agent-user-tools

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

2.80x

Quality

26%

Does it follow best practices?

Impact

84%

2.80x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-user-tools/SKILL.md

Quality

Content

36%Weight 40%Scale 1-5

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

The body is a serviceable agent prompt with a concrete MCP toolkit, but it is padded with buzzword sections, lacks real sequenced workflows with validation, and keeps all detail inline rather than pointing to reference files. Useful core is buried under persona and feature fluff.

Suggestions

Cut the 'Advanced features you leverage' and 'User experience optimizations you implement' sections — they are buzzword lists with no executable content and add tokens without guidance.

Add a short ordered workflow for common operations (e.g. update profile -> upload to private bucket -> verify URL) with an explicit validation step, especially for storage writes.

Provide concrete examples for the responsibilities currently only mentioned in prose (system monitoring, email verification, security operations), or move them to a reference file referenced from SKILL.md.

Dimension	Reasoning	Score
Conciseness	Substantial padding that Claude does not need: persona intro, 'Quality standards', 'Advanced features you leverage' (e.g. 'AI-powered file categorization'), and 'User experience optimizations you implement' are buzzword lists competing with the actually useful toolkit code.	2 / 5
Actionability	The toolkit block gives concrete, parameterised MCP calls (user_profile, storage_upload, realtime_subscribe, seraphina_chat), but several listed responsibilities (system monitoring, email verification, security) have no matching executable example, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The 'user support approach' numbered list is a priority ordering, not a sequenced workflow, and there are no validation checkpoints or feedback loops for operations like storage writes or profile updates.	2 / 5
Progressive Disclosure	Section headers provide structure and no bundle files exist to reference, but verbose API/feature lists that would benefit from living in separate reference files are inlined in a single ~90-line SKILL.md with no external pointers.	3 / 5
	Total	10 / 20 Passed

Description

17%Weight 40%Scale 1-5

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 is essentially a label plus an invocation command rather than a capability statement: it names no concrete actions, includes no natural trigger terms, and omits any 'use when' guidance. It reads as metadata, not a skill description.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Manage user profiles, upload and retrieve storage objects, configure real-time subscriptions, and consult Queen Seraphina for platform administration.'

Add an explicit trigger clause such as 'Use when the user asks to update their profile, manage files in storage buckets, set up realtime subscriptions, or perform Flow Nexus platform admin tasks.'

Replace the invocation-syntax phrase ('invoke with $agent-user-tools') with natural user-facing keywords (profile management, storage, subscriptions, platform admin).

Dimension	Reasoning	Score
Specificity	The phrase "Agent skill for user-tools" only names a vague domain and "invoke with $agent-user-tools" is a meta-invocation hint rather than a concrete capability; no real actions are described, placing it below the midpoint between fully vague (1) and naming a concrete action (3).	2 / 5
Completeness	It offers only a vague 'what' ("user-tools" is undefined) and provides no 'Use when...' trigger guidance, so it fails to answer when Claude should use it and caps below 3.	2 / 5
Trigger Term Quality	The only terms are the skill's own identifier ("user-tools", "$agent-user-tools") — technical invocation jargon rather than natural phrases a user would say, matching the 'no natural keywords' anchor.	1 / 5
Distinctiveness Conflict Risk	"user-tools" is extremely broad and would overlap with many platform/admin skills; the invocation syntax does not establish a distinct niche, matching 'very broad; high overlap risk'.	2 / 5
	Total	7 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-user-tools/SKILL.md
Commit: fa13ee4

Reviewed: about 5 hours 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.