CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-sandbox

Agent skill for sandbox - invoke with $agent-sandbox

45

4.65x
Quality

17%

Does it follow best practices?

Impact

93%

4.65x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-sandbox/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a useful catalog of MCP tool invocations for E2B sandbox management but is wrapped in excessive persona framing and vague quality guidance that wastes tokens. The tool examples are the strongest element, though they lack error handling patterns and validation steps. The workflow is sequential but missing critical checkpoints for destructive operations like sandbox deletion.

Suggestions

Remove the persona framing ('You are a Flow Nexus Sandbox Agent...') and quality standards platitudes; replace with a concise header and jump straight to tool usage patterns.

Add explicit validation steps to the workflow: e.g., check sandbox_status after creation before executing code, verify execution output before cleanup.

Include concrete error handling examples showing what to do when sandbox_create fails or sandbox_execute returns errors, with specific error codes or messages to watch for.

Trim the template list to a simple table or inline reference rather than a bulleted list with obvious descriptions (e.g., 'Node.js development with npm ecosystem' adds nothing Claude doesn't know).

DimensionReasoningScore

Conciseness

The content is verbose with significant padding. It explains Claude's role and responsibilities in a persona-style format ('You are a Flow Nexus Sandbox Agent'), lists obvious quality standards ('implement proper error handling'), and includes vague guidance like 'always consider security isolation, resource efficiency' that Claude already knows. The template list and quality standards sections add little actionable value.

1 / 3

Actionability

The JavaScript code examples showing MCP tool invocations are concrete and useful, providing specific function signatures with parameter examples. However, the code is illustrative rather than fully executable (e.g., placeholder values like 'sandbox_id'), and the deployment approach section is abstract guidance rather than concrete instructions. Missing details on error handling patterns and actual return value structures.

2 / 3

Workflow Clarity

The 6-step deployment approach provides a reasonable sequence, but lacks validation checkpoints and error recovery steps. For sandbox management involving resource creation and deletion (destructive operations), there are no explicit verification steps (e.g., confirm sandbox is running before executing code, verify cleanup succeeded). No feedback loops for handling execution failures.

2 / 3

Progressive Disclosure

The content is a monolithic single file with no references to supporting documentation. While the content is organized with headers and sections, the template descriptions, quality standards, and tool reference could be split into separate files. For a skill with no bundle files, the inline content is reasonably structured but could benefit from better separation of reference material from workflow guidance.

2 / 3

Total

7

/

12

Passed

Description

0%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what distinguishes it from other skills. Claude would have no basis for selecting this skill appropriately from a list of available skills.

Suggestions

Replace the entire description with concrete actions the skill performs (e.g., 'Executes code in an isolated sandbox environment, runs tests, and validates outputs').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to run code safely, test scripts, or execute commands in an isolated environment').

Remove the invocation instruction ('invoke with $agent-sandbox') from the description, as it is not useful for skill selection and wastes space that should describe capabilities.

DimensionReasoningScore

Specificity

The description provides no concrete actions whatsoever. 'Agent skill for sandbox' is entirely vague and abstract, giving no indication of what the skill actually does.

1 / 3

Completeness

Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.

1 / 3

Trigger Term Quality

The only potentially relevant term is 'sandbox,' which is overly generic and not a natural keyword a user would say when needing a specific capability. '$agent-sandbox' is an invocation command, not a trigger term.

1 / 3

Distinctiveness Conflict Risk

The description is so generic that it could conflict with virtually any agent or sandbox-related skill. There are no distinct triggers or domain-specific terms to differentiate it.

1 / 3

Total

4

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.