CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-fallback-execution

Fallback workflow for executing Python code when execute_code_sandbox fails

60

Quality

68%

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/sandbox-fallback-execution/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 is well-structured and highly actionable with executable, copy-paste-ready examples and a clear sequenced workflow; its main weakness is generic rather than explicit validation checkpoints and minor trimmable over-explanation.

Suggestions

Replace the generic verify step with an explicit pass/fail checkpoint (e.g., 'Only proceed if the script exits 0 and expected output/artifact is present').

Trim the heredoc syntax notes and redundant best-practice items that restate shell basics Claude already knows.

Add a brief explicit error-recovery loop for the install step (verify pip succeeded before running the heredoc).

DimensionReasoningScore

Conciseness

Mostly efficient with executable code blocks and a compact troubleshooting table, but includes minor trimmable over-explanation (heredoc syntax notes and best-practice items that restate known shell concepts or prior content).

4 / 5

Actionability

Fully executable, copy-paste-ready bash heredoc commands and a complete worked example (python-docx document creation) covering a common case.

5 / 5

Workflow Clarity

Clear four-step sequence with a verify-and-iterate step, but validation is generic ('check stdout/stderr', 'if errors persist, adjust') rather than an explicit pass/fail checkpoint, fitting the 'clear sequence with minor validation gaps' anchor.

4 / 5

Progressive Disclosure

A single self-contained SKILL.md with well-organized sections (overview, steps, example, best practices, troubleshooting, related tools), easy navigation, and no nested references — appropriately structured for a skill of this size.

5 / 5

Total

18

/

20

Passed

Description

51%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 defines a niche fallback use case with explicit what/when guidance, but relies on internal tool jargon rather than natural user-facing trigger terms and lacks enumerated concrete actions.

Suggestions

Add concrete fallback actions to the description (e.g., 'installs packages and runs Python via a shell heredoc').

Include natural user-facing trigger phrasing (e.g., 'Use when sandbox code execution fails or times out repeatedly').

Consider mentioning common symptoms users would describe (timeouts, persistent execution failures) alongside the tool name.

DimensionReasoningScore

Specificity

Names the domain (Python execution) and one implied fallback action ('when execute_code_sandbox fails') but does not enumerate concrete actions like pip install or heredoc execution, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

Explicitly states both what (fallback workflow for executing Python code) and when (when execute_code_sandbox fails); the 'when' is explicit but uses a technical/internal condition rather than user-facing trigger phrases, fitting the 'both present, when could be more explicit' anchor.

4 / 5

Trigger Term Quality

Only technical jargon and internal tool names appear ('execute_code_sandbox fails', 'Python code'); no natural phrases a user would actually say, matching the 'only technical jargon' anchor.

1 / 5

Distinctiveness Conflict Risk

A highly specific niche tied to a named tool's failure state, with a distinct trigger and minimal overlap risk with other skills.

5 / 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.