Implement Langfuse security best practices for API keys and data privacy.
Change code that has no tests, without breaking it — finding seams to substitute behavior, pinning current behavior with characterization…
Audit website legal compliance for Germany: General Data Protection Regulation (Datenschutz-Grundverordnung, DSGVO), Federal Data…
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons…
Write a load and performance testing plan for a service.
Automatically generate and verify loop invariants for algorithm correctness proofs
Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules…
This skill manages database testing by generating test data, wrapping tests in transactions, and validating database schemas.
This skill enables Claude to manage isolated test environments using Docker Compose, Testcontainers, and environment variables.
Design, build, extend and harden enterprise-grade AI agent systems: the harness (durable agent loop, event log, context hydration), tools…
Agent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.
Create mock MCP client for server testing with request/response simulation.
Build content moderation applications with Azure AI Content Safety SDK for Java.
Migrate test files from `as` type assertions to @total-typescript/shoehorn.
Prod Checklist for MindTickle.
Security Basics for MindTickle.
Use for authorized Android or iOS application reverse engineering and security testing, including APK or IPA analysis, runtime…
Keep secrets out of shipped mobile binaries and limit the damage of any client key.
Comprehensive mobile testing framework expertise
Demonstrate Insufficient Cryptography (OWASP Mobile Top 10 M10) during an authorized mobile assessment — showing that an app's use of…