agentlint
Audit any website for AI/agent-friendliness using AgentLint. Run `npx @cjavdev/agent-lint` with a URL to scan a site across 17 rules in 5 categories (transport, structure, tokens, discoverability, agent), get a 0-100 AgentScore with letter grade, and receive a prioritized remediation plan. Use this skill when: auditing a site for AI readiness, checking if a site has llms.txt or markdown support, improving a website's agent-friendliness score, fixing AgentLint violations, or understanding what makes a site AI-friendly. Trigger phrases: 'run agentlint', 'audit site for AI', 'check agent-friendliness', 'agentlint scan', 'AI-friendly audit', 'check llms.txt', 'agent readiness'.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 excellent skill description that hits all the marks. It provides specific concrete actions, comprehensive trigger terms, explicit 'Use when' guidance with multiple scenarios, and is highly distinctive with its focus on the AgentLint tool and AI-friendliness auditing domain. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Run npx @cjavdev/agent-lint with a URL', 'scan a site across 17 rules in 5 categories', 'get a 0-100 AgentScore with letter grade', 'receive a prioritized remediation plan'. Very detailed about what the tool does. | 3 / 3 |
Completeness | Clearly answers both what (audit websites using AgentLint, scan across rules, get scores and remediation plans) AND when with explicit 'Use this skill when:' clause listing 5 specific scenarios plus dedicated trigger phrases section. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'run agentlint', 'audit site for AI', 'check agent-friendliness', 'AI-friendly audit', 'check llms.txt', 'agent readiness'. Includes both technical terms and natural language variations users would say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool name 'AgentLint', unique domain of AI/agent-friendliness auditing, specific technical markers like 'llms.txt', and the exact command to run. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates best practices across all dimensions. It provides actionable CLI commands, comprehensive rule references in scannable tables, clear prioritization logic for remediation, and appropriately delegates detailed implementation examples to a reference file. The content respects Claude's intelligence while providing all necessary context for effective website auditing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting information in tables and structured lists without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable CLI commands, concrete flag options, specific rule IDs with point values, and a clear configuration JSON example. The workflow steps are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 3-step workflow (Run CLI → Parse Results → Present Remediation) with explicit guidance on what to extract and how to prioritize. Exit codes provide validation feedback for error handling. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections for quick reference, appropriately defers detailed remediation code examples to `references/remediation-guide.md` with a single-level reference. Tables make scanning efficient. | 3 / 3 |
Total | 12 / 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
- cjavdev/agent-lint
- Commit
04dcd58
- 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.