agent-sandbox

Agent skill for sandbox - invoke with $agent-sandbox

4.65x

Quality

18%

Does it follow best practices?

Impact

93%

4.65x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-sandbox/SKILL.md

Quality

Discovery

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 is an extremely weak description that fails on every dimension. It provides no information about what the skill does, when it should be used, or what distinguishes it from other skills. It reads more like a label or placeholder than a functional description.

Suggestions

Describe the concrete actions this skill performs (e.g., 'Executes code in an isolated sandbox environment, manages sandbox sessions, and retrieves execution results').

Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user asks to run code safely, test scripts in isolation, or execute untrusted code').

Remove the invocation command ('invoke with $agent-sandbox') from the description and replace it with capability and context information that helps Claude distinguish this skill from others.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for sandbox' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill for sandbox' with an invocation command, providing no functional or contextual information.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'sandbox', which is generic and technical. There are no natural keywords a user would say when needing this skill. '$agent-sandbox' is an invocation command, not a trigger term.	1 / 3
Distinctiveness Conflict Risk	The term 'sandbox' is extremely generic and could overlap with any number of skills involving sandboxed environments, testing, or isolated execution. There is nothing distinctive about this description.	1 / 3
	Total	4 / 12 Passed

Implementation

37%

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

The skill provides a reasonable overview of E2B sandbox management with useful function signatures, but suffers from generic persona framing, lack of validation workflows, and verbose sections that state things Claude already knows. The most valuable part—the toolkit API calls—is diluted by surrounding boilerplate about responsibilities and quality standards that add little actionable information.

Suggestions

Remove the persona framing, 'core responsibilities' list, and 'quality standards' section—these are generic best practices Claude already knows. Focus the skill on the specific API signatures and usage patterns.

Add explicit validation checkpoints to the workflow: e.g., after sandbox_create, check sandbox_status before executing code; after sandbox_execute, verify output/exit code before proceeding.

Provide a complete end-to-end example showing sandbox creation → code execution → output verification → cleanup as a concrete workflow with error handling.

Add a feedback loop for error recovery: e.g., 'If sandbox_execute returns an error, inspect the output, fix the code, and re-execute before proceeding.'

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary padding like the persona framing ('You are a Flow Nexus Sandbox Agent, an expert in...'), the 'core responsibilities' list which largely restates obvious things, and the 'quality standards' section which lists generic best practices Claude already knows. The toolkit section is useful but the surrounding content could be significantly tightened.	2 / 3
Actionability	The toolkit section provides concrete function signatures with example parameters, which is useful. However, the code examples are illustrative rather than fully executable workflows—they show individual API calls but don't demonstrate complete end-to-end usage patterns or error handling. The deployment approach is a generic checklist rather than concrete guidance.	2 / 3
Workflow Clarity	The 'deployment approach' is a vague 6-step list with no validation checkpoints, no error recovery steps, and no feedback loops. For sandbox management which involves resource creation and cleanup (potentially destructive/costly operations), there are no explicit verification steps like checking sandbox status after creation or confirming successful cleanup.	1 / 3
Progressive Disclosure	The content is organized into logical sections (toolkit, deployment approach, templates, quality standards) which provides some structure. However, it's a monolithic file with no references to external documentation, and the template descriptions and quality standards could be separated or condensed. For a skill of this size (~70 lines of content), the organization is adequate but not optimal.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 01070ed

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.