CtrlK
BlogDocsLog inGet started
Tessl Logo

python-shell-workaround

Workaround for executing Python code with external packages 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

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/python-shell-workaround/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 content is highly actionable with executable examples and a clear, well-organized structure, but it carries redundant example code and lacks an explicit error-recovery feedback loop in its workflow. Trimming repetition and adding a retry-on-failure step would round it out.

Suggestions

Collapse the duplicate openpyxl Workbook examples into a single canonical snippet referenced from both the steps and the Example Scenarios section to remove redundancy.

Promote Step 4 into an explicit feedback loop: if run_shell reports ModuleNotFoundError, run `pip install <package> && python3 ...` and re-verify, rather than just 'check stdout/stderr then proceed'.

Trim the 'Best Practices' entries that restate shell fundamentals Claude already knows (quote escaping, heredocs) and keep only skill-specific guidance like safe command chaining.

DimensionReasoningScore

Conciseness

The body is mostly lean but repeats near-identical openpyxl examples and the 'Best Practices' section explains shell basics (quote escaping, heredocs) that Claude already knows, fitting the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor.

2 / 3

Actionability

It provides fully executable, copy-paste-ready commands throughout — `python3 -c` one-liners, heredoc blocks, and concrete openpyxl/docx scripts — matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The four steps are clearly sequenced and Step 4 verifies output, but validation is implicit ('Check the stdout/stderr... then proceed') with no explicit error-recovery feedback loop such as a pip-install fallback on failure, fitting the 'steps listed but validation gaps; checkpoints implicit' anchor.

2 / 3

Progressive Disclosure

This single-purpose, self-contained skill is organized into clear, navigable sections (When to Use, Pattern, Steps, Best Practices, Examples, Limitations, Related Patterns) with no need for external references, satisfying the well-organized-sections allowance for simple skills.

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 concise and answers both what and when with a distinct, low-conflict niche, but its action list is thin and its trigger terms are somewhat terse and jargon-tinged. Tightening these would lift it from good to excellent.

Suggestions

Add one or two concrete capabilities to the description (e.g., 'run inline Python and install missing packages via run_shell') to reach the score-3 specificity anchor of multiple specific actions.

Broaden trigger coverage with natural user phrasing such as 'ModuleNotFoundError', 'pip install', or 'package not available' alongside 'sandbox fails'.

DimensionReasoningScore

Specificity

The description names the domain and an action ("executing Python code with external packages") but stops short of listing multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the score-3 'lists multiple specific concrete actions'.

2 / 3

Completeness

It explicitly answers both what ("Workaround for executing Python code with external packages") and when ("when sandbox fails"), and the explicit 'when sandbox fails' trigger satisfies the 'Use when...' cap rule, so it is not held at 2.

3 / 3

Trigger Term Quality

Terms like "Python code" and "external packages" are reasonably natural, but "sandbox fails" leans toward internal tooling jargon and common variations (pip, ModuleNotFoundError, package not available) are missing, fitting the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The sandbox-failure fallback framing carves a clear niche with a distinct trigger, making it unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

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.