CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-authentication

Agent skill for authentication - invoke with $agent-authentication

46

2.23x
Quality

17%

Does it follow best practices?

Impact

96%

2.23x

Average score across 3 eval scenarios

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

35%Scale 1-3

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

This skill provides a reasonable catalog of MCP tool signatures for Flow Nexus authentication, but is significantly weakened by verbose persona framing, generic workflow steps, and quality standards that restate things Claude already knows. The tool examples are the strongest element but lack error handling patterns and concrete multi-step workflow sequences that would make them truly actionable.

Suggestions

Remove the persona description, responsibility lists, and generic quality standards—these waste tokens on things Claude already knows. Focus the content on the MCP tool signatures and specific usage patterns.

Add concrete error handling examples: show what each MCP tool returns on success vs failure, and provide explicit if/then logic for common error states (e.g., duplicate email on registration, invalid credentials on login).

Replace the abstract 5-step workflow with concrete multi-step sequences for key flows (e.g., password reset: request token → validate token → update password → confirm), including validation checkpoints and error recovery steps.

Trim the 'common scenarios' list to only scenarios that require non-obvious tool combinations, and show the actual tool call sequences for each.

DimensionReasoningScore

Conciseness

The content is verbose and padded with unnecessary context. It explains Claude's role, responsibilities, and quality standards that Claude already knows (e.g., 'prioritize security, user experience,' 'handle errors gracefully,' 'follow GDPR best practices'). The persona framing ('You are a Flow Nexus Authentication Agent') and bullet-listed responsibilities add significant token overhead without actionable value.

1 / 3

Actionability

The MCP tool examples are concrete and show specific function signatures with parameters, which is useful. However, they are illustrative rather than fully executable workflows—there's no handling of return values, error states, or conditional logic. The 'common scenarios' and 'quality standards' sections describe rather than instruct.

2 / 3

Workflow Clarity

A 5-step workflow is listed (Assess, Execute, Validate, Provide Guidance, Security Check) but it's generic and abstract rather than specific to authentication operations. There are no explicit validation checkpoints, no error recovery feedback loops (e.g., what to do if login fails, if registration returns a duplicate email error), and no concrete sequencing for multi-step flows like password reset.

2 / 3

Progressive Disclosure

The content is organized into sections (toolkit, workflow, scenarios, quality standards) which provides some structure. However, it's a monolithic file with no references to external documentation, and content like the full list of common scenarios and quality standards could be trimmed or separated. For a skill with no bundle files, the inline content is somewhat bloated.

2 / 3

Total

7

/

12

Passed

Description

0%Scale 1-3

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 minimal description that provides almost no useful information for skill selection. It names a broad domain ('authentication') without specifying any concrete actions, use cases, or trigger conditions. It reads more like a command reference than a skill description.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Handles user login flows, generates JWT tokens, manages OAuth2 authorization, validates credentials.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to log in, authenticate, manage sessions, handle passwords, or configure OAuth providers.'

Remove the invocation syntax ('$agent-authentication') from the description and replace it with capability-focused language that helps Claude distinguish this skill from others.

DimensionReasoningScore

Specificity

The description says 'authentication' but provides no concrete actions. It doesn't describe what the skill actually does—no mention of login, token generation, OAuth flows, password management, or any specific capabilities.

1 / 3

Completeness

The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no 'Use when...' clause and no explanation of capabilities beyond the single word 'authentication.'

1 / 3

Trigger Term Quality

The only keyword is 'authentication,' which is broad and technical. It lacks natural user terms like 'login,' 'sign in,' 'password,' 'OAuth,' 'token,' 'credentials,' or 'session.' The '$agent-authentication' invocation syntax is not a natural user trigger.

1 / 3

Distinctiveness Conflict Risk

The term 'authentication' is extremely broad and could overlap with any security, login, identity, or access-control related skill. There is nothing to distinguish this from other potential auth-related skills.

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/claude-flow
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.