CtrlK
BlogDocsLog inGet started
Tessl Logo

execute-code-fallback

Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/execute-code-fallback/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands and well-organized sections, but it is somewhat redundant across its examples and lacks an explicit validation feedback loop for the risky fallback transition.

Suggestions

Consolidate the redundant pip-install and heredoc examples that recur across Steps 3-4, the Complete Example, and the Quick Reference table.

Add an explicit validation checkpoint with a retry loop, e.g., 'Run the command, check the exit code, and if non-zero, review stderr and re-run with fixes' rather than abstract 'verify output' guidance.

DimensionReasoningScore

Conciseness

The body is mostly lean and actionable, but the Complete Example and Quick Reference table repeat the same pip-install and heredoc patterns already shown in Steps 3-4, and a few considerations state near-obvious guidance.

2 / 3

Actionability

It provides fully executable, copy-paste-ready commands throughout, including 'run_shell(command="python3 -c \"...\"")', 'pip install pandas requests matplotlib', and complete heredoc examples.

3 / 3

Workflow Clarity

Steps are clearly sequenced with a numbered procedure and recovery checklist, but there is no explicit validate-then-fix-then-retry feedback loop; error handling is described abstractly ('Verify output and handle errors') rather than as a concrete checkpoint.

2 / 3

Progressive Disclosure

The skill is a self-contained, well-organized single file with clear sections (When to Apply, Fallback Procedure, Complete Example, Considerations, Quick Reference, Recovery Checklist) and no need for external references.

3 / 3

Total

10

/

12

Passed

Description

57%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinctive but lacks an explicit 'Use when...' trigger clause and relies on technical jargon rather than natural user language. It states what the skill does clearly but not when Claude should invoke it.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g., 'Use when execute_code_sandbox fails with e2b or sandbox-unavailable errors and code execution is still needed.'

Include natural user-facing phrasings (e.g., 'sandbox is down', 'code execution failed') alongside the technical tool names to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description names a concrete domain and a specific action ('Fallback from execute_code_sandbox to run_shell when e2b sandbox is unavailable'), but it lists only a single transition rather than multiple concrete actions.

2 / 3

Completeness

It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause; the 'when e2b sandbox is unavailable' clause is a condition of the action, not invocation guidance, so completeness caps at 2.

2 / 3

Trigger Term Quality

Terms like 'execute_code_sandbox', 'run_shell', and 'e2b sandbox' are technical tool names rather than natural phrasings a user would say, though 'sandbox unavailable' has some recognizable quality.

2 / 3

Distinctiveness Conflict Risk

The skill occupies a clear, narrow niche (e2b sandbox fallback) with distinct tool names, making it unlikely to trigger for the wrong skill.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

Is this your skill?

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.