CtrlK
BlogDocsLog inGet started
Tessl Logo

python-shell-workaround

Workaround for executing Python code with external packages when sandbox fails

57

Quality

65%

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

67%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 skill gives actionable, executable guidance with a clear step sequence and good section structure. Main weaknesses are redundancy between the Step 2 and Example Scenarios code blocks and a non-runnable tool-invocation snippet.

Suggestions

Remove the duplicated openpyxl Excel heredoc — keep one canonical example in Example Scenarios and reference it from Step 2 to cut tokens.

Replace the pseudo "tool: run_shell" block in Step 3 with an actual runnable shell command so every example is copy-paste ready.

Strengthen the Step 4 verification checkpoint with a concrete success/failure check (e.g. test for the output file or grep stderr for ModuleNotFoundError) to form a real feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes redundancy (an openpyxl Excel heredoc appears in both Step 2 and Example Scenarios) and light padding in Best Practices/Limitations that could be trimmed.

3 / 5

Actionability

It provides concrete, executable python3 -c and heredoc commands with real examples, though the Step 3 "tool: run_shell" block is a non-runnable pseudo-invocation.

4 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced (detect, convert, execute, verify) with a verify checkpoint in Step 4; the validation guidance is light but the operation is not destructive or batch.

4 / 5

Progressive Disclosure

Content is organized into well-labeled sections (When to Use, Pattern, Steps, Best Practices, Examples, Limitations, Related) with no bundle files; all content is inline which is acceptable for this size though slightly over 50 lines.

4 / 5

Total

15

/

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 answers both what and when with a clear, concise trigger tied to sandbox failure, but lacks keyword breadth and could name more concrete actions. It is distinct enough to avoid most conflicts.

Suggestions

Add natural synonyms and file/tool cues users actually say, e.g. "Use when execute_code_sandbox fails with ModuleNotFoundError or missing pip packages like openpyxl, pandas, python-docx".

Name 1-2 more concrete actions (e.g. "run Python one-liners or heredocs via run_shell and pip install missing packages") to lift specificity.

Tighten the trigger to reference the specific failure signal (ModuleNotFoundError / import errors) for sharper distinctiveness.

DimensionReasoningScore

Specificity

The phrase "executing Python code with external packages" names the domain and one concrete action, but coverage is not comprehensive (no mention of install/import/convert specifics).

3 / 5

Completeness

It states both what ("Workaround for executing Python code with external packages") and an explicit when ("when sandbox fails"), though the trigger could be more specific.

4 / 5

Trigger Term Quality

It includes relevant keywords ("Python code", "external packages", "sandbox fails") but misses common synonyms a user might say such as "pip", "libraries", or "imports".

3 / 5

Distinctiveness Conflict Risk

The sandbox-failure fallback niche is fairly distinct, but the broad "executing Python code" phrasing leaves minor overlap risk with general Python skills.

4 / 5

Total

14

/

20

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.