fallback-script-execution
Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail
- 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-script-execution
- description
- Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail
02 资源文件 1
- 其他.skill_id39 B
03 SKILL.md 正文
Fallback Script Execution with write_file + run_shell
When to Use This Skill
Use this pattern when:
shell_agentfails repeatedly with unclear error messagesexecute_code_sandboxconsistently errors or times out- You need better visibility into what's happening during execution
- Debugging inline code or delegated agents proves difficult
Core Pattern
Instead of delegating execution to an agent or running inline code, use this two-step approach:
- Write script to file using
write_file - Execute script using
run_shellwithpython script.py
This provides:
- Clearer error messages (full stack traces visible in run_shell output)
- Easier debugging (script persists for inspection)
- Better control over execution environment
- Ability to modify and re-run without rewriting code
Step-by-Step Instructions
Step 1: Write the Script File
Use write_file to create a self-contained Python script:
write_file with:
path: "path/to/script_name.py"
content: |
#!/usr/bin/env python3
# Your complete script here
# Include imports, logic, and error handling
Best Practices:
- Include descriptive comments
- Add try/except blocks for error handling
- Print intermediate results for debugging
- Use absolute or clear relative paths
Step 2: Execute the Script
Use run_shell to execute the script:
run_shell with:
command: "python path/to/script_name.py"
Best Practices:
- Capture and examine full output
- If errors occur, the script file is still available for inspection
- You can re-run with modifications without starting over
Example: Data Processing Task
❌ Problematic Approach (shell_agent fails repeatedly)
shell_agent with:
task: "Load Excel file, calculate correlations, save results"
Result: Agent struggles with path handling, unclear errors
✅ Recommended Approach (write_file + run_shell)
# Step 1: Write script
write_file with:
path: "correlation_analysis.py"
content: |
import pandas as pd
import sys
try:
# Load data
df = pd.read_excel('data.xlsx', sheet_name='Returns')
print(f"Loaded {len(df)} rows")
# Calculate correlation
corr = df.corr()
print(f"Correlation matrix shape: {corr.shape}")
# Save results
with pd.ExcelWriter('output.xlsx') as writer:
df.to_excel(writer, sheet_name='Returns')
corr.to_excel(writer, sheet_name='Correlation')
print("SUCCESS: output.xlsx created")
except Exception as e:
print(f"ERROR: {type(e).__name__}: {e}", file=sys.stderr)
sys.exit(1)
# Step 2: Execute script
run_shell with:
command: "python correlation_analysis.py"
Debugging Tips
- Add print statements at key points to trace execution
- Check file paths - use
run_shellwithls -la path/to verify files exist - Inspect errors - run_shell output shows full Python stack traces
- Modify and re-run - edit the script file and execute again without rewriting
When to Escalate
If this pattern also fails:
- Verify Python is available:
run_shellwithwhich pythonorpython --version - Check file permissions:
run_shellwithls -la script.py - Try explicit Python path:
run_shellwith/usr/bin/python script.py - Consider task complexity - may need to break into smaller scripts
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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.