python-shell-fallback

Fallback to shell execution when sandbox fails for library-dependent Python code

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/python-shell-fallback/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

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

The content is well-structured and actionable with executable examples and concrete troubleshooting commands. Its main weaknesses are a duplicated reportlab example that hurts conciseness and a verification step that lives in Best Practices rather than as an explicit workflow checkpoint.

Suggestions

Consolidate the Step 3 reportlab block and the Example section into one example to remove redundancy and improve conciseness.

Add an explicit 'Verify output' checkpoint as Step 4 in the workflow (e.g., check run_shell stdout/stderr and confirm the output file exists) to lift workflow clarity.

Replace the '# Your library-dependent code here' placeholder with a fully specified minimal example and clarify how the heredoc is passed to run_shell.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and on-task, but the reportlab PDF heredoc appears twice (Step 3 and the Example section) with near-identical content, and the opening justification about shell package access is mild padding; fits 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides copy-paste-ready heredoc code, a concrete reportlab example, and executable troubleshooting commands (which python3, pip3 list \| grep, pip3 install); not a 5 because the Step 3 'command:' block and '# Your library-dependent code here' placeholder leave minor ambiguity about the exact run_shell invocation.	4 / 5
Workflow Clarity	Steps 1-3 give a clear sequence, but validation is only mentioned in Best Practices ('Verify output - Check stdout/stderr') rather than embedded as an explicit checkpoint in the workflow, matching 'steps listed but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (When to Use, How to Implement, Example, Best Practices, Alternative, Troubleshooting) with all content appropriately inline for a single-purpose skill and no nested references; not a 5 only because the skill slightly exceeds the 50-line simple-skill threshold and has minor redundancy between Step 3 and the Example.	4 / 5
	Total	14 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 concisely states both the action and a clear trigger condition, giving it solid completeness and distinctiveness. It is held back by a single concrete action and missing natural trigger variations like specific import-error phrases.

Suggestions

Add 1-2 more concrete actions (e.g., 'run heredoc Python scripts', 'verify package availability') to lift specificity toward 4-5.

Include natural trigger phrases users would say, such as 'ModuleNotFoundError' or 'package not installed', to improve trigger term quality.

Tighten the 'when' clause with a concrete error example, e.g., 'Use when execute_code_sandbox fails with ModuleNotFoundError or ImportError for external libraries.'

Dimension	Reasoning	Score
Specificity	Names the domain (library-dependent Python code, sandbox failures) and one concrete action ("Fallback to shell execution"), matching the 'names domain and 1-2 concrete actions' anchor; not a 4 because only a single action is listed rather than several.	3 / 5
Completeness	Answers both "what" ("Fallback to shell execution") and "when" ("when sandbox fails for library-dependent Python code") with an explicit trigger clause, so it is not capped at 3; not a 5 because the trigger lacks concrete error-phrase triggers.	4 / 5
Trigger Term Quality	Includes relevant terms like "shell execution", "sandbox", and "library-dependent Python code", but misses common natural variations users would say such as specific error names (ModuleNotFoundError) or "pip install"; fits the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The sandbox-failure trigger carves a clear, distinct niche with only minor overlap risk against general Python execution skills; not a 5 because "shell execution" could lightly overlap with generic shell-scripting skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/python-shell-fallback/SKILL.md
Commit: 3827781

Reviewed: 20 days ago

Table of Contents

Discovery Implementation Validation

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.