CtrlK
BlogDocsLog inGet started
Tessl Logo

fallback-python-execution

Reliable Python execution workflow when execute_code_sandbox or shell_agent fail

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/fallback-python-execution/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 body delivers a clear, actionable two-step pattern with concrete code and a sensible verification step, organized into clean sections. It could be tightened by removing the redundant explanatory sections and folding error-recovery into the main workflow.

Suggestions

Trim or remove the 'Why This Works' section; the rationale is largely inferable and adds tokens without adding actionable guidance.

Replace the duplicated Excel example with a pointer to the step-by-step pattern, or make it demonstrate a distinct case rather than re-stating the same write-then-run flow.

Add an explicit feedback loop in Step 3 (e.g., 'If run_shell reports a Python error, read the traceback, fix script.py, and re-run') so error recovery is part of the workflow rather than only the troubleshooting table.

DimensionReasoningScore

Conciseness

Mostly efficient, but the 'Why This Works' section explains concepts Claude could infer and the Excel example duplicates the step-by-step pattern already shown, adding padding that could be trimmed.

3 / 5

Actionability

Provides concrete write_file and run_shell invocations with real Python code that is executable, though the tool calls are shown in a pseudo-YAML representation rather than literal executable form.

4 / 5

Workflow Clarity

A clear three-step sequence (Write, Execute, Verify) with an explicit verification step, but it lacks an inline error-recovery feedback loop in the main flow beyond the separate troubleshooting table.

4 / 5

Progressive Disclosure

Well-organized into clear sections with no need for external references, but at ~100 lines it slightly exceeds the simple-skill threshold where structure alone would warrant a top score.

4 / 5

Total

15

/

20

Passed

Description

55%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 clearly communicates a fallback purpose tied to specific tool failures, but leans on technical jargon for its trigger and stays vague about the concrete actions performed. Strengthening it with natural user trigger phrases and explicit actions would raise its quality.

Suggestions

Add natural trigger phrases a user might say (e.g., 'Use when Python code won't run, scripts fail to execute, or you need to create files like spreadsheets via Python').

Replace the abstract 'workflow' phrasing with concrete actions: 'Writes Python scripts to a file and runs them via the shell to create spreadsheets, documents, and data files.'

Keep the tool-failure trigger but pair it with user-facing symptoms so it triggers on natural language, not just internal tool names.

DimensionReasoningScore

Specificity

Names the domain ('Python execution workflow') and one concrete action pattern but does not enumerate the specific actions it performs (write script, run via shell, create files), keeping coverage non-comprehensive.

3 / 5

Completeness

It states both what ('Reliable Python execution workflow') and when ('when execute_code_sandbox or shell_agent fail'), but the 'what' is somewhat abstract and could be more explicit about the actual mechanism.

4 / 5

Trigger Term Quality

The trigger ('when execute_code_sandbox or shell_agent fail') relies on internal tool names rather than natural user phrasing; a user would rarely say these terms when needing the skill.

2 / 5

Distinctiveness Conflict Risk

The fallback-when-tools-fail niche is fairly distinct with a specific trigger, with only minor overlap risk against general Python execution skills.

4 / 5

Total

13

/

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.