CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-execution-fallback-717e65

Fallback from execute_code_sandbox to file-based run_shell execution when sandbox fails

63

Quality

73%

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/sandbox-execution-fallback-717e65/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 body is highly actionable with concrete, executable examples and a complete worked example, and is well-organized as a self-contained procedure. Its weaknesses are redundancy that hurts conciseness and a missing explicit validation/feedback checkpoint around the destructive cleanup step.

Suggestions

Collapse the overlap between "When to Use" and "Step 1: Detect When to Switch" into a single trigger section, and trim the promotional "Advantages Over Sandbox Execution" table.

Add an explicit validation step before cleanup (e.g., "Verify run_shell succeeded and output exists, then remove temp files; if it failed, fix and re-run") to introduce a feedback loop.

Consider whether the standalone "Complete Example" adds enough beyond the in-step examples to justify its length, or fold its unique parts into the steps.

DimensionReasoningScore

Conciseness

It avoids explaining basic concepts, but the "When to Use" section overlaps "Step 1: Detect When to Switch", the "Complete Example" duplicates Steps 2-4, and the "Advantages Over Sandbox Execution" table is promotional padding, so it could be tightened.

2 / 3

Actionability

It provides concrete, copy-paste-ready code (write_file, run_shell, rm, pip3 install, chmod), a full working data-processing example, and specific troubleshooting fixes, matching the fully-executable anchor.

3 / 3

Workflow Clarity

Steps 1-4 are clearly sequenced, but there is no explicit validation checkpoint or feedback loop before the destructive "rm script.py" cleanup ("after successful execution" is only implicit), which caps the score at 2.

2 / 3

Progressive Disclosure

It is a self-contained single-purpose procedure with no need for external references, organized into clear headed sections (When to Use, Procedure, Example, Best Practices, Troubleshooting), which per the simple-skill note justifies the top score.

3 / 3

Total

10

/

12

Passed

Description

75%

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 well-scoped with an explicit when-trigger, but relies on internal tool-name jargon (execute_code_sandbox, run_shell) rather than natural user keywords and describes only a single action. Overall a solid, distinctive description.

Suggestions

Add a "Use when the sandbox keeps failing..." style phrasing with natural user terms (e.g., "code execution sandbox", "sandbox errors") alongside the tool identifiers.

List one or two more concrete actions (e.g., write Python to a file, run it via shell, inspect output) to reach the score-3 specificity anchor.

DimensionReasoningScore

Specificity

Names the domain (sandbox execution) and a concrete action ("Fallback from execute_code_sandbox to file-based run_shell execution"), but it is a single action rather than multiple specific concrete actions, matching the score-2 anchor.

2 / 3

Completeness

It states what it does (fallback to file-based run_shell execution) and an explicit when ("when sandbox fails"), answering both what and when with explicit trigger guidance, so it is not capped at 2.

3 / 3

Trigger Term Quality

"sandbox fails" is reasonably natural, but the core keywords are tool identifiers (execute_code_sandbox, run_shell) that a user would not naturally say, so it has some relevant keywords while missing natural user phrasing.

2 / 3

Distinctiveness Conflict Risk

It targets a very specific fallback niche with distinct triggers (sandbox failure), making it clearly distinguishable and unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

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.