safe-script-execution

Fallback workflow for code execution when automated tools fail, using shell heredoc with verification

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/safe-script-execution/SKILL.md

Quality

Content

81%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 a well-structured, actionable fallback workflow with explicit verification and an error-recovery loop, scoring strongly on workflow clarity and actionability. Minor tightening of the anti-patterns/checklist redundancy and replacing placeholder paths would push it higher.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and minimal concept teaching, though the anti-patterns and troubleshooting checklist restate step content and could be trimmed.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready commands and a full worked PDF example; held back from 5 by placeholder paths (/full/path/to/) in the generic steps.	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit verification checkpoints (directory, output), an error-handling feedback loop (Step 5), and a troubleshooting checklist for error recovery.	5 / 5
Progressive Disclosure	Well-organized into clear sections (When to Use, Steps, Example, Anti-Patterns, Checklist) with no bundle files needed; slightly long for a single file but appropriately structured.	4 / 5
	Total	17 / 20 Passed

Description

62%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 cleanly covers what and when in one line and targets a distinct fallback niche, but it is terse and leans on technical phrasing over natural user keywords. More concrete actions and user-friendly trigger terms would lift specificity and trigger quality.

Suggestions

Add 1-2 more concrete actions (e.g., 'create, run, and verify scripts') to raise specificity toward a comprehensive action list.

Add natural trigger phrasing a user would say, such as 'Use when code execution tools keep failing or producing no output'.

Include synonyms or related terms (e.g., 'sandbox', 'shell', 'script execution') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('code execution') and 1-2 concrete mechanisms ('shell heredoc', 'verification'), matching the anchor for limited concrete actions, but lacks a fuller enumeration of actions.	3 / 5
Completeness	Explicitly states both what (fallback code-execution workflow via heredoc with verification) and when (when automated tools fail), though the 'when' clause is brief rather than fully spelled out.	4 / 5
Trigger Term Quality	Includes a genuine scenario trigger ('when automated tools fail') plus technical terms ('heredoc', 'verification'), but misses common user-phrased synonyms and stays partly jargon-heavy.	3 / 5
Distinctiveness Conflict Risk	The 'fallback when automated tools fail' framing carves a mostly distinct niche with only minor overlap risk against general code-execution skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUDS/OpenSpace
Path: benchmarks/gdpval/skills/safe-script-execution/SKILL.md
Commit: 3827781

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.