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 Explorer

by ai4s-research in ai4s-research/ai4s-skills

A skill your agent uses when the user has a vague research direction and wants to explore feasible specific topics.

MITAuto-check passedResearch & Science

Install Research Explorer

skills CLI
$ npx skills add ai4s-research/ai4s-skills --skill research-explorer -a claude-code

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

GitHub CLI
$ gh skill install ai4s-research/ai4s-skills research-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/ai4s-research/ai4s-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research-explorer .claude/skills/research-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-explorer
GitHub stars
237
Used in
2 other repos
Token cost
~1.3k tokens
SKILL.md length
553 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user has a vague research direction and wants to explore feasible specific topics.

  • Works in 5 steps: Understand the direction → Set up the run directory → Multi-dimensional exploration → …
  • The user has a vague research direction and wants to explore feasible specific topics
  • SKILL.md covers Overview, When to Use, When NOT to Use and Workflow, plus 2 more sections
  • Calls python3

What it does

Research Explorer is an agent skill from ai4s-research/ai4s-skills. Use when the user has a vague research direction and wants to explore feasible specific topics. Outputs a structured analysis with candidate topics, innovation/feasibility scoring, and a pre-survey of 20–30 representative works. Single-stage, no Python runtime.

Its SKILL.md is about 1.3k 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. It works with Python. The repository describes itself as: Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent. The licence is MIT.

When your agent uses it

  • The user has a vague research direction and wants to explore feasible specific topics

Example prompts

  • “/research-explorer”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Understand the direction
  2. Set up the run directory
  3. Multi-dimensional exploration
  4. Produce the three deliverables
  5. Optional handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 744ab20. 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:

    • python3

    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 Explorer loads about 1.3k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 553 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 ai4s-research/ai4s-skills at commit 744ab20, republished under its MIT licence (© ai4s-research). 553 words, ~1,284 tokens.

Download SKILL.mdSave it as .claude/skills/research-explorer/SKILL.md (or your agent's skills folder).
name
research-explorer
description
Use when the user has a vague research direction and wants to explore feasible specific topics. Outputs a structured analysis with candidate topics, innovation/feasibility scoring, and a pre-survey of 20–30 representative works. Single-stage, no Python runtime.

Research Explorer

Overview

Research-topic exploration SKILL. Takes a broad direction, performs multi-dimensional web research with the agent's own WebSearch / WebFetch tools, and produces three structured Markdown deliverables. Single stage, full quality from the start. No Python runtime, no LLM SDK.

When to Use

  • User says "I want to research X" without a specific topic.
  • User wants to know "what are the hot topics in X".
  • User needs help narrowing a broad field into 5–10 candidate topics.
  • User asks for "research landscape overview".

When NOT to Use

  • User already has a specific research question → use literature-survey or paper-writer.
  • User wants a quick fact-check → use WebSearch directly.

Workflow

Step 1 — Understand the direction

Confirm with the user:

  • Direction — the broad area of interest (e.g., "federated learning", "NLP for healthcare").
  • Constraints — theory vs. applied, specific methods, target venue, compute budget, time horizon.
  • Language — default English in conversation; reports in English unless the user requests otherwise.
Step 2 — Set up the run directory
bash
DIRECTION="<direction>"
SLUG=$(python3 -c "import re,hashlib,sys; t=sys.argv[1]; n=re.sub(r'[\\s_]+','-',re.sub(r'[^\\w\\s-]','',t.lower().strip())).strip('-')[:40].rstrip('-'); h=hashlib.sha1(t.encode()).hexdigest()[:8]; print(f'{n}-{h}')" "$DIRECTION")
TS=$(date +%Y-%m-%d_%H%M%S)
RUN=output/research-explorer/$SLUG/$TS

mkdir -p "$RUN"
ln -sfn "$TS" "output/research-explorer/$SLUG/latest"

In commands below $RUN = output/research-explorer/<slug>/latest.

Step 3 — Multi-dimensional exploration

Run WebSearch across the following dimensions (one query per dimension, more if returns are thin):

  1. Hot topics — "<direction> 2024 2025 hot topics" / "recent advances".
  2. Open problems — "<direction> open problems" / "challenges".
  3. Surveys — "<direction> survey 2024" / "<direction> review".
  4. Benchmarks — "<direction> benchmark" / "<direction> evaluation dataset".
  5. Applications — "<direction> applications" / "<direction> industry use cases".
  6. Cross-field — "<direction> + <adjacent field>" (pick 1–2 adjacent fields).
  7. Recent breakthroughs — papers from the last 6–12 months at top venues.

For each kept candidate, WebFetch the abstract URL to extract canonical title / authors / year / venue. Persist intermediate notes to $RUN/search_notes.md after every dimension so the work resumes cleanly.

Step 4 — Produce the three deliverables

Write these in $RUN/:

4.1 research_exploration.md

Structured analysis containing:

  • Direction recap & constraints.
  • Landscape map — main subfields and the relationships between them.
  • 5–10 candidate topics, each with:
    • Title (specific enough to be a paper title).
    • Motivation (why this matters now).
    • Innovation angle (what would be new).
    • Feasibility score (low / medium / high) with a brief justification (data availability, compute requirements, prior work density).
    • Risk / open question.
  • Recommendation — which 1–3 the user should pursue and why.
Show full SKILL.md (203 more words)Show less
4.2 topic_matrix.md

A hierarchical Markdown outline of the topic space:

# <Direction>
## Subfield A
### Topic A.1
### Topic A.2
## Subfield B
### Topic B.1

This file is consumable by the mindmap-render skill to produce a visual mindmap.

4.3 literature_pre_survey.md

A pre-survey table of 20–30 representative works discovered above, with columns: title, authors, year, venue, URL, one-sentence relevance note. Every entry must have a URL the agent fetched in this session.

Step 5 — Optional handoff

If the user picks a topic, suggest the next skill:

  • For a paper: the paper-writer skill (using the chosen topic).
  • For a survey: the literature-survey skill.
  • For an experiment package: the experiment-suite skill.
  • For a visual topic map: the mindmap-render skill consuming topic_matrix.md.

Cross-skill data flow (path convention)

A downstream skill can locate this exploration via the slug:

  • output/research-explorer/<slug>/latest/topic_matrix.md
  • output/research-explorer/<slug>/latest/literature_pre_survey.md

If the user picks one topic from the matrix, downstream skills compute their own slug from the topic (not the original direction), so the slug paths diverge from this skill onward — which is correct.

Important rules

  • No LLM SDK in this skill. Just a procedure + this SKILL.md.
  • Candidates are suggestions, not guaranteed novel — the user must verify originality before committing.
  • Feasibility scores are heuristic — flag uncertainty explicitly when relevant.
  • Every literature entry must have a URL fetched in this session; no memory-only entries.

© ai4s-research, 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/research-explorer of ai4s-research/ai4s-skills.

Open the folder on GitHubat commit 744ab20

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in ai4s-research/ai4s-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Research 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 Explorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Explorer this skillai4s-research/ai4s-skills2372 repos~1.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Last30daysmvanhorn/last30days-skill64k—~7.9kAutomated safety check: NotesMIT
NetworkxzLanqing/codex-claude-academic-skills4.7k15 repos~3.2kAutomated safety check: PassBSD-3-Clause
Nature-Style Scientific FiguresYuan1z0825/nature-skills47k—~2.9kAutomated safety check: PassApache-2.0
Citation ManagementK-Dense-AI/claude-scientific-writer2.4k2 repos~3.9kAutomated safety check: NotesMIT

Similar skills

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated today
    Research & ScienceAuto-check: notes

  • Networkx

    zLanqing/codex-claude-academic-skills

    Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python.

    4.7k GitHub starsUsed in 15 repos~3.2k tokens
    Research & ScienceAuto-check passed

  • Nature-Style Scientific Figures

    Yuan1z0825/nature-skills

    Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.

    47k GitHub stars~2.9k tokensUpdated today
    Research & ScienceAuto-check passed

  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

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

  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    739 GitHub starsUsed in 12 repos~3.7k tokens
    Research & ScienceAuto-check passed

More from ai4s-research/ai4s-skills

  • Experiment Suite

    ai4s-research/ai4s-skills

    A skill your agent uses when the user has a research question and needs a complete experiment package — design document, runnable code, results (measured or simulated with honest provenance)…

    237 GitHub starsUsed in 2 repos~2.5k tokens
    Auto-check passed

  • Literature Survey

    ai4s-research/ai4s-skills

    A skill your agent uses when the user wants a comprehensive literature survey on a specific research topic.

    237 GitHub starsUsed in 2 repos~2k tokens
    Auto-check passed

  • Integrity Auditor

    ai4s-research/ai4s-skills

    A skill your agent uses when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report.

    237 GitHub starsUsed in 1 repo~5k tokens
    Auto-check passed

  • Paper Writer

    ai4s-research/ai4s-skills

    A skill your agent uses when the user wants a complete, publication-grade research paper on a specific topic — produces 200+ real citations, 4–8 publication-grade figures, and 7 sections of…

    237 GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

  • Ai4s Agent

    ai4s-research/ai4s-skills

    A skill your agent uses when the user wants an end-to-end AI4S research pipeline — broad direction or specific topic in, full research package out (exploration + literature survey + experiment +…

    237 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

  • Mindmap Render

    ai4s-research/ai4s-skills

    Generate beautiful, high-resolution mindmaps from Markdown unordered lists.

    237 GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed

Works with

Categories

Questions about Research Explorer

What does Research Explorer do?

A skill your agent uses when the user has a vague research direction and wants to explore feasible specific topics. Research Explorer is an agent skill from ai4s-research/ai4s-skills. Use when the user has a vague research direction and wants to explore feasible specific topics.

When should I use Research Explorer?

Research Explorer fits situations like: the user has a vague research direction and wants to explore feasible specific topics.

How do I install Research Explorer in Claude Code?

Run `npx skills add ai4s-research/ai4s-skills --skill research-explorer -a claude-code`. Or copy the skill folder (skills/research-explorer in ai4s-research/ai4s-skills) into .claude/skills/research-explorer in your project. Claude Code loads it when a task matches its description.

How do I install Research Explorer in Codex?

Run `npx skills add ai4s-research/ai4s-skills --skill research-explorer -a codex`. Or copy the skill folder (skills/research-explorer in ai4s-research/ai4s-skills) into .agents/skills/research-explorer in your project. Codex loads it when a task matches its description.

Can I use Research 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 ai4s-research/ai4s-skills --skill research-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-explorer, .gemini/skills/research-explorer, .github/skills/research-explorer and .opencode/skills/research-explorer in your project.

What does Research Explorer need to run?

Going by SKILL.md and its folder, Research Explorer needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Research 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 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 Explorer use?

Research 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 Explorer use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Research Explorer?

Skills that share tags, products or a category with Research Explorer: GitHub Deep Research (bytedance/deer-flow, 84k stars), Last30days (mvanhorn/last30days-skill, 64k stars), Networkx (zLanqing/codex-claude-academic-skills, 4.7k stars) and Nature-Style Scientific Figures (Yuan1z0825/nature-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Explorer?

ai4s-research (a GitHub organization) maintains it in ai4s-research/ai4s-skills, which has 237 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 28, 2026.

Source: ai4s-research/ai4s-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.