agent-user-tools

Agent skill for user-tools - invoke with $agent-user-tools

2.80x

Quality

Does it follow best practices?

Impact

84%

2.80x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-user-tools/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 provides essentially no useful information for skill selection. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is so generic it could conflict with any number of other skills.

Suggestions

Replace the entire description with specific concrete actions the skill performs (e.g., 'Manages user preferences, configures tool settings, lists available tools').

Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected.

Remove the invocation command ('$agent-user-tools') from the description, as it provides no value for skill selection, and instead describe the skill's unique niche to distinguish it from other skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for user-tools' is entirely vague and abstract, providing no indication of 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' with an invocation command, providing no functional or contextual information.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. 'user-tools' is a generic internal label, and '$agent-user-tools' is a technical invocation command, not a natural language trigger.	1 / 3
Distinctiveness Conflict Risk	The term 'user-tools' is extremely generic and could overlap with virtually any skill that involves tools or user interactions. There is nothing distinctive about this description.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is heavily padded with abstract capability descriptions and marketing-style language that provides little actionable value to Claude. While the MCP tool signatures are a useful concrete element, the majority of the content describes vague responsibilities and features without clear workflows, validation steps, or practical guidance. The skill would benefit enormously from being trimmed to its essential tool signatures and adding concrete step-by-step workflows for common operations.

Suggestions

Remove the 'Advanced features', 'User experience optimizations', and 'Quality standards' sections entirely—they describe abstract capabilities Claude doesn't need explained and add no actionable guidance.

Add concrete step-by-step workflows for common operations (e.g., 'Upload a file: 1. Determine bucket → 2. Call storage_upload → 3. Verify with storage_get_url → 4. Return URL to user') with explicit validation checkpoints.

Extract storage bucket details and tool reference into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with tool signatures and key workflows.

Replace the persona/role description paragraph with a brief one-line purpose statement—Claude doesn't need to be told it's an 'expert in user experience optimization'.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of abstract capabilities Claude already understands (e.g., 'AI-powered file categorization', 'proactive threat detection'). The 'Advanced features', 'User experience optimizations', and 'Quality standards' sections are padded with vague marketing-style descriptions that consume tokens without adding actionable value.	1 / 3
Actionability	The tool invocation examples are concrete and show actual function signatures with parameters, which is useful. However, much of the content is abstract descriptions of responsibilities rather than executable guidance—there are no complete workflows showing how to handle specific user requests end-to-end.	2 / 3
Workflow Clarity	There are no sequenced multi-step workflows with validation checkpoints. The numbered list under 'user support approach' describes categories of work, not actionable steps. Storage operations and profile updates lack any error handling, validation, or feedback loops despite involving potentially destructive operations.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no clear hierarchy. Multiple sections that could be separate references (storage bucket details, advanced features, UX optimizations) are all inlined, making the skill bloated and hard to navigate.	1 / 3
	Total	5 / 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: f547cec

Reviewed: 4 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.