reliable-script-execution

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

Quality

69%

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

68%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 body is well-structured and actionable with concrete examples, but it lacks an explicit validation/verification checkpoint in its execution workflow, capping workflow clarity at 3 for a batch/risky operation. Removing the duplicated full example and adding a verify step would lift the top dimensions.

Suggestions

Insert an explicit validation checkpoint in the workflow, e.g. after execution check exit code/output and only clean up on success, to lift workflow_clarity past 3.

Drop or condense the 'Complete Example' since it restates the same three steps already shown, reducing conciseness padding.

Merge the 'Anti-Pattern' heredoc block into the 'Problem' section to avoid repeating the same snippet twice.

Dimension	Reasoning	Score
Conciseness	Efficient with no padding explaining concepts Claude already knows, though the 'Complete Example' and 'Anti-Pattern' sections duplicate the 3-step pattern and heredoc snippet already shown, costing the top score.	4 / 5
Actionability	Provides concrete, mostly copy-paste-ready write_file/run_shell invocations with real values and a full worked example, with only the minor gap that the tool-call syntax is illustrative rather than literal shell.	4 / 5
Workflow Clarity	The write-execute-clean-up sequence is clear, but running arbitrary scripts is a batch/risky operation with no explicit validation checkpoint in the workflow, which the rubric caps at 3.	3 / 5
Progressive Disclosure	A single self-contained file with clear section headers and no external references; well-organized for a simple single-purpose skill, with only minor duplication that keeps it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

53%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 clear and third-person with a concrete niche, but it lacks an explicit 'when to use' trigger clause and only names a single action, capping completeness and specificity at the midpoint. Adding a 'Use when...' clause with natural trigger phrases would substantially improve activation.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when running multi-line Python via shell, when heredoc fails, or when reliability matters more than brevity.'

Broaden trigger terms with natural user phrasing and synonyms (e.g. 'running Python from the shell', 'heredoc errors', 'unknown error').

List 2-3 concrete actions (e.g. write script to file, execute with timeout, clean up) to lift specificity from 3 to 4.

Dimension	Reasoning	Score
Specificity	Names the domain (Python script execution) and one concrete approach ('file-first approach instead of heredoc'), but does not list several specific actions, so it stops at anchor 3 rather than 4.	3 / 5
Completeness	Clearly states what it does but has no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3 even though the 'what' is clear.	3 / 5
Trigger Term Quality	Includes relevant keywords ('Python scripts', 'heredoc', 'file-first') but lacks the natural phrases and synonyms a user would say, matching anchor 3 rather than the comprehensive coverage of 4 or 5.	3 / 5
Distinctiveness Conflict Risk	The 'file-first approach instead of heredoc' framing carves a fairly distinct niche with only minor overlap risk against general coding skills, fitting anchor 4.	4 / 5
	Total	13 / 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/reliable-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.