AI & ML

Adds input and output guardrails to an agent, including validation, content filtering, domain scoping, and rate limiting, with TypeScript examples and wiring instructions.

Manages A/B tests by running a Python script that processes input and produces JSON results.

Configure tools and SDKs to route LLM requests through a single API key with native-compatible endpoints for Claude, GPT, and Gemini, including setup, base URLs, and code examples.

Builds a complete Uniswap V4 hook by delegating to a hook-builder agent, generating Solidity contracts, Foundry tests, CREATE2 address mining, and deployment scripts.

Monitors OpenClaw model API usage and prompts for user confirmation before switching models when quota is low.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

Enables semantic file search across a codebase using a vector-powered CLI, with integration for Claude and Codex agents.

Designs collaborative AI agent teams with CrewAI, covering agent roles, task definitions, crew orchestration, process types, memory, tools, and flows.

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design assets.

Build, optimize, and execute quantum circuits on IBM Quantum hardware or local simulators using Qiskit, including transpilation, primitives, and algorithm libraries.

Guides production LLM operations: RAG pipelines, embeddings, vector databases, fine-tuning, prompt engineering, cost estimation, quality evals, and AI architectures.

Build cross-platform AI chat interfaces with Makepad using MolyKit, covering async patterns, BotClient integration, and chat widgets.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and automatic statistical estimation.

Enables image generation and real-time X/Twitter data via external models using x402 micropayments, with budget tracking and wallet management.

Instrument LLM applications with Langfuse for tracing, prompt management, evaluation, and cost tracking, including integrations with OpenAI, LangChain, and LlamaIndex.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new contexts.

Controls a Chrome browser through the AIPex extension and MCP bridge, enabling navigation, clicking, form filling, screenshots, tab management, and content downloads.

Produces a complete narrated, subtitled, scored explainer video from a single topic prompt using a six-stage pipeline with script, voiceover, keyframes, animation, music, and local assembly.

Generates high-quality prompts for AI image, video, and music generation platforms, with optional browser automation to submit them to target sites.

Define every visual attribute as structured VGL JSON for deterministic, reproducible image generation with Bria FIBO models, covering objects, lighting, camera settings, composition, and style.

Silently restructures natural-language prompts into the format best suited for the model currently executing the skill, then answers the rewritten version.

Generates complete AI videos through a 6-stage pipeline (script, character/scene design, storyboard, reference images, video generation, post-production) or one-shot pipelines for short videos, action transfer, and digital human dubbing, all running on local servers.

Orchestrates multi-agent teams using the ClawTeam CLI, enabling task management, inter-agent messaging, git context integration, runtime profiles, and monitoring dashboards.

Search scientific papers via the BGPT MCP server and retrieve structured experimental data — methods, results, conclusions, quality scores, and 25+ metadata fields per paper.

Compile SOUL.md character profiles into synthetic diploid genomes (.genome.json) via trait-to-allele mapping.

Automates sequencing quality control by running FastQC and MultiQC, extracting quality metrics, and generating publication-ready visualizations via a CLI or MCP stdio server.

Detect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted /v1/tasks/splice/predict API. Returns per-position site probabilities and called sites.

Performs differential expression analysis on bulk RNA-seq or pseudo-bulk count matrices with QC, PCA, and contrast testing.

Generates, edits, and transforms images via the Bria API, including text-to-image, background removal, product photography, and batch processing for e-commerce catalogs.

Identifies a medication from a photo and generates a genotype-informed dosage card using CPIC guidelines and real 23andMe data.

Discovers, finds, audits, repairs, adapts, crafts, runs, debriefs, saves, and prepares repeatable AI-agent loops for publication, treating loops as bounded feedback systems.

Predicts enhancer activity in DNA sequences using the hosted Genomic Intelligence G0 DeepSTARR model, returning per-window activity scores.

Creates cross-platform agent skills from workflow descriptions, files, URLs, or screenshots. Supports single skills, multi-agent suites, template-based creation, cross-platform export, spec validation, and security auditing of third-party skills before install.

Statistical fine-mapping of GWAS loci using SuSiE, SuSiE-inf, and Approximate Bayes Factors to identify credible sets and posterior inclusion probabilities (PIPs) for causal variant discovery. SuSiE-inf adds an infinitesimal polygenic component for improved calibration at well-powered loci.

Computes evidence-aware polygenic risk scores from local VCF or WGS files using the just-prs engine and a pinned local MCP server, with honest interpretation and model comparison.

Simulates meiotic recombination to produce offspring genomes from parent pairs, modeling Mendelian segregation, de novo mutation, sex determination, trait inference, and clinical evaluation against a disease registry.