CtrlK
BlogDocsLog inGet started
Tessl Logo

python-execution-fallback-9d4989

Fallback method for executing Python when execute_code_sandbox fails with unknown errors

60

Quality

70%

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-9d4989/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable with executable, copy-paste-ready examples and a clear fallback workflow, supported by good section organization. It is held back by mild verbosity in the explanatory and guidelines sections.

Suggestions

Trim the 'Why This Works' section to one line or fold it into the guidelines, since heredoc and single-quote-EOF behavior are concepts Claude already knows.

Add an explicit validation step in the complete workflow (e.g. 'verify stdout is non-empty and matches expected output before proceeding').

Consolidate the redundant heredoc examples in 'Basic Syntax' and 'How to Call' to reduce overlap and tighten the file.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete examples, but the 'Why This Works' section and several Guidelines restate concepts (heredoc behavior, single-quoting EOF) Claude already knows, so it could be tightened past anchor 3.

3 / 5

Actionability

It provides multiple copy-paste-ready executable examples covering single-line, multi-line f-string, file-based, and full try/except fallback workflows, matching the anchor for fully executable guidance across common cases.

5 / 5

Workflow Clarity

The complete-workflow example gives a clear try -> fallback -> parse-stdout sequence with a troubleshooting table for recovery, but lacks an explicit 'verify the fallback produced valid output' checkpoint, keeping it below anchor 5.

4 / 5

Progressive Disclosure

The single self-contained file is well-organized with clear section headers and no nested references, but at ~80 lines with some redundancy across sections it has minor organization gaps rather than the cleanly split structure of anchor 5.

4 / 5

Total

16

/

20

Passed

Description

66%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 and distinctive with a clear embedded trigger clause, but it is let down by narrow trigger-term coverage and a 'what' that does not name the actual fallback mechanism (run_shell/heredoc).

Suggestions

Name the mechanism explicitly, e.g. 'Fallback method that runs Python via run_shell with a heredoc when execute_code_sandbox fails with unknown errors'.

Add natural trigger variations such as 'sandbox error', 'code execution failed', or 'execute_code_sandbox unavailable' to broaden keyword coverage.

Consider an explicit 'Use when...' phrasing and mention the .py-file alternative so the 'what' reads as comprehensive.

DimensionReasoningScore

Specificity

The description names the domain ('executing Python') and a concrete fallback action tied to a specific failure scenario, but lists only one action and omits the actual mechanism (run_shell/heredoc), so it is not comprehensive enough for a 4.

3 / 5

Completeness

It answers both 'what' (fallback method for executing Python) and 'when' (when execute_code_sandbox fails with unknown errors) with an explicit embedded trigger clause, but the 'what' is thin and does not name the method, keeping it below anchor 5.

4 / 5

Trigger Term Quality

It captures the relevant trigger phrases ('execute_code_sandbox fails', 'unknown errors') that match this scenario, but coverage is narrow with no synonyms or variation of the failure wording, so it falls short of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The trigger is highly specific to a single tool's failure mode, giving it a clear niche with minimal overlap risk against other skills.

5 / 5

Total

15

/

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.