CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-user-tools

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

60

2.80x
Quality

43%

Does it follow best practices?

Impact

84%

2.80x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 skill reads as a persona prompt rather than an operational guide: one genuinely useful toolkit snippet is surrounded by padded marketing-style bullet lists and vague quality standards. It lacks any concrete workflow, error handling, or validation steps, and contains a duplicated frontmatter block plus corrupted path strings in the code examples.

Suggestions

Cut the "Advanced features you leverage" and "User experience optimizations you implement" sections (and similar buzzword lists) or replace them with concrete guidance, e.g., actual bucket policies, subscription filter syntax, and cleanup commands.

Turn "Your user support approach" into a real sequenced workflow with validation checkpoints (e.g., verify storage upload succeeded, confirm subscription active, unsubscribe on completion) for the common tasks: profile update, file upload/share, and subscription setup.

Fix the corrupted delimiters in the toolkit examples ("projects$config.json" → "projects/config.json", "application$json" → "application/json") and remove the duplicated YAML frontmatter block inside the body; consider moving the full tool listing into a references/ file.

DimensionReasoningScore

Conciseness

The body is noticeably padded: sections like "Advanced features you leverage" ("Intelligent File Organization", "Advanced Analytics", "Integration Hub") and "User experience optimizations you implement" ("Personalized Dashboard", "Smart Notifications") are buzzword lists with no operational content, and a duplicated YAML frontmatter block sits inside the body. It avoids explaining concepts Claude already knows, so it is not at the severely-verbose level 1.

2 / 5

Actionability

The user-tools toolkit code block gives concrete, mostly complete MCP tool signatures with parameters, but values are placeholders ("user_id": "user_id") and paths/content-types appear corrupted ("projects$config.json", "application$json" instead of forward slashes), so guidance is concrete yet not reliably executable. Everything outside the toolkit block is abstract direction like "Implement efficient file organization and access patterns".

3 / 5

Workflow Clarity

"Your user support approach" lists six numbered items, but each is a bolded label plus a vague phrase with no actual sequence, no concrete steps, and no validation checkpoints (e.g., verifying an upload succeeded or cleaning up a subscription). This matches a rough list with many gaps and absent validation rather than a defined workflow.

2 / 5

Progressive Disclosure

The body has clear section headers and is a self-contained ~90-line document with no bundle files (references/, scripts/, assets/ are absent), so no broken or nested references exist. However, content that could live in a separate file (the full toolkit API listing) is inlined and the sections could be better organized for navigation.

3 / 5

Total

10

/

20

Passed

Description

50%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 a competent one-sentence summary of scope with a clear "what" and several named capability areas, but it contains no trigger guidance and its terms are category labels rather than natural user phrases. It reads as a persona tagline rather than a skill description built for invocation.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user wants to manage their flow-nexus profile, upload or share stored files, set up realtime subscriptions, or check platform status."

Replace category labels with concrete actions and natural synonyms: "Updates profile fields (name, bio, GitHub username), uploads files to private/public/shared/temp buckets, generates expiring share URLs, and subscribes to realtime table events."

Narrow the generic tail "platform administration" to the specific admin operations offered, reducing overlap with general system-administration skills.

DimensionReasoningScore

Specificity

"Handles profile management, storage operations, real-time subscriptions, and platform administration" names four capability areas, but each is a category rather than a concrete action — no verbs like "upload files to buckets", "update profile fields", or "subscribe to table events". It sits between naming the domain with minimal actions (2) and listing several specific actions (4).

3 / 5

Completeness

The "what" is reasonably clear (user management and system utilities across profiles, storage, subscriptions, administration), but there is no "Use when..." clause or any equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Terms like "profile management", "storage", "subscriptions", and "platform administration" are relevant to the domain, but the natural phrases a user would actually say ("update my profile", "upload a file", "set up notifications", "get a shareable file URL") and their synonyms are missing. "Platform administration" in particular is generic jargon rather than a user-spoken trigger.

3 / 5

Distinctiveness Conflict Risk

The named sub-domains give it some specificity, but "system utilities specialist" and "platform administration" are broad enough to overlap with general admin, storage, or notification skills. It could still be selected for the wrong skill in a mixed skill set.

3 / 5

Total

12

/

20

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.

Validation — 16 / 16 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.