideas.
Triggers: 给我一些研究灵感 · idea generator · 跨论文分析 · research ideas
Step 1 — Gather paper corpus
- Load
~/.openclaw/workspace/research-claw-reading-list.json - Filter papers with
status: "done"orstatus: "reading"(i.e., papers the user has actually engaged with) - For each paper, load its HTML note from the
note_linkfield (if available) or re-fetch abstract from arXiv - Extract: title, method summary, results, takeaway, tags for each paper
If fewer than 3 papers in the corpus, inform the user:
💡 你当前已读论文较少（{N} 篇）。建议先用"帮我读一下"深读几篇，效果会更好！以下基于现有内容生成。
Step 2 — Identify research gaps
Analyze the collected papers for:
- Recurring unsolved problems: limitations mentioned across multiple papers
- Methodology mismatches: technique A works in domain X but hasn't been tried in domain Y
- Evaluation gaps: common benchmarks that none of the papers tackle
- Combination opportunities: two methods from different papers that could be synergistically combined
- Scaling questions: results that hold at small scale but haven't been validated at large scale
Show full SKILL.md (161 more words)Show less
Step 3 — Generate idea proposals
Produce 3–5 research ideas. For each idea, output:
💡 Research Idea {N}: **{CATCHY_TITLE}**
📋 **Problem Statement**
{1-2 sentences: what specific gap or challenge does this idea address?}
🔧 **Proposed Approach**
{2-3 sentences: how would you tackle it? What's the key insight?}
📚 **Related Papers**
• {Paper 1 title} — {how it connects}
• {Paper 2 title} — {how it connects}
🎯 **Feasibility Assessment**
- Dataset: {what data is needed / what's available}
- Compute: {estimated compute requirements}
- Timeline: {rough estimate for a first experiment}
- Risk: {main technical risk}
⭐ **Why Now?** {1 sentence — why this is timely / what makes it tractable today}Step 4 — Output
Format all ideas in sequence. End with:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
💾 想把某个灵感发展成论文？说 "帮我写论文" 并描述你选中的想法！⚠️ Error Handling
| Error | Handling |
|---|---|
| arXiv API returns empty results | Retry once with broader query; if still empty, note "arXiv API temporarily unavailable" |
| PDF tool times out | Fall back to abstract-only mode; note [Abstract only — PDF timeout] in the note |
| PDF tool returns error for a paper | Try fetching https://ar5iv.labs.arxiv.org/html/{ARXIV_ID} as HTML fallback |
| Config file missing | Use defaults silently; add a note at end: "💡 想定制？说「更新我的研究画像」" |
| Reading list JSON missing or malformed | Start fresh with an empty list; inform user: "未找到现有列表，已新建空列表" |
| Template file not found | Report the expected path and ask user to check installation |
| No papers in last 3 days | Extend to 7 days, note it: "（近3天论文较少，已扩展至7天）" |
| Fewer than 3 read papers for Idea Generator | Proceed anyway, but note the limitation |
| User provides PDF/DOI instead of arXiv | Try to extract arXiv ID from DOI or search arXiv by title |
© AlphaLab-USTC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/idea-generator of AlphaLab-USTC/ResearchClaw.
Open the folder on GitHubat commit 9d64c4b
Compare with similar skills
Idea Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Idea Generator this skillAlphaLab-USTC/ResearchClaw | 134 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Hypothesis Generationspacering-net/codeg | 3.8k | 15 repos | ~3.6k | Automated safety check: Notes | MIT | |
| Nature Paper CardYuan1z0825/nature-skills | 46k | 2 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Hypothesis GenerationK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Good QuestionRimagination/good-question | 305 | 1 repos | ~4.3k | Automated safety check: Pass | MIT | |
| Claim-Driven Experiment PlannerzjYao36/Auto-Research-Refine | 128 | 7 repos | ~2.3k | Automated safety check: Notes | None |
Similar skills
Nature Paper Card
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
Hypothesis Generation
K-Dense-AI/claude-scientific-writer
Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready…
Good Question
Rimagination/good-question
A skill your agent uses when a researcher is choosing, framing, refining, or stress-testing a research question, hypothesis, thesis topic, project idea, grant direction, paper angle, or stalled…
Claim-Driven Experiment Planner
zjYao36/Auto-Research-Refine
Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.
High Stakes Analytics Decision Lab
limingrui679-design/high-stakes-analytics-decision-lab
Build or review source-backed descriptive, diagnostic, predictive, and prescriptive analysis for consequential decisions.
More from AlphaLab-USTC/ResearchClaw
Paper Reader
AlphaLab-USTC/ResearchClaw
Deep-read an arXiv paper and generate structured Deep Note reading notes.
Paper Scout
AlphaLab-USTC/ResearchClaw
Discover and recommend latest arXiv papers matching user research interests.
Paper Writer
AlphaLab-USTC/ResearchClaw
Help write research papers: outline, draft sections, auto-review, and rebuttal.
Reading List
AlphaLab-USTC/ResearchClaw
Manage a personal reading list with kanban-style statuses and HTML dashboard.
Research Claw
AlphaLab-USTC/ResearchClaw
Complete AI research assistant with 6 core capabilities: paper discovery, deep reading notes, reading list management, research taste learning, idea generation, and paper writing.
Research Profile
AlphaLab-USTC/ResearchClaw
Maintain and visualize the user research preference profile.
Related
Categories
Questions about Idea Generator
What does Idea Generator do?
Analyze connections across read papers and generate actionable research ideas. Idea Generator is an agent skill from AlphaLab-USTC/ResearchClaw. Analyze connections across read papers and generate actionable research ideas.
When should I use Idea Generator?
Idea Generator fits situations like: user says: 给我一些研究灵感; tasks that involve Hypothesis generation.
How do I install Idea Generator in Claude Code?
Run `npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a claude-code`. Or copy the skill folder (skills/idea-generator in AlphaLab-USTC/ResearchClaw) into .claude/skills/idea-generator in your project. Claude Code loads it when a task matches its description.
How do I install Idea Generator in Codex?
Run `npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a codex`. Or copy the skill folder (skills/idea-generator in AlphaLab-USTC/ResearchClaw) into .agents/skills/idea-generator in your project. Codex loads it when a task matches its description.
Can I use Idea Generator in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AlphaLab-USTC/ResearchClaw --skill idea-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/idea-generator, .gemini/skills/idea-generator, .github/skills/idea-generator and .opencode/skills/idea-generator in your project.
What does Idea Generator need to run?
SKILL.md names no scripts, command-line tools or credentials: Idea Generator is instructions for the agent only.
Does Idea Generator access the network?
SKILL.md names 1 domain. In commands or code: ar5iv.labs.arxiv.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Idea Generator safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Idea Generator use?
Idea Generator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Idea Generator use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Idea Generator?
Skills that share tags, products or a category with Idea Generator: Hypothesis Generation (spacering-net/codeg, 3.8k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars), Hypothesis Generation (K-Dense-AI/claude-scientific-writer, 2.4k stars) and Good Question (Rimagination/good-question, 305 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Idea Generator?
AlphaLab-USTC (a GitHub user) maintains it in AlphaLab-USTC/ResearchClaw, which has 134 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on April 7, 2026.
Source: AlphaLab-USTC/ResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.