Agent skill

Fallback Python Shell

by HKUDS in HKUDS/OpenSpace

Use runshell with Python heredoc when executecodesandbox or readfile fail

MITAuto-check passedDocuments & Office

Install Fallback Python Shell

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

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace fallback-python-shell --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/fallback-python-shell .claude/skills/fallback-python-shell && 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
fallback-python-shell
GitHub stars
7.7k
Token cost
~1k tokens
SKILL.md length
244 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Use runshell with Python heredoc when executecodesandbox or readfile fail

  • Works in 4 steps: Use python3 << 'EOF' (quoted EOF… → Indent Python code starting from column… → End with EOF on its own line with no… → …
  • Documents & Office work in your project
  • SKILL.md covers When to Use, Core Technique, Common Use Cases and Best Practices, plus 1 more section
  • Calls python3

What it does

Fallback Python Shell is an agent skill from HKUDS/OpenSpace. Use runshell with Python heredoc when executecodesandbox or readfile fail

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

It sits in Documents & Office. 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.

When your agent uses it

  • Documents & Office work in your project

Example prompts

  • “/fallback-python-shell”

Requirements

  • Python 3

Workflow steps

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

  1. Use python3 << 'EOF' (quoted EOF prevents variable expansion in the heredoc)
  2. Indent Python code starting from column 0 (no extra indentation from shell)
  3. End with EOF on its own line with no leading/trailing whitespace
  4. Print results to stdout to capture them in the tool response

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

    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

Fallback Python Shell loads about 1k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~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 HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 244 words, ~1,037 tokens.

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

Shell-Based Python Fallback

When to Use

Use this fallback pattern when:

  • execute_code_sandbox returns 'unknown error'
  • read_file returns 'unknown error' for supported formats
  • You need to process documents, analyze data, or read files programmatically

Core Technique

Run Python code through run_shell using a heredoc. This bypasses sandbox execution issues while maintaining Python's full capabilities for file I/O and data processing.

Basic Pattern
bash
python3 << 'EOF'
# Your Python code here
import json
import os

# Example: Read and process a file
with open('/path/to/file.txt', 'r') as f:
    content = f.read()
    print(content)
EOF
Key Syntax Points
  1. Use python3 << 'EOF' (quoted EOF prevents variable expansion in the heredoc)
  2. Indent Python code starting from column 0 (no extra indentation from shell)
  3. End with EOF on its own line with no leading/trailing whitespace
  4. Print results to stdout to capture them in the tool response

Common Use Cases

Reading Files (Fallback for read_file)
bash
python3 << 'EOF'
import json

# Read text file
with open('document.txt', 'r') as f:
    content = f.read()
    print(content)

# Read JSON file
with open('data.json', 'r') as f:
    data = json.load(f)
    print(json.dumps(data, indent=2))
EOF
Processing Excel/CSV Files
bash
python3 << 'EOF'
import pandas as pd

# Read Excel file
df = pd.read_excel('data.xlsx', sheet_name='Sheet1')
print(df.to_string())
print(f"Shape: {df.shape}")

# Read CSV
df = pd.read_csv('data.csv')
print(df.head(10))
EOF
Reading PDF Files
bash
python3 << 'EOF'
import fitz  # PyMuPDF

doc = fitz.open('document.pdf')
for page_num in range(len(doc)):
    page = doc[page_num]
    text = page.get_text()
    print(f"=== Page {page_num + 1} ===")
    print(text)
doc.close()
EOF
Reading Word Documents
bash
python3 << 'EOF'
from docx import Document

doc = Document('document.docx')
for para in doc.paragraphs:
    print(para.text)
EOF
Data Analysis
bash
python3 << 'EOF'
import pandas as pd
import numpy as np

df = pd.read_csv('data.csv')

# Basic statistics
print(f"Shape: {df.shape}")
print(f"Columns: {list(df.columns)}")
print(df.describe())

# Filter and aggregate
result = df.groupby('category').agg({'value': 'sum'})
print(result)
EOF

Best Practices

  1. Error Handling: Wrap file operations in try/except blocks

    bash
    python3 << 'EOF'
    try:
        with open('file.txt', 'r') as f:
            content = f.read()
            print(content)
    except FileNotFoundError:
        print("ERROR: File not found")
    except Exception as e:
        print(f"ERROR: {e}")
    EOF
  2. Large Output: For large files, process in chunks or print summaries

    bash
    python3 << 'EOF'
    with open('large_file.csv', 'r') as f:
        for i, line in enumerate(f):
            if i < 10:
                print(line.strip())
            else:
                print("... truncated ...")
                break
    EOF
  3. Working Directory: Remember run_shell executes in the current working directory. Use absolute paths or ensure you're in the right directory.

  4. Multiple Steps: Chain related operations in a single heredoc rather than multiple calls

    bash
    python3 << 'EOF'
    # Do all related work in one call
    with open('input.json') as f:
        data = json.load(f)
    
    processed = [transform(x) for x in data]
    
    with open('output.json', 'w') as f:
        json.dump(processed, f)
    
    print("Processing complete")
    EOF

Troubleshooting

  • Module not found: Some packages may not be available. Stick to standard library or commonly pre-installed packages (pandas, numpy are often available).
  • Permission errors: Ensure files aren't in protected directories.
  • Character encoding: Specify encoding explicitly: open('file.txt', 'r', encoding='utf-8')
  • Very long code: Split into multiple heredocs or write to a temporary .py file first.

© 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/fallback-python-shell of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Fallback Python Shell 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.

Fallback Python Shell compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fallback Python Shell this skillHKUDS/OpenSpace7.7k—~1kAutomated safety check: PassMIT
Word Document Reader and WriterHKUDS/DeepTutor41k—~2.5kAutomated safety check: PassApache-2.0
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0
Word DOCX ToolkitTokenRhythm/opensquilla7.1k—~1.7kAutomated safety check: PassApache-2.0
Markdown to HTML ReportMegaSuperKitty/WeClaw370—~456Automated safety check: PassMIT
Mathmodel SkillhandsomeZR-netizen/mathmodel-skill292—~2.5kAutomated safety check: PassMIT

Similar skills

  • Reads, creates and edits Word .docx files with python-docx, and drops to raw OOXML for tracked changes, comments and byte-exact edits.

    41k GitHub stars~2.5k tokensUpdated 3 days ago
    Documents & OfficeAuto-check passed
  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed
  • Word DOCX Toolkit

    TokenRhythm/opensquilla

    Inspects, edits in place or creates Word .docx files with bundled Python scripts, keeping existing styles intact when content changes.

    7.1k GitHub stars~1.7k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Markdown to HTML Report

    MegaSuperKitty/WeClaw

    Drafts a report in Markdown with numbered inline citations and a references section, then renders it to a styled HTML file through a Jinja2 template on Windows.

    370 GitHub stars~456 tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Mathmodel Skill

    handsomeZR-netizen/mathmodel-skill

    CUMCM 国赛、MCM/ICM 美赛与电工杯数学建模竞赛的端到端协作工作流。Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling…

    292 GitHub stars~2.5k tokensUpdated 11 days ago
    Documents & OfficeAuto-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
    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 Fallback Python Shell

What does Fallback Python Shell do?

Use runshell with Python heredoc when executecodesandbox or readfile fail. Fallback Python Shell is an agent skill from HKUDS/OpenSpace.

When should I use Fallback Python Shell?

Fallback Python Shell fits situations like: documents & Office work in your project.

How do I install Fallback Python Shell in Claude Code?

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

How do I install Fallback Python Shell in Codex?

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

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

What does Fallback Python Shell need to run?

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

Does Fallback Python Shell 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 Fallback Python Shell 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 Fallback Python Shell use?

Fallback Python Shell 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 Fallback Python Shell use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Fallback Python Shell?

Skills that share tags, products or a category with Fallback Python Shell: Word Document Reader and Writer (HKUDS/DeepTutor, 41k stars), Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Word DOCX Toolkit (TokenRhythm/opensquilla, 7.1k stars) and Markdown to HTML Report (MegaSuperKitty/WeClaw, 370 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fallback Python Shell?

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.