CtrlK
BlogDocsLog inGet started
Tessl Logo

safe-script-execution

Fallback workflow for code execution when automated tools fail, using shell heredoc with verification

59

Quality

67%

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

Quality

Content

85%

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 a well-sequenced, verification-backed workflow; the only weakness is redundancy across the steps, anti-patterns, and checklist that slightly inflates the token budget.

Suggestions

Collapse the Troubleshooting Checklist into Step 5 (Error Handling) to remove overlap with the step instructions and the Anti-Patterns list.

Trim the Anti-Patterns to only items not already implied by the step guidance (e.g. drop 'Don't assume working directory' since Step 1 already mandates pwd).

DimensionReasoningScore

Conciseness

The body is mostly lean procedural guidance, but the Anti-Patterns, Troubleshooting Checklist, and worked PDF example substantially restate the step instructions, so it could be tightened without losing clarity.

2 / 3

Actionability

Provides fully executable commands (pwd, ls, chmod, file, pdfinfo, py_compile, df) plus a complete, copy-paste-ready worked PDF-generation example, matching the level-3 anchor.

3 / 3

Workflow Clarity

A clear 5-step sequence includes an explicit verification checkpoint (Step 4) and an error-recovery feedback loop (Step 5) backed by a checklist, satisfying the level-3 anchor.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single self-contained procedural workflow organized into clear sections (When to Use, Steps, Example, Anti-Patterns, Checklist), so well-organized inline content earns the top score.

3 / 3

Total

11

/

12

Passed

Description

50%

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 concise and names a concrete mechanism, but it lacks an explicit trigger clause and natural keyword coverage, leaving every dimension at the mid-level anchor.

Suggestions

Add an explicit 'Use when…' clause stating natural triggers, e.g. 'Use when execute_code_sandbox or shell_agent repeatedly fail to produce expected outputs.'

Broaden natural trigger terms (e.g. 'script execution fails', 'tool errors', 'run code manually') so users would phrase the need similarly.

Sharpen distinctiveness by foregrounding the fallback-diagnostic niche rather than the generic 'code execution' framing.

DimensionReasoningScore

Specificity

Names the domain ("code execution") and a concrete mechanism ("shell heredoc with verification") but describes a single fallback workflow rather than listing multiple distinct actions, matching the level-2 anchor.

2 / 3

Completeness

Answers "what" (fallback workflow using heredoc with verification) and only implies "when" via the embedded clause "when automated tools fail"; with no explicit "Use when…" trigger clause, completeness is capped at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Includes some relevant terms a user might say ("code execution", "when automated tools fail") but leans on technical jargon ("shell heredoc") and lacks common natural variations, so it does not reach full coverage.

2 / 3

Distinctiveness Conflict Risk

The fallback-when-tools-fail niche is somewhat specific, but "code execution" broadly could overlap with general execution skills, so it is not yet a clearly distinct trigger set.

2 / 3

Total

8

/

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.