New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Research Idea Explorer

by jameslemon2002 in jameslemon2002/research-idea-explorer

A skill your agent uses when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot…

MITAuto-check passedResearch & Science

Install Research Idea Explorer

skills CLI
$ npx skills add jameslemon2002/research-idea-explorer --skill research-idea-explorer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jameslemon2002/research-idea-explorer research-idea-explorer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jameslemon2002/research-idea-explorer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research-idea-explorer .claude/skills/research-idea-explorer && rm -rf skills-src

Use ~/.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/

Facts

Skill name
research-idea-explorer
GitHub stars
136
Token cost
~1.4k tokens
SKILL.md length
688 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot…

  • Works in 6 steps: Start with a literature-guided… → Convert only the strongest brainstorm… → Reject ideas that are obvious… → …
  • The user wants cross-disciplinary research ideas generated as concise research cards with Title
  • SKILL.md covers Default policy, Preference handling, CLI mapping and Guardrails, plus 3 more sections
  • Calls python

What it does

Research Idea Explorer is an agent skill from jameslemon2002/research-idea-explorer. Use when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot prompting.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/retrieval.md` and `references/schema.md`).

It sits in Research & Science, covering Hypothesis generation. The repository describes itself as: Literature-grounded research idea exploration for CLI agents. 文献驱动的研究选题与方向探索工具。 The licence is MIT.

When your agent uses it

  • The user wants cross-disciplinary research ideas generated as concise research cards with Title
  • Distinctiveness
  • Significance rather than one-shot prompting

Example prompts

  • “/research-idea-explorer”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Start with a literature-guided single-pass divergence across multiple research moves. The built-in persona set remains an internal way to…
  2. Convert only the strongest brainstorm seeds into the shared internal schema
  3. Reject ideas that are obvious near-duplicates or amount to a thin "method + topic" pairing.
  4. If the user asks to deepen, branch, compare, or continue from an accepted direction, run a second literature-guided mutation round around…
  5. Push each retained idea one step further by adding
  6. When available, use the persistent memory graph so the session does not keep revisiting the same research neighborhoods.

What it can do on your machine

Read from SKILL.md and the folder at commit 14232d9. 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

    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 Explorer loads about 1.4k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 jameslemon2002/research-idea-explorer at commit 14232d9, republished under its MIT licence (© jameslemon2002). 688 words, ~1,413 tokens.

Download SKILL.mdSave it as .claude/skills/research-idea-explorer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
research-idea-explorer
description
Use when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot prompting.

Research Idea Explorer Skill

Use this skill when the task is to generate, refine, or compare research ideas across disciplines.

Default policy

If the machine has the packaged CLI installed, prefer calling:

  • research-idea-explorer
  • or rie

Use the repo-local fallback python -m research_idea_explorer.cli only when the packaged command is unavailable but the repository is present in the workspace.

Default to literature-first for every non-pure-functional invocation.

That means:

  • If the user asks to generate, refine, compare, extend, red-team, or continue research ideas, search literature first.
  • Treat literature retrieval as the default prelude, not an optional extra, unless the user explicitly says not to use it.
  • Keep hybrid retrieval as the default strategy unless the user explicitly prefers lexical, embedding, or graph.
  • Only skip retrieval for pure utility actions such as:
    • formatting an existing result
    • inspecting graph, summary, or neighbors
    • writing feedback
    • explaining the output schema or command usage

The workflow is:

  1. Start with a literature-guided single-pass divergence across multiple research moves. The built-in persona set remains an internal way to keep those moves orthogonal, but it should not dominate the user-facing framing.
  2. Convert only the strongest brainstorm seeds into the shared internal schema: Object, Puzzle, Claim, Contrast, Evidence, Scope, Stakes.
  3. Reject ideas that are obvious near-duplicates or amount to a thin "method + topic" pairing.
  4. If the user asks to deepen, branch, compare, or continue from an accepted direction, run a second literature-guided mutation round around the retained frontier families.
  5. Push each retained idea one step further by adding: data source, minimal runnable design, likely failure mode, and why the question matters now.
  6. When available, use the persistent memory graph so the session does not keep revisiting the same research neighborhoods.

Preference handling

When the user expresses stable preferences in conversation, carry them into the CLI call instead of treating them as disposable chat context.

Typical examples:

  • preferred direction: prefer causal identification, focus on policy relevance
  • constraints: avoid survey, don't do LLM, less benchmark work

Default behavior:

  • Pass those signals through --preference-note.
  • Use --remember-preferences topic when the preference is specific to the current topic.
  • Use --remember-preferences global only when the user clearly wants the same preference to apply across topics.
  • Reuse the same memory path so stored preferences can affect the next ideas run.
Show full SKILL.md (311 more words)Show less

CLI mapping

When you want the packaged command to do the work instead of manually re-creating the flow:

  • generate ideas: research-idea-explorer ideas --query "..."
  • inspect memory: research-idea-explorer graph --memory ./data/memory/cli-memory.json
  • list ideas for feedback: research-idea-explorer feedback --memory ./data/memory/cli-memory.json
  • accept or reject an idea: research-idea-explorer feedback --memory ./data/memory/cli-memory.json --idea-id <idea-id> --decision accepted
  • generate ideas while storing the user's conversation preferences: research-idea-explorer ideas --query "..." --preference-note "prefer causal identification, avoid survey" --remember-preferences topic
  • store preferences during feedback on a retained idea: research-idea-explorer feedback --memory ./data/memory/cli-memory.json --idea-id <idea-id> --decision accepted --note "prefer causal identification, avoid survey" --remember-preferences topic
  • inspect stored preference profiles: research-idea-explorer graph --memory ./data/memory/cli-memory.json --view preferences

If only the repo-local version is available, the same commands can be run with python -m research_idea_explorer.cli.

Guardrails

  • Do not output only titles. Output brainstorm seeds first when useful, then concise research cards.
  • Do not overuse Blind spot if a stronger puzzle such as Conflict, Distortion, or Mechanism unknown is available.
  • Treat Scale and Counterfactual as part of contrast and scope unless the user explicitly wants them foregrounded.
  • Search literature by default before proposing ideas, and use metadata to identify crowded areas before proposing ideas.
  • Prefer diversity of research moves over superficial variation in wording.

Diagram provenance

If you produce a diagram, distinguish clearly between:

  • a computed graph generated from stored nodes and edges
  • a literature-derived map synthesized from retrieved papers
  • a conceptual sketch synthesized by the agent

Do not present a hand-authored conceptual diagram as an automatically generated network graph.

Output shape

Each default research card should contain:

  • Title
  • Abstract
  • Design
  • Distinctiveness
  • Significance

The richer internal schema can still be used when deeper analysis is needed, but the default user-facing card should stay concise.

References

Read references/schema.md when you need the field meanings, internal move set, or puzzle definitions. Read references/retrieval.md when literature retrieval is available and you need to decide between lexical, embedding, or graph expansion.

© jameslemon2002, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in skills/research-idea-explorer of jameslemon2002/research-idea-explorer.

  • SKILL.md
  • agents/openai.yaml
  • references/retrieval.md
  • references/schema.md

Open the folder on GitHubat commit 14232d9

Compare with similar skills

Research Idea Explorer 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.

Research Idea Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Idea Explorer this skilljameslemon2002/research-idea-explorer136—~1.4kAutomated safety check: PassMIT
Hypothesis Generationspacering-net/codeg3.8k15 repos~3.6kAutomated safety check: NotesMIT
Nature Paper CardYuan1z0825/nature-skills46k2 repos~2.1kAutomated safety check: PassApache-2.0
Hypothesis GenerationK-Dense-AI/claude-scientific-writer2.4k2 repos~3.9kAutomated safety check: PassMIT
Good QuestionRimagination/good-question3051 repos~4.3kAutomated safety check: PassMIT
Claim-Driven Experiment PlannerzjYao36/Auto-Research-Refine1287 repos~2.3kAutomated safety check: NotesNone

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.8k GitHub starsUsed in 15 repos~3.6k tokens
    Research & ScienceAuto-check: notes

  • 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.

    46k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed

  • 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…

    2.4k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check passed

  • 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…

    305 GitHub starsUsed in 1 repo~4.3k tokens
    Research & ScienceAuto-check passed

  • 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.

    128 GitHub starsUsed in 7 repos~2.3k tokens
    Research & ScienceAuto-check: notes

  • 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.

    989 GitHub stars~2.2k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed

Categories

Questions about Research Idea Explorer

What does Research Idea Explorer do?

A skill your agent uses when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot…. Research Idea Explorer is an agent skill from jameslemon2002/research-idea-explorer. Use when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot prompting.

When should I use Research Idea Explorer?

Research Idea Explorer fits situations like: the user wants cross-disciplinary research ideas generated as concise research cards with Title; distinctiveness; significance rather than one-shot prompting.

How do I install Research Idea Explorer in Claude Code?

Run `npx skills add jameslemon2002/research-idea-explorer --skill research-idea-explorer -a claude-code`. Or copy the skill folder (skills/research-idea-explorer in jameslemon2002/research-idea-explorer) into .claude/skills/research-idea-explorer in your project. Claude Code loads it when a task matches its description.

How do I install Research Idea Explorer in Codex?

Run `npx skills add jameslemon2002/research-idea-explorer --skill research-idea-explorer -a codex`. Or copy the skill folder (skills/research-idea-explorer in jameslemon2002/research-idea-explorer) into .agents/skills/research-idea-explorer in your project. Codex loads it when a task matches its description.

Can I use Research Idea Explorer 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 jameslemon2002/research-idea-explorer --skill research-idea-explorer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-idea-explorer, .gemini/skills/research-idea-explorer, .github/skills/research-idea-explorer and .opencode/skills/research-idea-explorer in your project.

What does Research Idea Explorer need to run?

Going by SKILL.md and its folder, Research Idea Explorer needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Research Idea Explorer 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 Explorer 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 Research Idea Explorer use?

Research Idea Explorer 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 Research Idea Explorer use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Research Idea Explorer?

Skills that share tags, products or a category with Research Idea Explorer: 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 Research Idea Explorer?

jameslemon2002 (a GitHub user) maintains it in jameslemon2002/research-idea-explorer, which has 136 GitHub stars. The repository was last updated on April 2, 2026.

Source: jameslemon2002/research-idea-explorer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.