Agent skill

Shell Python Heredoc

by HKUDS in HKUDS/OpenSpace

Execute complex Python code via runshell heredoc when executecodesandbox fails

MITAuto-check passed

Install Shell Python Heredoc

skills CLI
$ npx skills add HKUDS/OpenSpace --skill shell-python-heredoc -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace shell-python-heredoc --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/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/shell-python-heredoc .claude/skills/shell-python-heredoc && 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
shell-python-heredoc
GitHub stars
7.7k
Token cost
~731 tokens
SKILL.md length
262 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Execute complex Python code via runshell heredoc when executecodesandbox fails

  • Works in 4 steps: Use << 'EOF' (with single quotes) to… → Indent Python code relative to the… → End with EOF on its own line (no leading… → …
  • SKILL.md covers Overview, When to Use, How to Use and Advantages Over…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Shell Python Heredoc is an agent skill from HKUDS/OpenSpace. Execute complex Python code via runshell heredoc when executecodesandbox fails

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It works with Python. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

  • “/shell-python-heredoc”

Requirements

  • Python 3

Workflow steps

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

  1. Use << 'EOF' (with single quotes) to prevent shell variable expansion
  2. Indent Python code relative to the heredoc delimiter
  3. End with EOF on its own line (no leading whitespace)
  4. Capture output from stdout/stderr for debugging

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are 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

Shell Python Heredoc loads about 731 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~731

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 HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 262 words, ~731 tokens.

Download SKILL.mdSave it as .claude/skills/shell-python-heredoc/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
shell-python-heredoc
description
Execute complex Python code via run_shell heredoc when execute_code_sandbox fails

Shell Python Heredoc (Fallback Pattern)

Overview

When execute_code_sandbox fails repeatedly (e.g., with "unknown error"), use run_shell with a Python heredoc as a reliable fallback for executing multi-line Python scripts with imports.

When to Use

  • execute_code_sandbox has failed 2+ times with unexplained errors
  • You need to run Python code with multiple imports (e.g., ReportLab, pandas)
  • The script is too complex for a one-liner but doesn't require persistence between calls
  • You need better error visibility from raw stdout/stderr

How to Use

Basic Pattern
python
run_shell(
    command="""python3 << 'EOF'
import sys
# Your Python code here
print("Hello from heredoc")
EOF""",
    timeout=300
)
Key Syntax Rules
  1. Use << 'EOF' (with single quotes) to prevent shell variable expansion
  2. Indent Python code relative to the heredoc delimiter
  3. End with EOF on its own line (no leading whitespace)
  4. Capture output from stdout/stderr for debugging
Example: Generating a PDF with ReportLab
python
run_shell(
    command="""python3 << 'EOF'
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello PDF")
c.save()
print("PDF created successfully")
EOF""",
    timeout=300
)
Example: Multi-file Data Processing
python
run_shell(
    command="""python3 << 'EOF'
import pandas as pd
import json

# Load and process data
df = pd.read_csv("data.csv")
summary = df.describe()

# Output results
print(summary.to_string())
with open("summary.json", "w") as f:
    json.dump(summary.to_dict(), f)
print("Processing complete")
EOF""",
    timeout=300
)

Advantages Over execute_code_sandbox

  • More reliable for complex imports (no sandbox isolation issues)
  • Full stdout/stderr access for debugging
  • Longer timeout flexibility (60s default vs 30s)
  • Direct filesystem access without ARTIFACT_PATH indirection

Disadvantages

  • No persistent state between calls (each heredoc is a fresh process)
  • Verbose for simple one-liners
  • Shell escaping may be needed for complex string literals

Troubleshooting

IssueSolution
EOF not recognizedEnsure EOF is on its own line with no leading spaces
Import errorsVerify packages are installed in the shell environment
File not foundUse absolute paths or check working directory with pwd
Syntax errorsCheck Python indentation within heredoc

See Also

  • Use execute_code_sandbox for simpler scripts when available
  • Use shell_agent for tasks requiring autonomous iteration and error recovery
  • Consider writing scripts to .py files for complex, reusable code

© HKUDS, 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 1 other file in benchmarks/gdpval/skills/shell-python-heredoc of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Shell Python Heredoc 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.

Shell Python Heredoc compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shell Python Heredoc this skillHKUDS/OpenSpace7.7k—~731Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k13 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 48 repos~2k tokens
    Documents & OfficeAuto-check passed
  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 13 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo
  • Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.7k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.7k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.7k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.7k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Shell Python Heredoc

What does Shell Python Heredoc do?

Execute complex Python code via runshell heredoc when executecodesandbox fails. Shell Python Heredoc is an agent skill from HKUDS/OpenSpace.

How do I install Shell Python Heredoc in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill shell-python-heredoc -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/shell-python-heredoc in HKUDS/OpenSpace) into .claude/skills/shell-python-heredoc in your project. Claude Code loads it when a task matches its description.

How do I install Shell Python Heredoc in Codex?

Run `npx skills add HKUDS/OpenSpace --skill shell-python-heredoc -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/shell-python-heredoc in HKUDS/OpenSpace) into .agents/skills/shell-python-heredoc in your project. Codex loads it when a task matches its description.

Can I use Shell Python Heredoc 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 HKUDS/OpenSpace --skill shell-python-heredoc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shell-python-heredoc, .gemini/skills/shell-python-heredoc, .github/skills/shell-python-heredoc and .opencode/skills/shell-python-heredoc in your project.

What does Shell Python Heredoc need to run?

SKILL.md names no scripts, command-line tools or credentials: Shell Python Heredoc is instructions for the agent only. Our summary lists: Python 3.

Does Shell Python Heredoc 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 Shell Python Heredoc 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 Shell Python Heredoc use?

Shell Python Heredoc 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 Shell Python Heredoc use?

About 731 tokens (SKILL.md is roughly 2.9k 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 Shell Python Heredoc?

Skills that share tags, products or a category with Shell Python Heredoc: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shell Python Heredoc?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

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