CtrlK
BlogDocsLog inGet started
Tessl Logo

python-execution-fallback

Four-step recovery workflow for code execution failures when inline Python fails

56

Quality

63%

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/python-execution-fallback/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 well-sequenced, validated workflow, but it suffers from notable redundancy and a monolithic structure with no progressive disclosure. Tightening repetition and splitting detailed material into reference files would raise the weaker dimensions.

Suggestions

Eliminate the third re-implementation in "Code Example: Complete Workflow" or collapse it into a reference to the step-by-step section to reduce redundancy.

Move the full worked example and "Common Failure Scenarios" into a reference file (e.g. references/EXAMPLES.md) and link to it from the body to improve progressive disclosure.

Trim overlap between "Best Practices" and the inline try/except guidance already shown in the code blocks.

DimensionReasoningScore

Conciseness

The same four-step workflow is re-implemented three times (overview, step-by-step, and the "Complete Workflow" example) and the Best Practices / Common Failure Scenarios sections overlap, so it is mostly useful but padded and could be tightened significantly.

2 / 3

Actionability

Provides fully executable, copy-paste-ready Python and shell (e.g. `python script.py 2>&1 | tee execution.log`) with concrete error handling, matching the executable-code anchor.

3 / 3

Workflow Clarity

A clear four-step sequence includes an explicit validation checkpoint (Step 4: Validate Output) and a feedback loop (inline fails -> write file -> execute -> validate), satisfying the validation-required guidance.

3 / 3

Progressive Disclosure

The ~190-line skill is a single monolithic file with no bundle files or external references, and content that could be split (full worked example, failure scenarios) is inline, though sections are well organized.

2 / 3

Total

10

/

12

Passed

Description

50%

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 what the skill does but omits an explicit usage trigger and relies on moderately generic terms, leaving it indistinguishable from broader debugging skills. All four dimensions land at the mid anchor.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers, e.g. "Use when inline Python execution fails with syntax or runtime errors in heredoc or sandbox contexts."

List concrete actions (e.g. "write the failing code to a .py file, execute it via shell, and validate the output") to lift specificity to 3.

Include natural user phrasings like "Python script won't run", "heredoc execution failed", or "sandbox error" to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("code execution failures") and an action ("recovery workflow") but does not enumerate multiple concrete actions; it is more than vague but short of a comprehensive action list.

2 / 3

Completeness

It states what the skill does ("Four-step recovery workflow") but provides no explicit "Use when..." trigger clause; per guidelines a missing trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Includes some natural terms a user might say ("Python", "code execution", "fails") but lacks common variations and explicit triggers, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

"Code execution failures" is fairly generic and could overlap with general debugging or Python-helper skills, so it is only somewhat distinctive.

2 / 3

Total

8

/

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.