Resolve file access failures by changing to the correct working directory before command execution
59
67%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./benchmarks/gdpval/skills/working-directory-resolution/SKILL.mdMany file operation failures occur because the tool's current working directory doesn't match where the target files are located. This skill provides a reliable pattern for resolving such issues.
File operations fail with errors like:
These failures often occur even when files are present in the workspace—the working directory context is simply wrong.
Always explicitly set the working directory before file operations by prepending cd to your shell commands.
cd /path/to/target/directory && your-command-hererun_shellrun_shell(command="cd /workspace/project && cat config.json")cd /workspace/project && ls -la && cat README.md && python script.pycd /workspace/project 2>/dev/null && cat file.txt || echo "Directory not found"Use this pattern when:
read_file fails to locate an existing fileexecute_code_sandbox can't find referenced filesUse absolute paths when possible
cd /workspace/project/src && python main.pyCombine related operations to avoid repeated cd calls
cd /workspace/project && ./build.sh && ./test.shVerify directory exists before operations
[ -d /workspace/project ] && cd /workspace/project && lsFor scripts, set working directory at the start
#!/bin/bash
cd "$(dirname "$0")" || exit 1
# Rest of script runs from script's directory| Issue | Wrong Approach | Correct Approach |
|---|---|---|
| Relative paths | cat config.json | cd /workspace && cat config.json |
| Assumed cwd | python script.py | cd /workspace && python script.py |
| Multiple dirs | cd dir1; cd dir2; cmd | cd dir1/dir2 && cmd |
If cd also fails:
pwd to check current directoryfind or ls -R to locate filesls -la /path/to/checkpwd && find /workspace -name "target_file.txt" 2>/dev/nullThis pattern is especially valuable when tools like execute_code_sandbox or read_file fail but run_shell with explicit directory context succeeds.
c5a9c4b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.