fallback-python-shell

Use run_shell with Python heredoc when execute_code_sandbox or read_file fail

Quality

67%

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

80%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 highly actionable with comprehensive executable examples and clean organization. The principal gap is workflow clarity: file-processing and batch operations have no explicit validation or verify-then-proceed steps, which the rubric caps at 3.

Suggestions

Add an explicit validation checkpoint to the workflow (e.g., after reading, verify the file exists / parsed correctly before processing, and surface a clear error if not).

Include a brief "Verify output" step in the multi-step chaining example so the read-transform-write flow has a feedback loop.

Trim the explanatory sentence in Core Technique to rely on the code examples to demonstrate the technique.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight, copy-paste-ready code blocks and minimal preamble, though lines like "This bypasses sandbox execution issues while maintaining Python's full capabilities" are mild over-explanation that could be trimmed.	4 / 5
Actionability	Every section provides fully executable, complete heredoc snippets covering the common formats (text, JSON, CSV, Excel, PDF, Word) with copy-paste-ready code and concrete library usage.	5 / 5
Workflow Clarity	The read-then-process flow is sequenced via examples but lacks explicit validation or verification checkpoints for file/batch operations, and the rubric caps such skills at 3 when validation is missing.	3 / 5
Progressive Disclosure	As a simple single-file skill with no bundle files, the body is well-organized into clear sections (When to Use, Core Technique, Use Cases, Best Practices, Troubleshooting) that are easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

55%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 what to do (run_shell with a Python heredoc) and a specific triggering condition (tool failures), making it reasonably complete and distinct. Its main weakness is trigger-term quality: it relies on internal tool-error names rather than natural user language.

Suggestions

Reframe the trigger in natural user-facing terms (e.g., "Use when a file needs to be read or data processed and the sandbox tool returns an unknown error") so it matches phrases users actually say.

Broaden specificity by naming the supported formats concretely (e.g., "Read and process text, JSON, CSV, Excel, PDF, and Word files via a shell-run Python heredoc").

Add common synonyms and file extensions (".csv", ".xlsx", ".pdf", ".docx") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Use run_shell with Python heredoc" names the tool and technique concretely, and "process documents, analyze data, or read files" lists a few actions, but coverage is not comprehensive — lacks enumeration of specific formats or transforms.	3 / 5
Completeness	The what ("Use run_shell with Python heredoc") and the when ("when execute_code_sandbox or read_file fail") are both explicitly present, though the when is phrased as internal-tool conditions rather than user-facing trigger phrases.	4 / 5
Trigger Term Quality	Triggers are framed around internal tool failures ("when execute_code_sandbox or read_file fail") rather than natural user phrases, and remaining keywords ("documents", "data", "files") are generic, missing common variations users would actually say.	2 / 5
Distinctiveness Conflict Risk	Tying the skill to specific tool failure conditions ("execute_code_sandbox or read_file fail") gives it a clear niche with minimal overlap risk against other skills, though the broad "process documents / analyze data" tail leaves minor overlap.	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/fallback-python-shell/SKILL.md
Commit: 3827781

Reviewed: 6 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.