Results for “sam”

Turn a music track into a beat-synced video — lyric video, slideshow, or kinetic promo — with optional user-supplied images or videos cut onto the same beat grid.

Runs a structured code review using four parallel subagents covering style, correctness, security, and performance, then synthesizes findings by severity and gives an approve/needs-changes recommendation.

Verifies every bibliographic entry in a paper for existence, metadata accuracy, and contextual support using web/DBLP/arXiv lookups, flagging hallucinated authors, wrong years, fabricated venues, and misattributed citations.

Runs a structured multi-agent deliberation: four specialist agents write independent position papers, two cross-examiners debate them, and the orchestrator synthesizes a final recommendation with implementation plan and risk register.

Runs a plan file through the Codex CLI as an independent adversarial reviewer, then folds accepted findings back into the plan. Read-only sandbox; Codex never edits.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Professional LaTeX formatting, strategic analysis frameworks (Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, BCG Matrix), and deep research integration.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Generate and rank theory-first or proof-oriented research ideas. Use when the user wants non-experimental research ideas, theoretical methods, proof programs, theorem candidates, impossibility results, convergence/sample-complexity analyses, or "analysis" variants of idea creation.

Clones a live web page's exact look into clean, semantic Tailwind — same design, but the framework-generated selectors (css-1a2b3c, sc-bdfBwQ, jsx-hashes) are replaced with real Tailwind utility classes — then validates the rewrite against the original in a loop until it matches. Use whenever a user points at a live URL and wants the SAME design rebuilt in readable Tailwind classes, not a restyle — phrasings like "rebuild this page in Tailwind but keep the exact look", "convert this React app's styling to Tailwind classes", "clone this design into clean Tailwind", "same look, real Tailwind classes, not the hashed ones", or "de-obfuscate this page's classes into Tailwind". For a byte-exact clone that KEEPS the original ugly selectors, use page-cloner. For a redesign that changes the look, use page-redesigner. Requires Claude in Chrome for capturing the source page.

Deploy and operate the RTVI-CV-3D microservice for multi-camera 3D detection and tracking, supporting sample datasets, custom videos, and RTSP streams.

Build, fit, validate, and compare Bayesian models using PyMC's modern API, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Extract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.

Test web applications for XML injection vulnerabilities including XXE, XPath injection, and XML entity attacks to identify data exposure and server-side request forgery risks.

Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features and classifying samples with machine learning models.

Generate a high-converting ad creative set — hero image, ad copy variations, and platform-optimized crops for Meta, Google Display, and LinkedIn.

Generates a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.

Recovers malware configuration, decodes C2 and beacon parameters, unpacks staged payloads, and extracts bot or campaign IDs from samples in a CTF sandbox environment.

Quantifies the minimum accuracy gap needed between two models for a sampled micro-benchmark to reliably preserve their ranking, using the MDAD metric from Yauney et al. (2025).

Provides guidance for using python-xxhash to implement fast non-cryptographic hashing, including algorithm selection, byte encoding, streaming updates, digest representation, and collision-aware identity for checksums, bucketing, and sampling.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Extract Jetson Linux BSP and sample-rootfs tarballs, run apply_binaries.sh with the correct GPU stack flag, and record the image metadata in the active target profile.

Test web applications for Cross-Site Request Forgery vulnerabilities by crafting forged requests that exploit authenticated user sessions during authorized security assessments.

Analyzes bootkit and rootkit malware that infects MBR, VBR, or UEFI firmware for pre-OS persistence, covering boot sector analysis, UEFI module inspection, and anti-rootkit detection.

Performs static analysis of Windows PE malware samples using PEStudio to examine file headers, imports, strings, resources, and indicators without executing the binary.

Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.

Generates a multi-part animated story video by establishing a consistent character, creating sequential scenes, and animating them using image generation and image-to-video models.

Creates a dramatic 'giant product' visual by compositing a product image into a scene where it appears building-sized next to a person, with an optional animation step.

Generates a realistic behind-the-scenes selfie of the user with a celebrity from a specified movie, with an option to create a cinematic video connecting multiple selfies.

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

Runs the current git diff through the Codex CLI for an independent, read-only second-opinion review, then triages findings back into the session for Claude to apply fixes.

Turns messy business process descriptions into structured workflows, classifies each step for automation potential using a GREEN/YELLOW/RED framework, and produces a prioritized automation roadmap with time savings estimates.

This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.

Implement Okta as a centralized identity provider for cloud environments, configure SSO with AWS, Azure, and GCP, deploy phishing-resistant MFA, automate user lifecycle management, and enforce adaptive access policies.

Reads and preprocesses 5-minute stock candlestick CSV data, then clusters the time series using tslearn's TimeSeriesKMeans, including data cleaning, percentage change calculation, model training, saving, and representative sample extraction.