CtrlK
BlogDocsLog inGet started
Tessl Logo

sandbox-fallback-python

Fallback to run_shell with embedded Python when execute_code_sandbox fails due to e2b unavailability

63

Quality

73%

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

Quality

Content

72%

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

The body is actionable with executable, copy-paste-ready examples and clear organization for a single-purpose fallback. Weaknesses are mild verbosity from repeated heredoc examples and validation that sits in best practices rather than as an explicit workflow checkpoint.

Suggestions

Trim redundant heredoc examples — the three 'Code Examples' repeat the pattern already shown in the procedure steps; consolidate to one or two distinct cases.

Add an explicit validation checkpoint in the procedure (e.g., a step that checks the run_shell exit code / stderr before proceeding) rather than mentioning verification only in Best Practices.

DimensionReasoningScore

Conciseness

Mostly efficient with executable snippets, but repeats the same heredoc pattern across three example sections and explains basics Claude already knows (using ls, absolute paths, pip install), matching the score-2 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

Provides fully executable, copy-paste-ready bash commands with heredoc-embedded Python and pip install chaining, plus concrete file-I/O examples, matching the score-3 anchor for fully executable code.

3 / 3

Workflow Clarity

A clear four-step sequence is present, but verification is relegated to 'Best Practices' rather than embedded as an explicit checkpoint in the procedure, leaving validation implicit per the score-2 anchor.

2 / 3

Progressive Disclosure

A self-contained single-purpose skill with clean section organization and no nested external references; keeping content inline is appropriate and there is no deep-reference indirection.

3 / 3

Total

10

/

12

Passed

Description

75%

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 concise and clearly answers both what the skill does and when to use it, occupying a distinct niche. Its main weakness is trigger-term quality: the activation conditions rely on internal tool/provider jargon rather than language a user would naturally say.

Suggestions

Add natural-language trigger terms a user might actually say (e.g., 'when the code sandbox is unavailable', 'Python execution fails', 'sandbox connection errors') alongside the technical conditions.

Frame the trigger around observable symptoms (timeout, connection failure) rather than only the internal provider name 'e2b'.

DimensionReasoningScore

Specificity

Names a concrete action ('run_shell with embedded Python') and domain (sandbox/e2b), but lists a single fallback action rather than multiple distinct actions, matching the score-2 anchor 'Names domain and some actions, but not comprehensive'.

2 / 3

Completeness

Clearly states what it does ('Fallback to run_shell with embedded Python') and an explicit when-trigger ('when execute_code_sandbox fails due to e2b unavailability'), answering both what and when; not capped at 2 because explicit trigger guidance is present.

3 / 3

Trigger Term Quality

Includes some natural keywords ('Python', 'sandbox'), but the primary triggers ('execute_code_sandbox', 'e2b unavailability') are internal technical jargon a user would not naturally say, and common natural variations are missing.

2 / 3

Distinctiveness Conflict Risk

Occupies a narrow, distinct niche (a specific fallback from a named sandbox tool to run_shell) with triggers unlikely to fire for unrelated skills.

3 / 3

Total

10

/

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.