byjoslat· 46 skills
Scans a MAF 1.3.0 codebase for known anti-patterns AFTER migration is complete. Prefer the MCP tool MafScanAntiPatterns for one-shot scans; this skill is for understanding the rule taxonomy or contributing new anti-pattern rules. Detects insecure credential usage (DefaultAzureCredential, hard-coded keys), unsafe defaults (EnableSensitiveData=true in non-dev), thread-unsafe state in AIContextProvider, missing observability (UseOpenTelemetry not wired), and missing identity (ManagedIdentityCredential preferred over secret-based auth). Counterpart to migration tooling: this is steady-state best-practice review.
$npx -y skills add joslat/maf-doctor --skill maf-anti-pattern-scannerInstalls into the current project.
Run `npx skills use "https://github.com/joslat/maf-doctor" --skill "joslat/maf-doctor/maf-anti-pattern-scanner"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/joslat/maf-doctor" that are relevant to the current task. Run `npx skills add "https://github.com/joslat/maf-doctor"` and select the relevant skills, then follow their instructions.