CtrlK
BlogDocsLog inGet started
Tessl Logo

code-execution-fallback-e81068

Fallback workflow for executing Python code when execute_code_sandbox fails repeatedly

67

Quality

80%

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/code-execution-fallback-e81068/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 executable code, a clear sequenced workflow, an explicit verification checkpoint, and a practical troubleshooting table. Its only real weakness is conciseness — the worked example and best-practices sections duplicate material already covered in the step instructions.

Suggestions

Trim or remove the 'Complete Example' since it re-covers Steps 2–4, or compress it to a minimal end-to-end snippet that adds something the steps don't.

Merge the 'Best Practices' list with the per-step 'Tips' to avoid restating the same guidance twice.

Fold the 'Alternative commands' bullets into Step 3 to reduce a standalone section that mostly elaborates one step.

DimensionReasoningScore

Conciseness

The body is mostly efficient and actionable but carries padding — the 'Complete Example' largely restates Steps 2–4, and 'Best Practices' repeats the earlier 'Tips' — so it could be tightened, matching 'Mostly efficient but includes some unnecessary explanation or could be tightened.'

2 / 3

Actionability

It provides fully executable, copy-paste-ready code for write_file and run_shell, concrete alternative commands, and a troubleshooting table with specific fixes, meeting 'Fully executable code/commands; specific examples; copy-paste ready.'

3 / 3

Workflow Clarity

The five steps are clearly sequenced and Step 4 is an explicit validation checkpoint (confirm exit code 0, inspect output), supported by a troubleshooting/error-recovery table, matching 'Clear sequence with explicit validation steps; feedback loops for error recovery.'

3 / 3

Progressive Disclosure

It is a single self-contained file with no nested references and cleanly organized into well-signaled sections (steps, example, troubleshooting, best practices), so navigation is easy even without external bundle files.

3 / 3

Total

11

/

12

Passed

Description

75%

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 states what the skill does and the specific failure condition that should trigger it, giving it a clear, low-conflict niche. Its main weakness is specificity — it names the domain and one implied action rather than listing multiple concrete operations, and it relies on a single technical trigger phrase.

Suggestions

List a couple of concrete fallback actions (e.g., 'write Python scripts to disk and run them via the shell') instead of the generic 'executing Python code'.

Add natural-language trigger variations users might say, such as 'Use when execute_code_sandbox keeps failing, times out, or returns unknown errors'.

Consider an explicit 'Use when...' clause to make the trigger phrasing match natural user requests more directly.

DimensionReasoningScore

Specificity

The description names the domain ('executing Python code') and the fallback action, but lists no multiple concrete actions — it stays at the level of 'Names domain and some actions, but not comprehensive' rather than enumerating several specific operations.

2 / 3

Completeness

It explicitly answers both what ('Fallback workflow for executing Python code') and when ('when execute_code_sandbox fails repeatedly'), meeting the anchor for clearly answering both what and when with an explicit trigger.

3 / 3

Trigger Term Quality

It uses the concrete tool name 'execute_code_sandbox fails repeatedly' as a trigger a user might echo, but offers only that one phrasing with no common variations, matching 'Some relevant keywords but missing common variations.'

2 / 3

Distinctiveness Conflict Risk

The niche is narrow and tied to a specific named tool's repeated failures, making it unlikely to trigger for unrelated skills, matching 'Clear niche with distinct triggers; unlikely to conflict.'

3 / 3

Total

10

/

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.