CtrlK
BlogDocsLog inGet started
Tessl Logo

python-execution-fallback

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

56

Quality

62%

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

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 four-step fallback workflow with executable examples and a validation checkpoint. Its main weakness is redundancy from the 'Complete Workflow' example that repeats the step-by-step guidance already provided.

Suggestions

Remove or significantly condense the 'Code Example: Complete Workflow' section since it duplicates the per-step examples already shown.

Add an explicit recovery action when Step 4 validation fails (e.g., inspect execution.log, fix the script, re-run) to close the feedback loop.

Trim the introductory paragraph and 'This approach:' bullets that restate what the code already demonstrates.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete code per step, but the 'Code Example: Complete Workflow' section re-implements the same four steps already shown, adding notable redundancy.

3 / 5

Actionability

Concrete, executable Python and shell snippets are provided for each step (inline attempt, file write, shell execution, validation), with only minor gaps around the abstracted execute_code_sandbox/run_shell APIs.

4 / 5

Workflow Clarity

The four steps are clearly sequenced with an explicit validation step (Step 4) and a feedback loop (Step 1 to Step 2 on failure), though no recovery action is specified when validation itself fails.

4 / 5

Progressive Disclosure

Content is well organized into clearly headed sections with no external bundle files needed; the only gap is the large inline 'Complete Workflow' example that could be trimmed or split.

4 / 5

Total

15

/

20

Passed

Description

57%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 conveys both purpose and a trigger condition in a concise third-person form, but it stays at a structural level ('four-step recovery workflow') without naming the concrete actions the skill performs. Adding the key verbs and a broader set of trigger phrases would lift it.

Suggestions

Name the concrete actions in the description, e.g. 'Writes the failing code to a .py file, executes it via shell, and validates the output'.

Broaden trigger terms to include natural variations users might say, such as 'heredoc', 'shell', 'script execution', or 'Python keeps failing inline'.

Consider an explicit 'Use when ...' clause to make the trigger guidance unambiguous.

DimensionReasoningScore

Specificity

The phrase 'recovery workflow for code execution failures' names the domain but the action ('recovery workflow') is generic; no concrete actions like 'write to file', 'execute', or 'validate' are listed.

2 / 5

Completeness

It answers both what ('four-step recovery workflow') and when ('when inline Python fails'), but the 'when' is a single trigger that could be more explicit and specific.

4 / 5

Trigger Term Quality

Relevant keywords like 'inline Python fails' and 'code execution failures' are present, but common variations/synonyms (heredoc, shell, script, debugging) are missing.

3 / 5

Distinctiveness Conflict Risk

The niche (inline Python execution failure fallback) is fairly distinct, with only minor overlap risk against general debugging or retry 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.