reliable-script-execution

Execute Python scripts reliably using file-first approach instead of heredoc

Quality

70%

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/reliable-script-execution/SKILL.md

Quality

Content

75%

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 concrete, executable examples and a clear three-step workflow, and it appropriately avoids explaining basics Claude already knows. Its main weakness is repetition of the same pattern across multiple sections, which adds length without adding information.

Suggestions

Consolidate the Solution, Complete Example, and Anti-Pattern sections to remove the repeated three-step restatement and cut length.

Promote the 'Check shell output for errors and retry' bullet into an explicit Step 2b validation checkpoint in the main workflow.

Trim or merge the 'When to Use This Pattern' and 'Best Practices' lists, since several points duplicate guidance already implied by the example.

Dimension	Reasoning	Score
Conciseness	It correctly assumes Claude knows Python/shell/JSON basics, but restates the same three-step file-first pattern across the Solution, Complete Example, and Anti-Pattern sections, so it could be tightened.	2 / 3
Actionability	Provides concrete, executable tool calls (write_file/run_shell with specific paths, content, and timeouts) and a complete working example that is copy-paste ready.	3 / 3
Workflow Clarity	The write-execute-cleanup sequence is clearly numbered and shown end-to-end, but error-recovery is only a best-practice bullet rather than an integrated validation checkpoint.	2.5 / 3
Progressive Disclosure	Single, cleanly sectioned SKILL.md with no nested references and no bundle files, but at roughly 100 lines it is somewhat long for a single-purpose pattern where 3 is reserved for tight, well-organized simple skills.	2.5 / 3
	Total	10 / 12 Passed

Description

66%

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 conveys a specific, concrete capability with a clear technical approach, but omits any 'Use when...' trigger guidance, which limits completeness and leaves invocation timing implicit. Trigger terms are relevant but could cover more natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when executing multi-line Python via shell or when heredoc fails with unknown error.'

Broaden trigger terms to natural phrasings a user would say, such as 'run Python', 'execute script', or 'shell command fails'.

List a couple of distinct concrete actions (e.g. write-to-file then execute, optional cleanup) to raise specificity toward multiple-action coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Execute Python scripts reliably') and a specific method ('file-first approach instead of heredoc'), but describes a single core action rather than listing multiple distinct capabilities.	2.5 / 3
Completeness	Clearly states what the skill does, but has no 'Use when...' clause or equivalent explicit trigger for when Claude should invoke it, which caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms a developer might say ('Python scripts', 'heredoc', 'file-first'), but lacks common natural phrasings like 'run Python' or 'execute a script'.	2.5 / 3
Distinctiveness Conflict Risk	The file-first-vs-heredoc niche is fairly distinct and unlikely to conflict broadly, though the absence of explicit trigger scenarios leaves some overlap risk.	2.5 / 3
	Total	9.5 / 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/reliable-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.