verified-script-execution

Fallback workflow for reliable file creation and verification when automated code execution fails

Quality

66%

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/verified-script-execution/SKILL.md

Quality

Content

65%

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 bash commands and a clear step sequence, but it over-explains basic shell mechanics Claude already knows and is monolithic with no progressive disclosure or error-recovery feedback loop.

Suggestions

Trim explanations of basic shell concepts (heredoc quoting, chmod, pwd) that Claude already knows; keep only the non-obvious escaping rules and the worked example.

Add an explicit verification failure feedback loop (e.g., 'If the output file is missing or wrong, inspect the error, fix the script, and re-run Step 4').

Consider splitting the complete worked example into a referenced script file so SKILL.md stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is actionable and organized but spends substantial space explaining shell concepts Claude already knows (heredoc quoting, chmod, pwd, nested delimiters), with redundant tips/pitfalls sections that pad token usage.	2 / 3
Actionability	Every step provides concrete, copy-paste-ready bash commands plus a full worked end-to-end example, all genuinely executable.	3 / 3
Workflow Clarity	The four-step sequence is clear with an explicit verification step and set -e fail-fast, but it lacks an explicit error-recovery feedback loop (verify -> fix -> re-verify) when verification fails.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a single monolithic ~150-line file with all content inline; sections are well-organized but nothing is split out into references.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 answers both what and when with an explicit trigger and a distinct fallback niche, but its action vocabulary is generic and its trigger term reads as internal jargon rather than natural user language.

Suggestions

List more specific concrete actions (e.g., 'create scripts via heredoc, make executable, verify output') instead of the generic 'file creation and verification'.

Reword the trigger in natural user terms a user would actually say (e.g., 'Use when the code sandbox or shell tool keeps failing to create files') rather than 'when automated code execution fails'.

Add concrete trigger keywords like 'sandbox failures', 'shell errors', 'files not being created' to improve natural-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	It names a concrete action ('file creation and verification') and a domain, but not multiple specific actions, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It states what it does ('reliable file creation and verification') and gives an explicit when clause ('when automated code execution fails'), satisfying both the what and the when.	3 / 3
Trigger Term Quality	'when automated code execution fails' is a relevant situational trigger but uses internal/system jargon rather than natural user phrasings, so it falls short of full trigger coverage.	2 / 3
Distinctiveness Conflict Risk	The fallback-when-execution-fails framing is a recognizable niche, but 'file creation and verification' is a generic action domain that could overlap with many file/document skills.	2 / 3
	Total	9 / 12 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/verified-script-execution/SKILL.md
Commit: c5a9c4b

Reviewed: 2 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.