CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-fallback-execution-5eda7b

Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

64

Quality

76%

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-fallback-execution-5eda7b/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable code and a clear sequenced workflow including a verification checkpoint. It loses points for redundancy across the example sections and a monolithic single-file structure with no progressive disclosure.

Suggestions

Remove the redundancy between Steps 3-5 and the 'Complete Example Pattern' — keep one canonical end-to-end example and reference it from the other sections.

Move the extended examples or the 'Applicable Use Cases' list into a separate reference file to reduce inline length and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly concrete but redundant: Steps 3-5 and the 'Complete Example Pattern' re-implement the same write/run flow, and the Overview restates context Claude already knows. Could be tightened by keeping one canonical end-to-end example.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code throughout (write_file, run_shell with python/pip commands, ls verification) with specific, concrete commands.

3 / 3

Workflow Clarity

Clearly sequenced Step 1-5 workflow with an explicit verification checkpoint (Step 5: 'ls -la output.pdf' / read_file) and try/except error handling in the complete example.

3 / 3

Progressive Disclosure

Well-organized into labeled sections but monolithic: over 50 lines with all content inline and no references to separate files for the extended examples or use-case list.

2 / 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 clearly conveys both purpose and trigger condition with concrete actions and a distinct niche. It is slightly technical in its trigger phrasing and frames a single fallback flow rather than a spread of capabilities.

DimensionReasoningScore

Specificity

Names the domain (Python code execution) and concrete actions ('writing scripts to disk and running via shell'), but these are sub-steps of a single fallback flow rather than a broad set of distinct capabilities.

2 / 3

Completeness

Explicitly states both what it does ('Fallback pattern for executing Python code ... by writing scripts to disk and running via shell') and when to use it ('when sandbox execution fails').

3 / 3

Trigger Term Quality

Includes relevant terms like 'sandbox execution fails' and 'Python code', but the phrasing leans technical/internal and lacks common user variations or a clean 'Use when' trigger.

2 / 3

Distinctiveness Conflict Risk

A narrow, specific niche (sandbox-failure fallback) with a distinct trigger condition unlikely to fire 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.