AI & ML

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

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.

Generates luxury jewelry product videos with high-end commercial cinematography and macro animation using AI image and video generation.

Generates a humorous, ultra-realistic video of an anthropomorphic animal vlogger in a real-world setting using AI image and video generation.

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 dynamic product advertisement image with flying ingredients, then animates it into a cinematic product showcase video.

Turns a product photo into a cinematic video advertisement using AI rendering and animation.

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

Turns a person's photo into a custom 3D action figure with collectible toy packaging.

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.

Generates a 15-second cinematic cooking tutorial video from a single person photo, using a two-step process that first creates a composite reference sheet and then animates the full sequence with consistent character and environment.

Decides when to delegate to compressed-output subagents (investigator, builder, reviewer) instead of using vanilla agents, saving main-context tokens across long sessions.

Plans and coordinates the deployment of a model to Amazon SageMaker AI, selecting the appropriate pathway (real-time, serverless, async, batch, or Bedrock CMI) based on model type, traffic, latency, and cost constraints.

Integrates multi-dimensional health data to detect anomalies, predict risks (hypertension, diabetes, cardiovascular), and generate personalized recommendations and interactive HTML reports.

Build applications that programmatically interact with GitHub Copilot using an SDK that wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Enables compact, machine-native agent-to-agent messaging using a shared vocabulary of 340+ 2-character atoms across 7 domains, achieving 3x compression over natural language.

Guides the creation of MCP servers that enable LLMs to interact with external services through well-designed tools.

Provides persistent, self-hosted semantic memory for AI agents via MCP, storing worklogs, decisions, and notes in PostgreSQL with pgvector for meaning-based retrieval across sessions.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks, including model serving, feature engineering, A/B testing, and monitoring.

Designs and governs recursive self-improvement loops where an agent mines its own failures and proposes edits to its own harness, prompts, or workflow, covering acceptance gates, diversity preservation, and the optimization ladder.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Polls a local relay for animation-refinement jobs from the Timeline Inspector, posts suggestions or applies changes to transition code.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Guide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal evidence.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

Bridge any skill folder or directory of skill folders to Claude Code, Codex, generic Agents, and Grok using symlinks plus Grok bridge files.

Turns a local folder into a searchable, maintainable knowledge base for AI agents, handling setup, navigation, content ingestion, querying, and health checks without external databases or RAG systems.

Transforms fuzzy problems into structured briefs that AI agents can reason about, critique, and act upon, while evaluating how much of the problem can be automated.

查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报，通过公开只读 API 获取实时数据。

Documents the design system of BMW's corporate website, including color palette, typography, spacing, and layout tokens for UI implementation.

Documents the warm, editorial design system of Claude.com, including color palette, typography, spacing, and surface modes for consistent brand implementation.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Analyze suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior detection.

Specialized CTF sandbox skill for analyzing prompt-to-tool chains, deployment drift, and supply-chain provenance in cloud, container, and CI/CD environments.

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Compresses conversation transcripts into prioritized notes using an LLM observer, consolidates them when they grow, and recovers any missed sessions without a database or vector store.