Segurança

Reproduces the full prefill sensitivity analysis pipeline for reward hacking indicators. Use when evaluating how susceptible model checkpoints are to exploit-eliciting prefills, computing token-based trajectories, or comparing logprob vs token-count as predictors of exploitability.

GitHub PR utilities for code review workflows

Türkçe metin yazımı, düzeltme ve üslup yardımı. Resmi/gayriresmi ton ayarı, sen/siz seçimi, Türkçe dilbilgisi kontrolü ve doğal Türkçe ifadeler için kullan. Türkçe yazarken, Türkçe metin düzeltirken veya Türkçe içerik üretirken aktive et.

Trade and interact with Uniswap in Python using Ape and the uniswap-sdk package.

Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via tmux wrapper (sub-5ms latency) or file-based team inbox for async workflows

SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.

Use when the user asks for a roadmap, timeline, phased plan, or execution sequence.

Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.

Container vulnerability scanning and dependency risk assessment using Grype with CVSS severity ratings, EPSS exploit probability, and CISA KEV indicators. Use when: (1) Scanning container images and filesystems for known vulnerabilities, (2) Integrating vulnerability scanning into CI/CD pipelines with severity thresholds, (3) Analyzing SBOMs (Syft, SPDX, CycloneDX) for security risks, (4) Prioriti

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, modern APIs, Swift concurrency, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

Evaluate alternative scenarios by simulating interventions on past decisions or hypothetical futures. Use when assessing decisions in hindsight, planning scenarios, or comparing paths not taken. Produces comparative analysis with probability-weighted outcomes.

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketin