AGENT SKILL

fallback-code-execution

Fallback workflow for running code via file write and shell when sandbox execution fails

适用职业开发工程师
License 许可
MIT
所属仓库
HKUDS/AgentPilot
最近更新
2026-11-12
Stars
★ 8.0k
Forks
944

01 前言 Front Matter

name
fallback-code-execution
description
Fallback workflow for running code via file write and shell when sandbox execution fails

02 资源文件 1

03 SKILL.md 正文

Fallback Code Execution Workflow

Overview

This skill defines a robust workaround for executing code (specifically Python) when the primary execute_code_sandbox tool fails repeatedly with unknown or transient errors. Instead of continuing to retry the failing tool, the agent switches to a manual file-write and shell-execution pattern.

Trigger Conditions

Activate this workflow when:

  1. execute_code_sandbox fails 2 or more times consecutively for the same logic.
  2. Error messages are generic, unknown, or indicate environment issues rather than syntax errors.
  3. The code logic itself is verified correct but the execution environment is unstable.

Procedure

Step 1: Write Script to File

Use the write_file tool to save the Python script to a specific path in the workspace.

  • Path: Choose a descriptive name ending in .py (e.g., scripts/generate_report.py).
  • Content: Ensure the script includes necessary error handling and print statements for debugging.
  • Dependencies: If the script requires external libraries, ensure a requirements.txt is updated or installed via shell beforehand.

Example:

tool: write_file
path: workspace/scripts/process_data.py
content: |
  import sys
  # ... script logic ...
  print("Success")

Step 2: Execute via Shell

Use the run_shell tool to execute the script using the system Python interpreter.

  • Command: python3 <path_to_script> or python <path_to_script>.
  • Working Directory: Ensure the shell command runs from the workspace root or the directory containing the script.
  • Capture Output: Store stdout and stderr for verification.

Example:

tool: run_shell
command: python3 scripts/process_data.py

Step 3: Verify Execution

  1. Check Exit Code: Ensure the shell command returned exit code 0.
  2. Check Output: Verify expected files were created or expected stdout messages appeared.
  3. Handle Errors: If the shell execution fails, inspect the stderr output. This often provides more detailed tracebacks than the sandbox tool.

Best Practices

  • Absolute Paths: When writing scripts that access files, use absolute paths or resolve paths relative to __file__ to avoid working directory issues.
  • Permissions: Ensure the workspace directory allows file creation and execution.
  • Cleanup: Optionally remove temporary scripts after successful execution if cleanliness is required.
  • Logging: Add explicit print() statements in the Python script to log progress, as shell output capture is sometimes more reliable than sandbox return values.

Example Scenario

Problem: execute_code_sandbox times out while generating a PDF. Solution:

  1. Write generate_pdf.py to workspace/scripts/.
  2. Run python3 workspace/scripts/generate_pdf.py via run_shell.
  3. Confirm output.pdf exists in the workspace.

04 同仓库更多 Skills

HKUDS
HKUDS/AgentPilot

agentpilot

Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.

★ 8.0k
HKUDS
HKUDS/AgentPilot

remember

Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.

★ 8.0k
HKUDS
HKUDS/AgentPilot

skill-discovery

Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

delegate-task

Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.

Skill与智能体开发
★ 8.0k
HKUDS
HKUDS/AgentPilot

write-special-chars-ts-check

Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.

★ 8.0k
HKUDS
HKUDS/AgentPilot

write-special-chars-readback

Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of /tmp helper scripts.

★ 8.0k