CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-fallback-execution

Fallback workflow for executing Python code when execute_code_sandbox fails

54

Quality

60%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-structured, with executable examples, a clear validated workflow, and clean single-file organization. The only meaningful weakness is mild verbosity from restated guidance across the Complete Example and Best Practices sections.

Suggestions

Trim overlap between the Step-by-Step Instructions, Complete Example, and Best Practices sections to reduce token cost without losing clarity.

Optionally fold the troubleshooting table and Best Practices into the relevant steps so each instruction carries its own caveats inline.

DimensionReasoningScore

Conciseness

The body is mostly efficient with step lists and executable code and avoids explaining basic concepts, but the Complete Example and Best Practices sections partially restate the step instructions and could be tightened.

2 / 3

Actionability

It provides fully executable, copy-paste-ready commands and code (pip install, quoted-EOF heredoc, a complete python-docx example) plus a concrete troubleshooting table with specific fixes.

3 / 3

Workflow Clarity

A clear four-step sequence (Detect, Install, Execute, Verify) is given, with Step 4 acting as an explicit validation and feedback loop (check stdout/stderr, inspect output, adjust script on persistent errors).

3 / 3

Progressive Disclosure

It is a well-organized single-file skill with clearly labeled sections and no nested or external references, satisfying the simple-skill allowance for top-level progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

35%

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 a specific fallback scenario but relies on an internal tool name as its trigger rather than natural user phrasing, weakening trigger-term quality and distinctiveness. It answers what and when but lacks the explicit user-facing 'Use when' guidance that would lift completeness to the top level.

Suggestions

Add a natural-language 'Use when...' clause naming user-facing terms (e.g., 'Use when sandboxed code execution keeps failing, timing out, or hitting unknown errors') so the trigger matches what a user would actually say.

Expand the capability list beyond the single fallback action to the concrete steps it performs (install dependencies, run Python via heredoc, verify output) to raise specificity.

Replace the internal tool reference with a more distinctive user-context niche to reduce overlap with general code-execution skills.

DimensionReasoningScore

Specificity

Names a concrete domain and action ('executing Python code') plus a specific trigger condition ('when execute_code_sandbox fails'), but describes only a single fallback action rather than the multiple specific concrete actions expected at score 3.

2 / 3

Completeness

It answers both what ('Fallback workflow for executing Python code') and when ('when execute_code_sandbox fails'), but the trigger is an internal-failure condition rather than an explicit user-context 'Use when...' clause, capping it below 3.

2 / 3

Trigger Term Quality

The only trigger phrase ('execute_code_sandbox fails') is an internal tool name, not natural language a user would say; there are no common user-facing trigger variations.

1 / 3

Distinctiveness Conflict Risk

Tied to a specific tool's failure it is somewhat distinct, but the trigger is technical/internal rather than a clear user-language niche, so it could still overlap with general code-execution skills.

2 / 3

Total

7

/

12

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.