agent-authentication
Agent skill for authentication - invoke with $agent-authentication
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-authentication56
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 96%
↑ 2.23xAgent success when using this skill
Validation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically underdeveloped, providing almost no useful information for skill selection. It names a broad domain ('authentication') without specifying any concrete capabilities, use cases, or trigger conditions. The inclusion of invocation syntax is irrelevant to helping Claude choose when to use this skill.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Generates OAuth tokens, manages API credentials, handles login flows, stores secrets securely').
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user mentions login, credentials, API keys, tokens, OAuth, or needs to authenticate with external services').
Remove the invocation syntax '$agent-authentication' as it doesn't help with skill selection and replace with capability-focused content.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions - 'authentication' is abstract and 'invoke with $agent-authentication' describes how to call it, not what it does. | 1 / 3 |
Completeness | Fails to answer both 'what does this do' (no specific capabilities listed) and 'when should Claude use it' (no 'Use when...' clause or trigger guidance). | 1 / 3 |
Trigger Term Quality | Contains only the technical term 'authentication' and a command syntax. Missing natural user terms like 'login', 'password', 'sign in', 'credentials', 'OAuth', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Authentication' is extremely generic and could conflict with any skill involving login, security, API keys, tokens, user management, or access control. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides good actionable MCP tool examples that are immediately usable, which is its primary strength. However, it suffers from verbose persona-style framing that wastes tokens, and the workflow section lacks concrete validation steps and error handling patterns critical for authentication operations. The 'Quality standards' section describes principles Claude already knows rather than providing specific implementation guidance.
Suggestions
Remove persona framing ('You are a Flow Nexus Authentication Agent...') and responsibility lists - start directly with the tool examples
Add concrete error handling examples showing how to detect and recover from failed authentication attempts
Replace 'Quality standards' prose with specific validation commands or checks (e.g., how to verify a session is valid)
Condense 'Common scenarios' into a brief list or remove entirely - Claude can infer these from the tool signatures
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains some unnecessary framing ('Your expertise lies in...', 'Your core responsibilities') and verbose descriptions of what Claude already understands about authentication concepts. The tool examples are efficient, but surrounding prose could be tightened. | 2 / 3 |
Actionability | Provides concrete, executable MCP tool calls with clear parameter examples. The JavaScript code blocks are copy-paste ready with realistic parameter values for registration, login, profile management, and password operations. | 3 / 3 |
Workflow Clarity | Lists a 5-step workflow approach but lacks explicit validation checkpoints and error recovery loops. 'Validate Results' is mentioned but no concrete validation commands or error handling patterns are provided. For authentication operations involving security, explicit feedback loops should be present. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections (toolkit, workflow, scenarios, standards), but everything is inline in one file. For a skill of this size (~70 lines), some content like 'Common scenarios' and 'Quality standards' could be condensed or the structure could be tighter. | 2 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.