CtrlK
BlogDocsLog inGet started
Tessl Logo

run-shell-python-file-io

Use run_shell with inline Python for reliable file I/O when execute_code_sandbox cannot access working directory files

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/run-shell-python-file-io/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 and well-structured for a simple skill, but it teaches basic Python I/O Claude already knows and its batch-processing workflow lacks explicit validation checkpoints.

Suggestions

Trim explanations of basic Python file I/O (e.g., the open()/os.getcwd() walkthrough) and the redundant 'Common Use Cases' list to improve conciseness.

Add a validation checkpoint to the multi-file batch example (e.g., verify processed file count matches input count, and handle read errors per file) to lift workflow_clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient but explains basic Python file I/O (open, os.getcwd, content.upper()) that Claude already knows and pads with redundant 'Common Use Cases' and repeat examples, matching the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It provides multiple fully executable, copy-paste-ready code blocks (python3 -c, here-doc to /tmp, batch glob) plus a troubleshooting table, matching the 'fully executable code; copy-paste ready' anchor.

3 / 3

Workflow Clarity

Steps are sequenced (Identify → Write inline → Complex logic → Verify) with a verification step, but the batch/multi-file example lacks validation checkpoints for partial failures, and the rubric caps batch workflows at 2 when validation is missing.

2 / 3

Progressive Disclosure

This is a simple skill with no bundle files and well-organized sections (When to Use, Pattern, Steps, Best Practices, Troubleshooting), which the rubric allows to score 3 per its simple-skills note.

3 / 3

Total

10

/

12

Passed

Description

60%

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 complete and distinctive, but its trigger terms are technical jargon rather than language users would naturally say, and its capability list is narrow rather than comprehensive.

Suggestions

Add natural user-facing trigger terms (e.g., 'Use when the sandbox can't see your files', 'file reading, file writing, reading workspace files') alongside the technical phrasing to improve trigger_term_quality.

List a few more concrete file operations the skill covers (read, write, transform, batch process) to lift specificity from 'some actions' to a fuller enumeration.

DimensionReasoningScore

Specificity

It names a concrete action ('Use run_shell with inline Python for reliable file I/O') and the domain, but it is not a comprehensive list of multiple specific actions, matching the 'names domain and some actions' anchor.

2 / 3

Completeness

It explicitly answers both what (run_shell with inline Python for file I/O) and when ('when execute_code_sandbox cannot access working directory files'), satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

The terms used ('run_shell', 'inline Python', 'execute_code_sandbox', 'file I/O') are technical jargon a user would not naturally say, matching the 'technical jargon or overly generic' anchor.

1 / 3

Distinctiveness Conflict Risk

It targets a specific niche (sandbox file-access workaround) with a distinct trigger unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.