Results for “sam”

Reference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.

Finds architectural friction in a codebase and proposes deep-module refactors to improve testability and AI-navigability, informed by the domain glossary and ADRs.

Builds a throwaway prototype to answer a design question, choosing between a runnable terminal app for logic/state questions or multiple UI variations switchable from one route.

Runs a multi-agent academic research pipeline covering systematic review, LaTeX paper writing, peer review, and end-to-end orchestration with integrity gates.

Applies design engineering principles to polish UI components, covering typography, surfaces, animations, and performance with concrete CSS values and review checklists.

OI-3 spike harness — the FORKED (context fork) readability-guidance variant. Same payload as the inline variant but declared to run in a forked context. Use only when a spike consumer skill invokes it.

Determines when adrenal venous sampling may be skipped in primary aldosteronism. Applies to patients <35 years with spontaneous hypokalemia, marked aldosterone excess, and unilateral adrenal lesions suggestive of cortical adenoma on CT.

Design and evaluate A/B tests with power, sample size, and robust metric interpretation. Use when: (1) planning controlled experiments, (2) reading p-values/effects, (3) sequential testing safeguards. NOT for: dark-pattern optimization.

Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft using Sysmon Event ID 10, Windows Security logs, and SIEM correlation rules.

Segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks with zero-shot transfer.

Combine a person's photo and a clothing item to virtually try on outfits, with an option to generate a professional fashion model video.

Generate a pack of professional or aesthetic photos from a single reference image while preserving the exact identity of the person.

Generate a complete Amazon product listing image set — hero image, lifestyle shot, feature infographic, and detail closeup optimized for Amazon standards.

Generates a Pixar-style 3D cartoon character from a photo and animates it with a reference dance video using the MuAPI platform.

Generates opinionated design systems with curated color palettes, font pairings, UI styles, product-type rules, and UX guidelines across multiple tech stacks.

Conducts autonomous multi-source research using a planner/executor architecture and an MCP server, with tools for deep research, quick search, report writing, and source retrieval.

Guides completing development work by verifying tests, presenting structured options for merging, creating a pull request, keeping, or discarding a branch, and cleaning up worktrees.

Surveys a codebase as a senior advisor and produces prioritized, self-contained implementation plans for other models or agents to execute, without modifying source code.

Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity?" - deterministically, even under concurrent writes.

Organizes PyTorch code with a Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks, and minimal boilerplate. Scales from laptop to supercomputer with the same code.

Generate platform-tuned vertical short clips (YouTube Shorts, TikTok, Reels) from long-form videos using muapi.ai's AI clipping endpoint.

Audits a paper draft by tracing every numeric claim and assertion back to result files on disk, flagging untraced, mismatched, stale, uncited, and phantom references.

Scopes code-review blast radius and detects architectural hotspots using Tree-sitter AST analysis and GraphRAG, with an MCP server for graph-based analysis.

Backs up the live global Claude Code configuration (settings.json, CLAUDE.md, statusline.ts) into a git repository, with an allowlist and secret scan to prevent leaking credentials.

Trace a break between two records of the same position or cash — accounting vs custodian, fund vs prime broker, trade vs settlement — from the aggregate difference down to the offending transaction, and classify it for clearing.

Design and implement Monte Carlo methods for uncertainty quantification, risk analysis, and probabilistic simulations across scientific and financial domains. Use when "monte carlo, random sampling, uncertainty quantification, risk analysis, stochastic simulation, MCMC, variance reduction, probabilistic, " mentioned.

Discover SameDayDesk's twenty-two account-free machine services and produce a verified, non-spending purchase intent from the live OpenAPI contract and unpaid HTTP 402 challenge. Use to select and preflight public web extraction, company or wallet enrichment, repository security scans, JSON-LD generation, AI-search audits, Morpho risk analysis, work opportunities, agent-service discoverability, agent-surface context budgets, contract-qualified service search, seller integrity, x402 or MPP payment offers, Base or Solana transaction evidence, or delegated-wallet policy conformance before a separately authorized payment executor is involved.

Downloads NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Used for Auto Setup; does not extract or edit profiles.

Generate an OpenAPI 3.1 specification from a browser-trace capture by analyzing observed HTTP traffic, templating URLs, and inferring JSON schemas from request/response samples.

Rapidly classify malware samples against known family signatures using YARA rules, covering rule writing, scanning, and integration with analysis pipelines.

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

Generate cinematic videos with Seedance 2.0 using director-level prompts, camera grammar, and multi-mode generation across Chinese, Global, and VIP tiers.

Generate a single continuous cinematic shot video with no cuts, using text or image prompts and configurable style, duration, and aspect ratio.

Reads brand identity, ICP, and messaging files to produce on-brand social video with storyboard, reference images, and Seedance 2.0-optimized prompts.

Generate a cinematic freeze-effect video where time stops mid-scene, the subject walks through the frozen world, then time resumes with a snap.

Creates a cinematic 5–10 second product advertisement video from a product photo and brand brief, using AI image generation, upscaling, and video animation.