CtrlK
BlogDocsLog inGet started
Tessl Logo

python-shell-fallback

Fallback to shell execution when sandbox fails for library-dependent Python code

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/python-shell-fallback/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 highly actionable with executable code and a clean section structure. Its main weaknesses are redundant heredoc examples that hurt conciseness and an implicit rather than inline validation checkpoint in the workflow.

Suggestions

Consolidate the three near-identical heredoc examples (Step 2, Step 3, and the PDF Example) into one canonical runnable example to reduce redundancy and tighten conciseness.

Promote the "Verify output" check into an explicit Step 4 validation checkpoint within the workflow rather than only listing it under Best Practices, to strengthen workflow_clarity.

DimensionReasoningScore

Conciseness

The body is mostly lean and code-forward without over-explaining basics, but the three near-identical heredoc blocks (Step 2, Step 3, and the PDF Example) are redundant and could be consolidated.

2 / 3

Actionability

It provides fully executable, copy-paste-ready heredoc code (a complete reportlab PDF example) plus concrete troubleshooting commands such as `which python3` and `pip3 list | grep package_name`.

3 / 3

Workflow Clarity

The Step 1→2→3 sequence is clear, but the verification checkpoint ("Verify output — Check stdout/stderr") lives in Best Practices rather than as an explicit step, and the troubleshooting feedback loop is separated from the main flow.

2 / 3

Progressive Disclosure

It offers a clear overview with well-organized sections and easy header navigation, no nested references, and no content that needs splitting for this self-contained single-purpose skill.

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 compact and clearly states both the action and an explicit trigger condition, giving it strong completeness and distinctiveness. It is held back by single-action specificity and somewhat technical trigger phrasing rather than natural user terms.

Suggestions

Add natural trigger terms a user would actually say (e.g., "ModuleNotFoundError", "import error", "can't find module") alongside the technical "sandbox fails" phrasing to improve trigger_term_quality.

List more concrete actions (e.g., "run Python via heredoc, generate PDFs, render charts") to raise specificity beyond a single action.

DimensionReasoningScore

Specificity

"Fallback to shell execution" names one concrete action and the domain (library-dependent Python), but lists only a single action rather than multiple specific concrete actions.

2 / 3

Completeness

It answers both what ("Fallback to shell execution") and when ("when sandbox fails for library-dependent Python code") with an explicit trigger, which is better than the score-2 example that omits the when.

3 / 3

Trigger Term Quality

It includes relevant keywords ("shell execution", "Python code") but the phrasing "sandbox fails for library-dependent Python code" is internal jargon, missing natural user terms like "ModuleNotFoundError" or "import error".

2 / 3

Distinctiveness Conflict Risk

The narrow trigger (sandbox failure for library-dependent Python) defines a clear niche that is 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.