fallback-python-shell

Use run_shell with Python heredoc when execute_code_sandbox or read_file fail

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/fallback-python-shell/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 body is highly actionable with complete executable examples for every supported file type and clean organization, but repeats the heredoc skeleton, keeps all content inline despite its length, and treats validation as optional rather than a workflow checkpoint.

Suggestions

Consolidate the repeated heredoc skeleton into one canonical pattern and reference it, dropping the duplicated boilerplate from each use-case block.

Promote error handling from an optional best practice into an explicit workflow step with a validate/retry feedback loop.

Move the per-file-type recipes into a references file (e.g., RECIPES.md) linked from the body to improve progressive disclosure at this length.

Dimension	Reasoning	Score
Conciseness	Code is direct and prose is minimal, but the basic heredoc skeleton repeats across nearly every use-case section and a separate 'Basic Pattern' duplicates it, adding tokens that could be tightened.	2 / 3
Actionability	Each file type has a fully executable, copy-paste-ready Python heredoc with concrete imports and print statements, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The single action is unambiguous and well-sequenced, but error handling/validation is shown as an optional best practice rather than an integrated checkpoint, and the rubric caps batch/file operations without validation feedback loops at 2.	2 / 3
Progressive Disclosure	Sections are well-organized and clearly headed, but the skill exceeds 50 lines with all per-file-type examples inline in one file rather than split into referenced bundles, fitting the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

52%

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 answers what and when with an explicit failure-trigger, but relies on internal tool names rather than natural user keywords and only names one core action, limiting specificity and trigger-term quality.

Suggestions

Reframe triggers in user-natural language (e.g., 'when code execution or file reading returns an unknown error') rather than internal tool identifiers.

Add a couple of concrete capability phrases (e.g., 'process documents, analyze data, read files') to raise specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Use run_shell with Python heredoc') but does not enumerate multiple specific capabilities, so it sits at the 'names domain and some actions' anchor rather than a comprehensive list.	2 / 3
Completeness	Explicitly states both what ('Use run_shell with Python heredoc') and when ('when execute_code_sandbox or read_file fail'), satisfying the explicit-trigger requirement for the top anchor.	3 / 3
Trigger Term Quality	Triggers are internal tool names ('execute_code_sandbox or read_file fail') — technical jargon a user would not naturally say, matching the 'technical jargon or overly generic' anchor rather than natural keywords.	1 / 3
Distinctiveness Conflict Risk	The tool-failure trigger is a distinct niche, but 'run shell with Python heredoc' is a broadly applicable technique that could overlap with general code/shell skills, so it is only somewhat specific.	2 / 3
	Total	8 / 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/fallback-python-shell/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.