agent-authentication

Agent skill for authentication - invoke with $agent-authentication

2.23x

Quality

57%

Does it follow best practices?

Impact

96%

2.23x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

65%

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

The content is actionable with concrete MCP tool examples and a sequenced workflow, but it is diluted by marketing prose, lacks concrete validation checkpoints, and keeps everything in one inline file instead of leveraging progressive disclosure. A stray second YAML frontmatter block inside the body is also a structural anomaly.

Suggestions

Trim marketing language ('seamless', 'comprehensive', 'expertise lies in') and the generic closing paragraph to improve token efficiency.

Make the workflow's validation step concrete: specify what to check in tool responses (e.g., session token presence, error codes) and an explicit retry/fix loop.

Move the large toolkit code block and common-scenarios catalog into a references file (e.g., TOOLKIT.md) and link to it, and remove the duplicate YAML frontmatter block from the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool listings, but it carries marketing fluff ('seamless user onboarding', 'comprehensive account management', 'expertise lies in') and generic closing prose that could be trimmed; not padded enough for a 1, not lean enough for a 3.	2 / 3
Actionability	The toolkit provides concrete, parameterized MCP calls (user_register, user_login, user_profile, user_reset_password, etc.) that are copy-paste ready and specific, matching the 'fully executable code' anchor.	3 / 3
Workflow Clarity	A five-step workflow with an explicit 'Validate Results' step is present, but validation is described abstractly ('handle any error states') with no concrete checkpoint or error-recovery feedback loop, so it sits at 2 rather than 3.	2 / 3
Progressive Disclosure	The skill is a single self-contained file with well-organized sections and no nested references, but at ~75 lines (above the 50-line simple-skill threshold) the inline toolkit and scenario catalog could be split into reference files rather than kept monolithic.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 frontmatter description identifies the authentication domain and an invocation path but is vague on capabilities and lacks explicit 'when to use' triggers. The much richer second description block is buried in the body rather than the frontmatter.

Suggestions

Replace the frontmatter description with the concrete capability list (login, registration, session management, profile/password operations) so specificity and completeness improve.

Add an explicit 'Use when...' clause naming natural triggers like login, sign in, register, password reset, and session management.

Move the better description ('Flow Nexus authentication and user management specialist...') into the actual frontmatter instead of leaving a generic placeholder.

Dimension	Reasoning	Score
Specificity	The description names a clear domain ("authentication") but lists no concrete actions, only an invocation hint; it is more focused than 'Helps with documents' yet lacks the multiple specific actions needed for a 3.	2 / 3
Completeness	It weakly answers 'what' (an agent skill for authentication) but provides no 'Use when...' trigger guidance beyond how to invoke, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes the natural term 'authentication' and the invocation cue '$agent-authentication', but misses common variations users would say such as 'login', 'sign in', 'register', or 'password reset'.	2 / 3
Distinctiveness Conflict Risk	Authentication is a reasonably distinct niche, but the description is generic enough ('Agent skill for authentication') that it could overlap with other auth-related skills rather than carving a clear, conflict-free trigger space.	2 / 3
	Total	8 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-authentication/SKILL.md
Commit: 26c35b5

Reviewed: about 6 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.