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

Run Shell Python File Io

by HKUDS in HKUDS/OpenSpace

Use runshell with inline Python for reliable file I/O when executecodesandbox cannot access working directory files

MITAuto-check passed

Install Run Shell Python File Io

skills CLI
$ npx skills add HKUDS/OpenSpace --skill run-shell-python-file-io -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace run-shell-python-file-io --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/run-shell-python-file-io .claude/skills/run-shell-python-file-io && 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
run-shell-python-file-io
GitHub stars
7.7k
Token cost
~917 tokens
SKILL.md length
298 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Use runshell with inline Python for reliable file I/O when executecodesandbox cannot access working directory files

  • Works in 4 steps: Identify File Access Needs → Write Inline Python via run_shell → Handle Complex Logic → …
  • SKILL.md covers When to Use This Skill, The Pattern, How to Apply and Best Practices, plus 3 more sections
  • Calls python3

What it does

Run Shell Python File Io is an agent skill from HKUDS/OpenSpace. Use runshell with inline Python for reliable file I/O when executecodesandbox cannot access working directory files

Its SKILL.md is about 920 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

  • “/run-shell-python-file-io”

Requirements

  • Python 3

Workflow steps

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

  1. Identify File Access Needs
  2. Write Inline Python via run_shell
  3. Handle Complex Logic
  4. Verify File Operations

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

Run Shell Python File Io loads about 917 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 298 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~917

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). 298 words, ~917 tokens.

Download SKILL.mdSave it as .claude/skills/run-shell-python-file-io/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
run-shell-python-file-io
description
Use run_shell with inline Python for reliable file I/O when execute_code_sandbox cannot access working directory files

Run Shell Python File I/O

When to Use This Skill

Use this technique when execute_code_sandbox cannot access files in your working directory, but you need to perform file operations (read, write, transform) as part of your task execution.

The Pattern

Instead of using execute_code_sandbox, run Python code directly through run_shell with explicit path handling. This provides reliable file I/O capabilities within the task workspace.

How to Apply

Step 1: Identify File Access Needs

Determine which files you need to read from or write to in the working directory.

Step 2: Write Inline Python via run_shell

Construct a Python script that handles your file operations and execute it through run_shell:

bash
python3 -c "
import os

# Get the working directory
work_dir = os.getcwd()
print(f'Working directory: {work_dir}')

# Read a file
with open('input.txt', 'r') as f:
    content = f.read()

# Process the content
processed = content.upper()

# Write to output file
with open('output.txt', 'w') as f:
    f.write(processed)

print('File operation complete')
"
Step 3: Handle Complex Logic

For more complex operations, write a temporary Python script file first:

bash
cat > /tmp/process.py << 'EOF'
import os
import json

work_dir = os.getcwd()

# Read input
with open('data.json', 'r') as f:
    data = json.load(f)

# Transform
result = {k: v * 2 for k, v in data.items()}

# Write output
with open('result.json', 'w') as f:
    json.dump(result, f, indent=2)

print(f'Processed {len(data)} items')
EOF

python3 /tmp/process.py
Step 4: Verify File Operations

After execution, verify the files were created/modified correctly:

bash
ls -la
cat output.txt

Best Practices

  1. Use Absolute or Relative Paths Explicitly: Always specify file paths clearly; os.getcwd() helps confirm your working directory.

  2. Handle Errors Gracefully: Add try/except blocks to catch file I/O errors:

    python
    try:
    with open('file.txt', 'r') as f:
        content = f.read()
except FileNotFoundError:
    print('File not found')

  3. Use Here-Docs for Complex Scripts: For scripts longer than a few lines, use bash here-documents to avoid escaping issues.

  4. Clean Up Temporary Files: If you create temporary scripts, consider removing them after execution.

  5. Check Working Directory First: Print os.getcwd() to confirm you're operating in the expected directory.

Common Use Cases

  • Reading configuration files from the workspace
  • Writing generated reports or outputs
  • Transforming data files (CSV, JSON, XML)
  • Batch processing multiple files
  • Generating structured documents (PDFs, spreadsheets)

Example: Processing Multiple Files

bash
python3 -c "
import os
import glob

work_dir = os.getcwd()
files = glob.glob('*.txt')

for f in files:
    with open(f, 'r') as file:
        content = file.read()
    # Process each file
    with open(f'processed_{f}', 'w') as out:
        out.write(content.strip().upper())

print(f'Processed {len(files)} files')
"

Troubleshooting

IssueSolution
File not foundCheck os.getcwd() output; use absolute paths if needed
Permission deniedEnsure the directory is writable; avoid protected system paths
Encoding errorsSpecify encoding explicitly: open('file.txt', 'r', encoding='utf-8')
Multi-line script issuesUse here-doc (<< 'EOF') instead of -c for complex scripts

© 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/run-shell-python-file-io of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Run Shell Python File Io 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.

Run Shell Python File Io compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Run Shell Python File Io this skillHKUDS/OpenSpace7.7k—~917Automated 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

  • Audio Track Production Workflow

    HKUDS/OpenSpace

    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

  • Cascade Failure Recovery

    HKUDS/OpenSpace

    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

  • Sandbox Code Execution Fallback

    HKUDS/OpenSpace

    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

  • Code Execution Fallback

    HKUDS/OpenSpace

    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

  • Code Execution Fallback and Path Anchoring

    HKUDS/OpenSpace

    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

  • Code Execution Fallback E81068

    HKUDS/OpenSpace

    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 Run Shell Python File Io

What does Run Shell Python File Io do?

Use runshell with inline Python for reliable file I/O when executecodesandbox cannot access working directory files. Run Shell Python File Io is an agent skill from HKUDS/OpenSpace.

How do I install Run Shell Python File Io in Claude Code?

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

How do I install Run Shell Python File Io in Codex?

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

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

What does Run Shell Python File Io need to run?

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

Does Run Shell Python File Io 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 Run Shell Python File Io 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 Run Shell Python File Io use?

Run Shell Python File Io 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 Run Shell Python File Io use?

About 917 tokens (SKILL.md is roughly 3.7k 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 Run Shell Python File Io?

Skills that share tags, products or a category with Run Shell Python File Io: 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 Run Shell Python File Io?

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.