⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

code-runner

@noesskeetit⭐ 0 stars

Use this skill when you need to execute Python or JavaScript code. Supports data analysis (pandas, numpy, scipy), visualization (matplotlib, seaborn), web prototyping (React, Tailwind), and general scripting. Output includes stdout, stderr, and any generated files (images, data files). Isolation (network, filesystem) is the responsibility of the runtime environment.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

OpenClaw Skills

A set of agent-agnostic skills for coding agents (OpenClaw, Claude Code, Cursor, Cline, Aider, etc.). Each skill is a self-contained folder with a SKILL.md (YAML frontmatter + instructions) and a scripts/ directory of executables the agent can call.

No Docker images, no gateway service, no external runtime — just markdown + scripts. The host environment is responsible for installing dependencies and providing isolation.

Skills

SkillPurposeHeavy deps
code-runnerExecute Python or JavaScript with stdout/stderr/file capturepandas, numpy, matplotlib (~420 MB venv)
diagram-generatorMermaid + Graphviz → SVG/PNG/PDFgraphviz binary, mermaid-cli (~470 MB Chromium cache)
document-analyzerRead/extract/OCR PDF, DOCX, XLSX, PPTX, CSV; PDF form fillingtesseract, poppler, ghostscript
document-creatorCreate and validate DOCX, XLSX, PPTX, PDF; OOXML schema validationpython-docx, openpyxl, pptx, reportlab, OOXML XSD schemas (bundled)
git-assistantCommits, code review, PR descriptionsstdlib only
web-browserBrowser automation: navigate, screenshot, fill forms via Playwrightplaywright + Chromium (~525 MB)
web-search-searxngMeta-search via self-hosted SearXNG (auto-bootstraps its container)docker daemon access
web-search-tavilyAI-optimized search via Tavily APIstdlib only, requires TAVILY_API_KEY

Skill format

skill-name/
├── SKILL.md           # YAML frontmatter + instructions for the agent
├── requirements.txt   # Python deps (when applicable)
└── scripts/           # executables the agent invokes

SKILL.md starts with a YAML block:

---
name: skill-name
description: "When to use this skill, what it does, what it does NOT do."
license: MIT
---

The description is what the agent reads to decide when to invoke the skill. The body explains how to use the scripts.

Install a single skill

cd skill-name
pip install -r requirements.txt   # if present
# install any system deps listed in SKILL.md (tesseract, graphviz, ...)

For skills that ship their own service (currently only web-search-searxng), the script auto-starts the container on first call — no manual setup needed beyond a working docker daemon.

Resource footprint

Designed to coexist on a small VM (≥2 GB RAM, ~10 GB disk). Heaviest skills:

  • web-browser — peak ~375 MB RAM per Chromium session
  • diagram-generator — peak ~500 MB-1 GB during Mermaid render
  • document-analyzer — up to ~1 GB on large PDFs with OCR
  • web-search-searxng — ~200-300 MB resident as background container

Run heavy skills serially on constrained hardware.

Adding a new skill

  1. Create your-skill/ with SKILL.md and scripts/
  2. Use the YAML frontmatter format above
  3. Make description tell the agent when and when NOT to use the skill
  4. Document each script's CLI in SKILL.md
  5. Pin major versions in requirements.txt if Python deps are involved

License

MIT — see LICENSE.

// HOW IT'S BUILT

KEY FILES

code-runner/SKILL.mdREADME.md

// REPO STATS

0 stars