New: 97,000+ 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

Repl

by nteract in nteract/nteract

Use nteract notebooks as a persistent Python REPL. An agent skill from nteract/nteract.

BSD-3-ClauseAuto-check passedData & Analytics

Install Repl

skills CLI
$ npx skills add nteract/nteract --skill repl -a claude-code

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

GitHub CLI
$ gh skill install nteract/nteract repl --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/nteract/nteract.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nightly/skills/repl .claude/skills/repl && 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
repl
GitHub stars
178
Token cost
~1.1k tokens
SKILL.md length
462 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Use nteract notebooks as a persistent Python REPL. An agent skill from nteract/nteract.

  • Works in 6 steps: Start or reuse a notebook-backed REPL → Declare dependencies before import-heavy… → Run and iterate → …
  • This skill whenever youre about to run python3 -c
  • SKILL.md covers If the notebook tools aren't…, Quick Start (direct pi tools), Quick Start (MCP tools) and Core Workflow, plus 2 more sections
  • Calls python3 and codex

What it does

Repl is an agent skill from nteract/nteract. Use nteract notebooks as a persistent Python REPL. Trigger this skill whenever you're about to run python3 -c, write a throwaway .py script, or chain multiple shell commands for data exploration, analysis, plotting, or iterative computation. Notebooks preserve state between cells, show rich output, and can be used in realtime with users.

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 Data & Analytics, covering Data analysis and Data visualization. It works with Python. The repository describes itself as: We're back! Now firing notebooks out of a t-shirt gun. The licence is BSD-3-Clause.

When your agent uses it

  • This skill whenever youre about to run python3 -c
  • Write a throwaway .py script
  • Chain multiple shell commands for data exploration
  • Iterative computation

Example prompts

  • “/repl”

Requirements

  • Python 3

Workflow steps

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

  1. Start or reuse a notebook-backed REPL
  2. Declare dependencies before import-heavy code
  3. Run and iterate
  4. Check your work
  5. Save when done
  6. Open the app for the user

What it can do on your machine

Read from SKILL.md and the folder at commit 217d6fe. 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
    • codex

    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

Repl loads about 1.1k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 nteract/nteract at commit 217d6fe, republished under its BSD-3-Clause licence (© nteract). 462 words, ~1,070 tokens.

Download SKILL.mdSave it as .claude/skills/repl/SKILL.md (or your agent's skills folder).
name
repl
description
Use nteract notebooks as a persistent Python REPL. Trigger this skill whenever you're about to run python3 -c, write a throwaway .py script, or chain multiple shell commands for data exploration, analysis, plotting, or iterative computation. Notebooks preserve state between cells, show rich output, and can be used in realtime with users.

Use a Notebook Instead of python3 -c

When nteract notebook tools are available and you're about to do multi-step Python work — chaining python3 -c commands, writing a throwaway .py script, or running exploratory code — use a notebook-backed REPL instead. You get persistent state between cells, rich output (tables, plots, errors with tracebacks), and users and agents can view the notebook in realtime.

Prefer the direct pi tools when present:

  • python — execute code in the persistent notebook session.
  • python_add_dependencies — batch-add packages and hot-sync the environment.
  • python_save_notebook — save the backing notebook.

If only MCP tools are available, use create_notebook, create_cell, execute_cell, set_cell, and get_all_cells.

If the notebook tools aren't appearing

If you loaded this skill but neither the direct pi tools (python, python_add_dependencies) nor the MCP notebook tools are available, don't fall back to python3 -c. Ask the user to verify that the nteract plugin is installed and enabled in Codex, then restart Codex after any plugin or marketplace changes. The most common cause is that the plugin was installed or updated after the current Codex session started.

If Codex reports the plugin is installed but the tools still do not appear, ask the user to refresh and reinstall the selected plugin to clear stale local cache state:

sh
codex plugin marketplace upgrade nteract-plugins
codex plugin remove nteract@nteract-plugins      # or nightly@nteract-plugins
codex plugin add nteract@nteract-plugins         # or nightly@nteract-plugins
codex mcp list

Start a new Codex session after reinstalling; running sessions do not hot-load newly installed MCP tools.

If tools still don't appear after restarting Codex:

  • Confirm the nteract desktop app/daemon is running.
  • Run nteract doctor to check the installation (nteract --channel nightly doctor for the Nightly install).
  • Share any error messages from the session.

Quick Start (direct pi tools)

json
python({
  "code": "import numpy as np\nnp.arange(3)",
  "dependencies": ["numpy"]
})

Pass dependencies on the first python call when imports may be missing. The pi REPL records them before kernel startup when possible; later dependency additions use hot-sync.

Show full SKILL.md (171 more words)Show less

Quick Start (MCP tools)

create_notebook(dependencies=["numpy"])
create_cell(source="import numpy as np\nnp.arange(3)", cell_type="code", and_run=true)

Core Workflow

  1. Start or reuse a notebook-backed REPL:

    • Direct: call python(...); the session is created lazily and state persists.
    • MCP: call create_notebook(...) or connect_notebook(...).

  2. Declare dependencies before import-heavy code:

    • Direct: pass dependencies to python or call python_add_dependencies.
    • MCP: pass dependencies to create_notebook or use manage_dependencies.

  3. Run and iterate:

    • Direct: call python repeatedly; variables/imports persist.
    • MCP: edit with set_cell(...) and rerun with execute_cell(...).

  4. Check your work:

    • Direct: inspect returned text/images/tables.
    • MCP: get_all_cells(format="summary", include_outputs=true).

  5. Save when done: python_save_notebook(...) or save_notebook(...).

  6. Open the app for the user: show_notebook() when they ask to see it. This can be disruptive if unexpected.

When to Use This

  • Exploring a dataset (load, filter, plot, iterate)
  • Running multi-step computations where later steps depend on earlier results
  • Generating visualizations (matplotlib, plotly, altair)
  • Prototyping code that you'll refine over several iterations
  • Any task where you'd otherwise chain 3+ python3 -c commands

When NOT to Use This

  • One-shot commands (python3 -c "print(2+2)" is fine as-is)
  • Running existing scripts (python3 script.py)
  • Non-Python tasks

© nteract, BSD-3-Clause. 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 plugins/nightly/skills/repl of nteract/nteract.

Open the folder on GitHubat commit 217d6fe

Compare with similar skills

Repl 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.

Repl compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repl this skillnteract/nteract178—~1.1kAutomated safety check: PassBSD-3-Clause
Python Executorcortega26/chile-hub1132 repos~1.5kAutomated safety check: PassMIT
Raccoon DataanalysisSenseTime-Copilot/raccoon-dataanalysis-skill137—~1.9kAutomated safety check: PassNone
Save Research Notebooknapjon/krisk118—~702Automated safety check: PassBSD-3-Clause
Math Modeling Data Cleaning and Chartsyushui2022/MathModel-Skill4521 repos~1.7kAutomated safety check: PassMIT
Hybrid-Engine Data Analysiscode-yeongyu/oh-my-openagent70k—~1.4kAutomated safety check: PassCustom licence

Similar skills

  • Python Executor

    cortega26/chile-hub

    Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).

    113 GitHub starsUsed in 2 repos~1.5k tokens
    Data & AnalyticsAuto-check passed

  • Raccoon Dataanalysis

    SenseTime-Copilot/raccoon-dataanalysis-skill

    Raccoon (小浣熊) Data Analysis - Remote code interpreter and data visualization service powered by SenseTime.

    137 GitHub stars~1.9k tokensUpdated 6 mo ago
    Data & AnalyticsAuto-check passed

  • Save Research Notebook

    napjon/krisk

    Convert a completed data-analysis conversation into evidence-backed, reproducible living research through the Krisk MCP server.

    118 GitHub stars~702 tokensUpdated 6 days ago
    Data & AnalyticsAuto-check passed

  • Math Modeling Data Cleaning and Charts

    yushui2022/MathModel-Skill

    Cleans raw or scraped competition data and produces exploratory charts and a figure plan as one stage of a mathematical modeling paper workflow.

    452 GitHub starsUsed in 1 repo~1.7k tokens
    Data & AnalyticsAuto-check passed

  • Hybrid-Engine Data Analysis

    code-yeongyu/oh-my-openagent

    Analyzes CSV, Parquet and JSON data with DuckDB, Polars, numpy and matplotlib, preferring a persistent kernel over repeated one-shot processes.

    70k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Vega-Lite Interactive Charts

    oaustegard/claude-skills

    Builds interactive Vega-Lite charts from uploaded data: analyzes the fields, picks five to ten fitting chart types, and produces a React artifact with the data embedded inline.

    150 GitHub stars~2.1k tokensUpdated 6 days ago
    Data & AnalyticsAuto-check passed

More from nteract/nteract

All 10 skills in this repo

  • Automerge Sync

    nteract/nteract

    Automerge sync protocol internals, document model (OpSet, ChangeGraph, fork/merge, save/load lifecycle), and higher-level protocol design patterns.

    178 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed

  • Daemon Dev

    nteract/nteract

    Develop, debug, and manage the runtimed daemon, Python bindings, and build system.

    178 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Execution Pipeline

    nteract/nteract

    The end-to-end cell execution pipeline from MCP tool call through daemon to kernel and back.

    178 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

  • Nteract Diagnostics

    nteract/nteract

    Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token.

    178 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Testing

    nteract/nteract

    Run tests, verify changes, and collect diagnostics. An agent skill from nteract/nteract.

    178 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Architecture

    nteract/nteract

    Architecture and documentation framing for cross-cutting repo decisions, docs taxonomy placement, ADRs, memos, PRDs, implementation plans, audits, measurements, runbooks, and source-grounded…

    178 GitHub stars~497 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Repl

What does Repl do?

Use nteract notebooks as a persistent Python REPL. An agent skill from nteract/nteract. Repl is an agent skill from nteract/nteract. Use nteract notebooks as a persistent Python REPL.

When should I use Repl?

Repl fits situations like: this skill whenever youre about to run python3 -c; write a throwaway .py script; chain multiple shell commands for data exploration; iterative computation.

How do I install Repl in Claude Code?

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

How do I install Repl in Codex?

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

Can I use Repl 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 nteract/nteract --skill repl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repl, .gemini/skills/repl, .github/skills/repl and .opencode/skills/repl in your project.

What does Repl need to run?

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

Does Repl 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 Repl 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 Repl use?

Repl is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Repl use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Repl?

Skills that share tags, products or a category with Repl: Python Executor (cortega26/chile-hub, 113 stars), Raccoon Dataanalysis (SenseTime-Copilot/raccoon-dataanalysis-skill, 137 stars), Save Research Notebook (napjon/krisk, 118 stars) and Math Modeling Data Cleaning and Charts (yushui2022/MathModel-Skill, 452 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repl?

nteract (a GitHub organization) maintains it in nteract/nteract, which has 178 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

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