agent-authentication
Agent skill for authentication - invoke with $agent-authentication
42
11%
Does it follow best practices?
Impact
96%
2.23xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-authentication/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically underdeveloped. It provides essentially no information about what the skill does beyond the single word 'authentication', includes no trigger guidance, and lacks any concrete actions or use cases. The inclusion of an invocation command ('$agent-authentication') does not help Claude decide when to select this skill.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Manages user authentication flows including login, token refresh, OAuth2 authorization, and session management.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to log in, authenticate, manage credentials, handle OAuth tokens, or troubleshoot sign-in issues.'
Remove the invocation instruction ('invoke with $agent-authentication') from the description and replace it with capability and trigger information that helps Claude select the right skill.
| Dimension | Reasoning | Score |
|---|---|---|
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, credential management, or any specific capabilities. | 1 / 3 |
Completeness | The description barely addresses 'what' (just says 'authentication') and completely lacks any 'when' guidance. There is no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'authentication', which is broad and technical. Missing natural terms users might say like 'login', 'sign in', 'password', 'credentials', 'OAuth', 'token', 'SSO', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Authentication' is extremely broad and could overlap with many security, login, identity, or access-control related skills. There's nothing to distinguish this skill's specific niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with persona framing, generic responsibilities, and quality platitudes that Claude already knows, significantly reducing token efficiency. While the MCP tool signatures provide some concrete value, the workflow guidance is abstract and lacks the validation checkpoints and error-handling feedback loops critical for authentication operations. The skill would benefit greatly from stripping the persona/responsibility sections and replacing them with concrete, executable workflows for each authentication scenario.
Suggestions
Remove the persona framing, 'core responsibilities,' 'quality standards,' and generic guidance paragraphs—these waste tokens on things Claude already knows.
Replace the abstract 5-step workflow with concrete, scenario-specific workflows (e.g., registration flow, password reset flow) that include explicit validation of return values and error handling branches.
Add concrete examples showing how to handle MCP tool return values, error states, and conditional branching (e.g., what to do when login fails, how to verify email confirmation status).
Convert the 'common scenarios' list into actionable step-by-step procedures with specific MCP tool calls chained together, including validation checkpoints between steps.
| Dimension | Reasoning | Score |
|---|---|---|
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 actual 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 | The 5-step 'workflow approach' is generic and abstract ('Assess Requirements,' 'Execute Flow,' 'Validate Results') without concrete validation checkpoints, error handling steps, or feedback loops. For authentication operations—which involve security-sensitive state changes—there are no explicit validation or retry mechanisms described. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections (toolkit, workflow, scenarios, standards), which provides some structure. However, it's a monolithic file with no references to external documentation, and several sections (common scenarios, quality standards) could be trimmed or externalized. No bundle files exist to reference. | 2 / 3 |
Total | 6 / 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.
- Repository
- ruvnet/claude-flow
- Commit
9d4a9ea
- 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.