CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-fallback-python-e5d7ae

Fallback to run_shell with Python heredoc when execute_code_sandbox fails

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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/sandbox-fallback-python-e5d7ae/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 skill body is highly actionable with executable examples and clear validation-gated workflows, but it is a single monolithic document that exceeds the lean length threshold and could tighten some redundant sections.

Suggestions

Move the full worked PDF example and the comparison table into a references file (e.g., EXAMPLES.md) and link to it from the body to apply progressive disclosure and trim the main file.

Tighten or remove the 'Comparison Table' section, since its distinctions are already implied by the surrounding guidance and it repeats information.

Consolidate 'Common Failure Indicators' and the 'When to Use' trigger phrasing so the failure-detection list is not restated across sections.

DimensionReasoningScore

Conciseness

The body is mostly lean and actionable, but the comparison table and some explanatory sections (e.g., restating 'Common Failure Indicators') add length that could be tightened without losing value.

2 / 3

Actionability

It provides multiple complete, executable examples — heredoc, file-based, PDF generation with reportlab, and pip install — that are concrete and copy-paste ready.

3 / 3

Workflow Clarity

The file-based and PDF examples show clear write → execute → verify sequences with an explicit verification step ('Verify output exists') and an error-handling section for feedback loops.

3 / 3

Progressive Disclosure

Content is well-organized into clear sections, but it is entirely monolithic with no external references despite exceeding 50 lines, and material like the full PDF example and comparison table could be split out.

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 is concise and answers both what and when with a distinct niche, but its trigger vocabulary leans on technical jargon and lists only one action, limiting its natural-trigger coverage and specificity.

Suggestions

Add a 'Use when...' clause with user-natural phrasing such as 'when the sandbox errors out or e2b fails' to broaden trigger coverage beyond the technical term 'execute_code_sandbox fails'.

Drop or de-emphasize the jargon term 'heredoc' in favor of plain language like 'inline Python script', which a user is more likely to say.

Name the additional concrete actions the fallback supports (e.g., run library-heavy scripts, generate files) so specificity reaches a comprehensive level.

DimensionReasoningScore

Specificity

The phrase 'Fallback to run_shell with Python heredoc' names a concrete action and domain, but it describes only a single action rather than a comprehensive list of capabilities.

2 / 3

Completeness

It explicitly states what it does ('Fallback to run_shell with Python heredoc') and when to use it ('when execute_code_sandbox fails'), satisfying both what and when.

3 / 3

Trigger Term Quality

'when execute_code_sandbox fails' is a relevant trigger, but 'heredoc' is technical jargon a user would not naturally say, and common variations like 'sandbox error' are missing.

2 / 3

Distinctiveness Conflict Risk

It targets a narrow, specific failure-mode niche (sandbox fallback with Python heredoc) with distinct triggers that are unlikely to conflict with other 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.