CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-sandbox

Agent skill for sandbox - invoke with $agent-sandbox

41

4.65x
Quality

11%

Does it follow best practices?

Impact

93%

4.65x

Average score across 3 eval scenarios

SecuritybySnyk

Risky

Do not use without reviewing

Optimize this skill with Tessl

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

Quality

Content

22%

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

This skill reads more like a persona description and capability overview than an actionable skill file. While the MCP tool signatures are a useful reference, the surrounding content is padded with generic responsibilities, vague deployment steps, and quality standards that Claude already knows. The skill would benefit greatly from being restructured into a lean reference with concrete, chained workflow examples and explicit validation steps.

Suggestions

Remove the persona preamble, 'core responsibilities' list, and 'quality standards' section — these are generic concepts Claude already knows and waste tokens.

Add a concrete end-to-end workflow example showing chained tool calls (create → execute → check status → cleanup) with actual expected outputs and error handling.

Add explicit validation checkpoints: after sandbox creation verify status before executing code, after execution check output/errors before proceeding, and verify deletion succeeded.

Replace the abstract 'deployment approach' steps with a concrete decision tree or checklist tied to specific tool calls and parameters.

DimensionReasoningScore

Conciseness

The content is verbose with significant padding. It includes a persona preamble ('You are a Flow Nexus Sandbox Agent...'), lists of 'core responsibilities' that describe rather than instruct, a 'quality standards' section of generic best practices Claude already knows, and a closing paragraph of vague advice. Much of this could be eliminated.

1 / 3

Actionability

The MCP tool call examples are concrete and show actual function signatures with parameters, which is useful. However, they are illustrative rather than fully executable (e.g., placeholder sandbox_id values, no real workflow showing how to chain calls), and the deployment approach section is abstract guidance rather than concrete instructions.

2 / 3

Workflow Clarity

The 'deployment approach' is a high-level numbered list of abstract steps (Analyze Requirements, Select Template, etc.) with no validation checkpoints, no error recovery loops, and no concrete sequencing of tool calls. For sandbox lifecycle management involving resource creation and deletion, the lack of any verification or cleanup validation is a significant gap.

1 / 3

Progressive Disclosure

The content is organized into logical sections (toolkit, templates, deployment approach, quality standards), which provides some structure. However, there are no references to external files, and content like the full template descriptions and quality standards could be separated. For a skill with no bundle files, the inline organization is adequate but not optimal.

2 / 3

Total

6

/

12

Passed

Description

0%

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. It reads more like a label or placeholder than a functional description that Claude could use for skill selection.

Suggestions

Describe the specific actions this skill performs (e.g., 'Executes code in an isolated sandbox environment, runs tests, and manages temporary files').

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 and replace it with capability and context information that helps Claude distinguish this skill from others.

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 description 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 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 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/ruflo
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.