with▌

Executes Atomic Red Team tests for MITRE ATT&CK technique validation using the atomic-operator Python framework. Loads test definitions from YAML atomics, runs attack simulations, and validates detection coverage. Use when testing SIEM detection rules, validating EDR coverage, or conducting purple team exercises.

Practical guidance for building effective AI applications using techniques from 60 product leaders and practitioners. \n \n Covers core prompting patterns: few-shot examples, decomposition for complex tasks, self-criticism, and context placement for cache efficiency \n Emphasizes architecture decisions over prompt tuning: context engineering, RAG data preparation, layered model supervision, and specialized models for specific tasks \n Provides evaluation frameworks: mandatory evals with binary P

Batch-share Google Drive folders with multiple collaborators at specified permission levels. \n \n Requires the gws-drive skill to execute folder sharing and permission management operations \n Supports role-based access control: assign editor (writer) or viewer (reader) permissions to individual collaborators \n Includes folder discovery by name and permission verification steps to confirm successful sharing \n Designed as a multi-step recipe for programmatic team collaboration workflows \n

Base Account is an ERC-4337 smart wallet providing universal sign-on, one-tap USDC payments, and multi-chain support (Base, Arbitrum, Optimism, Zora, Polygon, BNB, Avalanche, Lordchain, Ethereum Mainnet).

Use Read tool before announcing skill usage. The session-start hook does NOT read skills for you. Announcing without calling Read = lying.

Review Web Audio API code for sound synthesis best practices.

Give AI agents intelligent access to your Sanity content. Unlike embedding-only approaches, Agent Context is schema-aware—agents can reason over your content structure, query with real field values, follow references, and combine structural filters with semantic search.

symfony:tdd-with-phpunit

TRL provides post-training methods for aligning language models with human preferences.

Key benefits: