Agent skill

Robust File Creation

by HKUDS in HKUDS/OpenSpace

Fallback to runshell and writefile when executecodesandbox or shellagent fail on filesystem operations

MITAuto-check passed

Install Robust File Creation

skills CLI
$ npx skills add HKUDS/OpenSpace --skill robust-file-creation -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace robust-file-creation --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/robust-file-creation .claude/skills/robust-file-creation && 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
robust-file-creation
GitHub stars
7.8k
Token cost
~758 tokens
SKILL.md length
307 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback to runshell and writefile when executecodesandbox or shellagent fail on filesystem operations

  • Works in 4 steps: Detect the Failure → Create Directories Explicitly → Write Files Individually → …
  • SKILL.md covers When to Use, Fallback Procedure, Complete Example Flow and Best Practices, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Robust File Creation is an agent skill from HKUDS/OpenSpace. Fallback to runshell and writefile when executecodesandbox or shellagent fail on filesystem operations

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

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

Example prompts

  • “/robust-file-creation”

Requirements

  • Python 3

Workflow steps

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

  1. Detect the Failure
  2. Create Directories Explicitly
  3. Write Files Individually
  4. Verify Creation (Optional)

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 bash).

    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

Robust File Creation loads about 758 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 307 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~32
When it runs · the whole SKILL.md, loaded when a task matches
~758

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). 307 words, ~758 tokens.

Download SKILL.mdSave it as .claude/skills/robust-file-creation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
robust-file-creation
description
Fallback to run_shell and write_file when execute_code_sandbox or shell_agent fail on filesystem operations

Robust File Creation Strategy

When creating complex project structures, automated tools like execute_code_sandbox and shell_agent may fail with 'unknown error' on filesystem operations. This skill provides a reliable fallback strategy using explicit shell commands.

When to Use

Apply this pattern when:

  • execute_code_sandbox fails with unknown error on file/directory creation
  • shell_agent fails to complete filesystem operations after retries
  • You need to create nested directory structures with multiple files
  • Task progress is blocked by filesystem tool failures

Fallback Procedure

Step 1: Detect the Failure

When either execute_code_sandbox or shell_agent fails on filesystem operations (especially after automatic retries), immediately switch to the manual hybrid approach.

Step 2: Create Directories Explicitly

Use run_shell with mkdir -p for each required directory:

bash
run_shell command="mkdir -p /path/to/nested/directory"

The -p flag ensures parent directories are created automatically.

Step 3: Write Files Individually

Use write_file tool for each file with explicit path and content:

write_file path="/path/to/file.py" content="..."

Do not attempt to batch multiple file creations in a single operation.

Step 4: Verify Creation (Optional)

Confirm the structure was created correctly:

bash
run_shell command="ls -la /path/to/directory"
# or
run_shell command="tree /path/to/directory"

Complete Example Flow

[execute_code_sandbox fails on project setup]
        ↓
[run_shell mkdir -p src/components]
[run_shell mkdir -p src/utils]
[run_shell mkdir -p tests]
        ↓
[write_file path="src/main.py" content="..."]
[write_file path="src/components/widget.py" content="..."]
[write_file path="tests/test_main.py" content="..."]
        ↓
[run_shell ls -la src/  # verify]

Best Practices

  1. Create all directories first before writing any files to avoid path errors
  2. Write files one at a time rather than attempting batch operations
  3. Use absolute or clearly relative paths to avoid ambiguity
  4. Verify after creation when working on critical deliverables
  5. Document the structure in comments or SKILL.md if it's complex

Why This Works

  • run_shell executes commands directly without the abstraction layer that can fail
  • write_file is a primitive operation with fewer failure modes
  • Separating directory creation from file writing isolates potential failure points
  • Explicit commands are easier to debug when issues occur

Anti-Patterns to Avoid

❌ Don't keep retrying the same failing execute_code_sandbox command ❌ Don't attempt to create complex nested structures in a single Python script via sandbox ❌ Don't assume directories exist before writing files to them ❌ Don't skip verification on critical project scaffolding

© 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/robust-file-creation of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Robust File Creation 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.

Robust File Creation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Robust File Creation this skillHKUDS/OpenSpace7.8k—~758Automated safety check: PassMIT
Executealirezarezvani/claude-skills28k—~831Automated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Shell ScriptingRightNow-AI/openfang18k—~827Automated safety check: PassApache-2.0
Crush Shell Builtinscharmbracelet/crush29k—~790Automated safety check: PassCustom licence
Remotion Video Creationaffaan-m/ECC276k2 repos~910Automated safety check: PassMIT

Similar skills

  • Execute

    alirezarezvani/claude-skills

    /cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.

    28k GitHub stars~831 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Shell Scripting

    RightNow-AI/openfang

    Shell scripting expert for Bash, POSIX compliance, error handling, and automation

    18k GitHub stars~827 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Crush Shell Builtins

    charmbracelet/crush

    Explains how to add a new in-process builtin command to Crush's embedded POSIX shell, so it is intercepted before reaching the OS, with context polling and exit-status rules.

    29k GitHub stars~790 tokensUpdated today
    DevelopmentAuto-check passed
  • Best practices for Remotion - Video creation in React. An agent skill from affaan-m/ECC.

    276k GitHub starsUsed in 2 repos~910 tokens
    Media & CreativeAuto-check passed
  • Ulw Execute

    code-yeongyu/oh-my-openagent

    Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents.

    70k GitHub stars~6.3k tokensUpdated today
    Agent WorkflowsAuto-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.

    7.8k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.8k 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.

    7.8k 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.

    7.8k 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.

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Robust File Creation

What does Robust File Creation do?

Fallback to runshell and writefile when executecodesandbox or shellagent fail on filesystem operations. Robust File Creation is an agent skill from HKUDS/OpenSpace.

How do I install Robust File Creation in Claude Code?

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

How do I install Robust File Creation in Codex?

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

Can I use Robust File Creation 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 robust-file-creation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/robust-file-creation, .gemini/skills/robust-file-creation, .github/skills/robust-file-creation and .opencode/skills/robust-file-creation in your project.

What does Robust File Creation need to run?

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

Does Robust File Creation 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 Robust File Creation 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 Robust File Creation use?

Robust File Creation 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 Robust File Creation use?

About 758 tokens (SKILL.md is roughly 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 Robust File Creation?

Skills that share tags, products or a category with Robust File Creation: Execute (alirezarezvani/claude-skills, 28k stars), Debugging Executions (n8n-io/n8n, 207k stars), Shell Scripting (RightNow-AI/openfang, 18k stars) and Crush Shell Builtins (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Robust File Creation?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 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.