Paper Navigator
AI4Scientist/nano-scientist
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…
Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty.
Install Research Idea Generation
$ npx skills add lingzhi227/agent-research-skills --skill idea-generation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lingzhi227/agent-research-skills idea-generation --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/lingzhi227/agent-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/idea-generation .claude/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .claude/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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/lingzhi227/agent-research-skills/tree/main/skills/idea-generationType 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 lingzhi227/agent-research-skills --skill idea-generation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lingzhi227/agent-research-skills idea-generation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/idea-generation .agents/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .agents/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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 lingzhi227/agent-research-skills --skill idea-generation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lingzhi227/agent-research-skills idea-generation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/idea-generation .cursor/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .cursor/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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/lingzhi227/agent-research-skills.git --path skills/idea-generation--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 lingzhi227/agent-research-skills --skill idea-generation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lingzhi227/agent-research-skills idea-generation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/idea-generation .gemini/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .gemini/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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 lingzhi227/agent-research-skills idea-generationInstalls 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 lingzhi227/agent-research-skills --skill idea-generation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/idea-generation .github/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .github/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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 lingzhi227/agent-research-skills --skill idea-generation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lingzhi227/agent-research-skills idea-generation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/idea-generation .opencode/skills/idea-generation && 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-generation" agent skill from https://github.com/lingzhi227/agent-research-skills/tree/main/skills/idea-generation into .opencode/skills/idea-generation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "idea-generation", 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-generation- GitHub stars
- 390
- Token cost
- ~747 tokens
- SKILL.md length
- 274 words
- Files
- 3 (incl. scripts, references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- None found
At a glance
Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty.
- Works in 4 steps: Generate Ideas → Iterative Refinement (up to 5 rounds per… → Novelty Assessment → …
- Brainstorming new research directions for a given area or codebase
- SKILL.md covers Input, Scripts, References and Workflow, plus 3 more sections
- Runs Python scripts from its folder; calls python
What it does
The workflow runs in four steps. First it generates three to five diverse research ideas from a research area or codebase context, each with a name, title, experiment plan and ratings, using templates in references/ideation-prompts.md. Second, each idea goes through up to five rounds of refinement where the agent critically evaluates its quality, novelty and feasibility and revises it while preserving its core spirit, stopping early once the idea converges.
Third, promising ideas get a novelty assessment, either by running scripts/novelty_check.py, which performs an iterative multi-round literature search against Semantic Scholar and arXiv, or by searching those sources manually, ending in a binary novel-or-not verdict with justification. Fourth, every idea is scored one to ten on interestingness, feasibility and novelty, with rules calling for harsh, realistic ratings, no overfitting to one dataset or model, and sufficient contribution for a conference paper. The output is a JSON record per idea, and the skill names literature-search and deep-research as natural upstream skills and research-planning and experiment-design as downstream ones.
When your agent uses it
- Brainstorming new research directions for a given area or codebase
- Checking whether a research idea is novel against existing literature
- Scoring and comparing several candidate research ideas before committing to one
Example prompts
- “Generate some research ideas in federated learning for NeurIPS.”
- “Check whether this proposed idea about sparse attention is actually novel.”
- “Score these three research ideas on interestingness, feasibility and novelty.”
Requirements
- Python for scripts/novelty_check.py
- Network access to Semantic Scholar and arXiv for the novelty check
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Generate Ideas
- Iterative Refinement (up to 5 rounds per idea)
- Novelty Assessment
- Rank and Select
What it can do on your machine
Read from SKILL.md and the folder at commit 9e6c085. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Research Idea Generation loads about 747 tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 274 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 274 words (~747 tokens).
“Generate and refine novel research ideas with literature-backed novelty assessment.”
- name
- idea-generation
- argument-hint
- research-area
Files
SKILL.md and 2 other files (scripts, references) in skills/idea-generation of lingzhi227/agent-research-skills.
- SKILL.md
- references/ideation-prompts.md
- scripts/novelty_check.py
Open the folder on GitHubat commit 9e6c085
Compare with similar skills
Research Idea Generation 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 |
|---|---|---|---|---|---|---|
| Research Idea Generation this skilllingzhi227/agent-research-skills | 390 | — | ~747 | Automated safety check: Pass | None | |
| Paper NavigatorAI4Scientist/nano-scientist | 128 | — | ~7.7k | Automated safety check: Notes | None | |
| Math Discovery Evidence Searchtradecatlabs/vibe-coding-cn | 17k | — | ~554 | Automated safety check: Pass | MIT | |
| Novelty CheckGRIND-Lab-Core/night_owl_research_agent | 106 | — | ~1k | Automated safety check: Pass | None | |
| Literature Reviewneflibata-feng/MyArxiv-Agent | 126 | 20 repos | ~5.9k | Automated safety check: Notes | MIT | |
| Paper Research on arXivXiaomiMiMo/MiMo-Code | 14k | — | ~1.5k | Automated safety check: Pass | MIT |
Similar skills
Math Discovery Evidence Search
tradecatlabs/vibe-coding-cn
Turns a vague math interest into a bounded, searchable problem and builds a source-traced evidence graph, with novelty checks and conjectures drawn from evidence gaps.
Novelty Check
GRIND-Lab-Core/night_owl_research_agent
Validates that a research idea is genuinely novel vs. An agent skill from GRIND-Lab-Core/night_owl_research_agent.
Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
Paper Research on arXiv
XiaomiMiMo/MiMo-Code
Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.
Literature Review Agent
Ar9av/PaperOrchestra
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.
More from lingzhi227/agent-research-skills
All 31 skills in this repoBackward Traceability
lingzhi227/agent-research-skills
Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.
Statistical Data Analysis
lingzhi227/agent-research-skills
Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.
Excalidraw Canvas Toolkit
lingzhi227/agent-research-skills
Draws and refines Excalidraw diagrams on a live canvas through MCP tools or a REST API, with screenshots, file import and export, snapshots and Mermaid conversion.
Research Experiment Designer
lingzhi227/agent-research-skills
Plans research experiments in four progressive stages, from a first working implementation through baseline tuning and creative research to ablation studies.
Scientific Figure Generation
lingzhi227/agent-research-skills
Generates publication-quality scientific figures with matplotlib or seaborn through query expansion, a run-and-retry coding loop and a visual check of the rendered PNG.
Academic LaTeX Formatter
lingzhi227/agent-research-skills
Sets up conference-specific LaTeX paper templates, checks a draft for formatting and submission issues, and auto-fixes common problems for venues like ICML, ICLR, NeurIPS, AAAI and ACL.
Related
Works with
Categories
Questions about Research Idea Generation
What does Research Idea Generation do?
Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty. The workflow runs in four steps.md.
When should I use Research Idea Generation?
Research Idea Generation fits situations like: brainstorming new research directions for a given area or codebase; checking whether a research idea is novel against existing literature; scoring and comparing several candidate research ideas before committing to one.
How do I install Research Idea Generation in Claude Code?
Run `npx skills add lingzhi227/agent-research-skills --skill idea-generation -a claude-code`. Or copy the skill folder (skills/idea-generation in lingzhi227/agent-research-skills) into .claude/skills/idea-generation in your project. Claude Code loads it when a task matches its description.
How do I install Research Idea Generation in Codex?
Run `npx skills add lingzhi227/agent-research-skills --skill idea-generation -a codex`. Or copy the skill folder (skills/idea-generation in lingzhi227/agent-research-skills) into .agents/skills/idea-generation in your project. Codex loads it when a task matches its description.
Can I use Research Idea Generation 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 lingzhi227/agent-research-skills --skill idea-generation -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-generation, .gemini/skills/idea-generation, .github/skills/idea-generation and .opencode/skills/idea-generation in your project.
What does Research Idea Generation need to run?
Going by SKILL.md and its folder, Research Idea Generation needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python for scripts/novelty_check.py; Network access to Semantic Scholar and arXiv for the novelty check.
Does Research Idea Generation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Research Idea Generation 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Research Idea Generation use?
No licence was found for Research Idea Generation or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Research Idea Generation use?
About 747 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.9k tokens, read only when the agent opens those files.
What are the alternatives to Research Idea Generation?
Skills that share tags, products or a category with Research Idea Generation: Paper Navigator (AI4Scientist/nano-scientist, 128 stars), Math Discovery Evidence Search (tradecatlabs/vibe-coding-cn, 17k stars), Novelty Check (GRIND-Lab-Core/night_owl_research_agent, 106 stars) and Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Idea Generation?
lingzhi227 (a GitHub user) maintains it in lingzhi227/agent-research-skills, which has 390 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on February 27, 2026.
Source: lingzhi227/agent-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.