CtrlK
BlogDocsLog inGet started
Tessl Logo

code-execution-fallback-e81068

Fallback workflow for executing Python code when execute_code_sandbox fails repeatedly

59

Quality

68%

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/code-execution-fallback-e81068/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 actionable and well-structured with executable code and a useful troubleshooting table, but it lacks an explicit validation/verification checkpoint in the disk-writing workflow and carries some redundant examples that pad the token budget.

Suggestions

Add an explicit validation step before Step 5 cleanup (e.g., assert the script exited 0 and verify expected output/exit file exists before deleting anything).

Remove or trim the Complete Example section, which largely restates Steps 2-4 with boilerplate code already shown above.

Replace the placeholder write_file(...)/run_shell(...) blocks with literal, copy-pasteable tool invocations so the guidance is fully executable.

DimensionReasoningScore

Conciseness

The body is mostly useful but padded in places—e.g., "Use clear, self-contained code that doesn't rely on sandbox-specific paths" and the duplicated boilerplate write_file example in the Complete Example restate guidance already covered, which could be tightened.

3 / 5

Actionability

Provides concrete, copy-paste-ready write_file/run_shell code blocks and a troubleshooting table with specific commands, with only minor gaps (the write_file calls are shown as pseudocode-style invocations rather than literal tool calls).

4 / 5

Workflow Clarity

Steps are clearly numbered 1-5 with sequencing, but this workflow writes scripts to disk (a batch/persistence operation) yet lacks an explicit validation checkpoint verifying the result before cleanup, which caps clarity at 3 per the destructive/batch guidance.

3 / 5

Progressive Disclosure

No bundle files exist, so structure rests on well-organized inline sections (When to Use, Steps, Troubleshooting, Best Practices, When NOT to Use); navigation is clear, though the Complete Example duplicates inline content rather than being split out.

4 / 5

Total

14

/

20

Passed

Description

77%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 is specific, distinct, and answers both what and when with a clear trigger tied to repeated sandbox failures. It is slightly verbose for a description and could tighten its keyword coverage, but it is well above the midpoint.

DimensionReasoningScore

Specificity

Names the specific fallback mechanism ("write_file + run_shell to save Python scripts to disk and execute them via command line") and the triggering condition, yielding several concrete actions, though it stops short of a fully comprehensive enumeration.

4 / 5

Completeness

It clearly states both what it does (fallback workflow using write_file + run_shell) and when to use it (when execute_code_sandbox fails repeatedly 2+ attempts); the trigger is explicit but slightly less granular than the top anchor.

4 / 5

Trigger Term Quality

Includes natural, user-sayable phrases like "execute_code_sandbox fails repeatedly" and "command line", but lacks synonyms or common variations users might say (e.g., Python won't run, sandbox errors), so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

It carves out a very specific niche (fallback only when a named sandbox tool fails repeatedly), with a distinct trigger unlikely to fire for unrelated skills and minimal conflict risk.

5 / 5

Total

17

/

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.