shell-python-heredoc

Execute complex Python code via run_shell heredoc when execute_code_sandbox fails

Quality

68%

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/shell-python-heredoc/SKILL.md

Quality

Content

75%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 guide with executable examples and clear usage criteria for a simple fallback pattern. The main gaps are an undemonstrated stderr-capture rule, no explicit retry/validate loop for the fallback, and a See Also section that is prose rather than linked references.

Suggestions

Show a concrete example capturing stderr/stdout to back the stated 'Capture output' rule and lift actionability.

Add an explicit fallback feedback loop (e.g., if the heredoc also fails, check indentation/EOF, then fall back to writing a .py file) to strengthen workflow clarity.

Convert the 'See Also' prose into real cross-references or split the two long examples into an examples/ file to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with direct executable examples and no explanation of known concepts, matching anchor 4; minor trimmable commentary in the Advantages/Disadvantages sections keeps it from a 5.	4 / 5
Actionability	Two complete, copy-paste-ready heredoc examples plus a basic pattern and concrete syntax rules provide mostly executable guidance (anchor 4); the stated stdout/stderr capture rule is never demonstrated, leaving a minor gap versus anchor 5.	4 / 5
Workflow Clarity	Clear trigger criteria, a defined execution pattern, and a troubleshooting table give a clear sequence with most checkpoints present (anchor 4); no explicit validate/retry feedback loop for the fallback case itself prevents a 5.	4 / 5
Progressive Disclosure	Well-organized into clear self-contained sections with no nested references (anchor 4); at ~95 lines with two full inline code examples it exceeds the simple-skill threshold and could split examples into a separate file, and the 'See Also' items are prose rather than real links, keeping it from a 5.	4 / 5
	Total	16 / 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 clearly states both what the skill does and a concrete trigger condition, with a distinct niche tied to sandbox failure. It is held back from top scores by narrow trigger-term coverage and limited enumeration of specific actions.

Suggestions

Broaden trigger terms with natural user phrasings and synonyms (e.g., 'Python script fails to run', 'sandbox error', 'multi-line Python in shell').

List a couple more specific concrete actions or use cases (e.g., 'run scripts with heavy imports like pandas or ReportLab') to lift specificity.

Add a 'Use when...' clause spelling out multiple trigger scenarios for stronger completeness.

Dimension	Reasoning	Score
Specificity	Names the concrete mechanism ('run_shell heredoc') and action ('Execute complex Python code') with a trigger condition, matching anchor 3's '1-2 concrete actions'; it does not enumerate multiple specific actions required for a 4.	3 / 5
Completeness	Explicitly answers both 'what' ('Execute complex Python code via run_shell heredoc') and 'when' ('when execute_code_sandbox fails'), matching anchor 4; it is not 5 because the 'when' is a single condition without varied concrete trigger phrases.	4 / 5
Trigger Term Quality	Relevant keywords ('execute_code_sandbox fails', 'Python code') are present but lack common synonyms or file extensions, and 'heredoc' is jargon, fitting anchor 3 rather than the broader coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific failure condition ('execute_code_sandbox fails') giving a distinct niche with minor overlap risk, fitting anchor 4; it lacks the rich synonym-filled triggers of anchor 5 and is more distinct than the broad anchor 3.	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/shell-python-heredoc/SKILL.md
Commit: 3827781

Reviewed: 25 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.