CtrlK
BlogDocsLog inGet started
Tessl Logo

fallback-script-execution

Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail

52

Quality

56%

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/fallback-script-execution/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 an executable worked example and a clear, well-sequenced two-step workflow backed by error-recovery guidance. Its main weaknesses are mild verbosity in motivational bullets and a fully monolithic structure with no progressive disclosure into reference files.

Suggestions

Trim the 'This provides:' benefits bullet list and the 'Problematic Approach' example, since the recommended example already demonstrates the value concretely.

Move the full correlation_analysis.py worked example into a references/ file (e.g. EXAMPLES.md) and link to it from a brief inline skeleton, improving progressive disclosure for this >50-line skill.

Add an explicit validation checkpoint between the two steps, e.g. 'After writing, verify the file exists with run_shell ls -la before executing,' to make the workflow's quality gate explicit.

DimensionReasoningScore

Conciseness

It avoids explaining basic concepts and stays mostly efficient, but the benefits bullet list and the redundant 'Problematic Approach' example add padding that could be tightened.

2 / 3

Actionability

Provides a complete, executable Python example with imports and try/except plus copy-paste-ready write_file and run_shell commands, making the guidance concrete and directly usable.

3 / 3

Workflow Clarity

The two-step sequence is unambiguous, and an explicit error-recovery feedback loop (inspect errors, modify the persisted script, re-run) plus escalation verification commands give clear checkpoints for a simple skill.

3 / 3

Progressive Disclosure

Sections are well-organized, but the skill is entirely monolithic with no reference files, and the lengthy worked example could be split out for a >50-line skill rather than kept fully inline.

2 / 3

Total

10

/

12

Passed

Description

35%

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 includes an explicit trigger condition but leans on internal tool jargon rather than natural user terms, and the 'what' is abstract without naming the concrete write_file + run_shell mechanism. It is adequate but not sharply specific or user-friendly.

Suggestions

Replace internal tool jargon ('shell_agent', 'execute_code_sandbox') with natural trigger phrasing a user would say, e.g. 'Use when shell commands or sandboxed code keep failing and you need full stack traces.'

State the concrete mechanism in the 'what' clause, e.g. 'Writes a script to a file with write_file and runs it with run_shell to get full stack traces and re-runnable debugging.'

Add a short 'Use when...' sentence with common variations ('when debugging fails repeatedly', 'when you need to inspect a failing script') to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('script execution workflow', 'two-step') and the debugging purpose, but does not list the concrete actions (write_file then run_shell), staying abstract rather than comprehensive.

2 / 3

Completeness

An explicit 'when shell_agent and execute_code_sandbox consistently fail' clause is present, but the 'what' is generic ('two-step script execution workflow for debugging') without naming the actual mechanism, so it is not a clear, concrete both-what-and-when statement.

2 / 3

Trigger Term Quality

The only triggers are internal tool identifiers ('shell_agent', 'execute_code_sandbox') — technical jargon a user would not naturally say rather than natural language keywords.

1 / 3

Distinctiveness Conflict Risk

Tied to a fairly niche fallback scenario for specific tool failures, yet 'script execution workflow' is a broad concept that could still overlap with general scripting or debugging skills.

2 / 3

Total

7

/

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.