AI & ML

Analyze single-cell RNA-seq data with Scanpy, covering quality control, normalization, dimensionality reduction, clustering, marker gene identification, and visualization.

Performs astronomical data analysis with astropy: coordinate transformations, unit conversions, FITS file handling, cosmological calculations, time systems, tables, and WCS.

Enforces a machine-readable behavioral contract for multi-agent development, mandating specification-first workflows, git checkpoints, context lineage, and quality gates.

Analyzes runtime history to identify failures and inefficiencies, then autonomously writes improvements using a protocol-constrained evolution engine. Communicates with EvoMap Hub via a local Proxy mailbox.

Backtests quantitative trading strategies across 9 engines and 25 data sources, analyzes trade journals, and runs multi-agent research teams.

Computes phylogenetic distance matrices and trees from genomic VCF or FASTA data using the fastreeR hybrid Java/Python toolkit.

Builds, refines, tests, or validates a CLI-Anything harness for a GUI application or source repository, producing a Python-based Click CLI with REPL mode and JSON output.

Detect promoter regions in DNA sequences by calling the Genomic Intelligence G0 transformer (GENA-LM BERT Large) hosted API. Returns per-window promoter probabilities and called regions as a report and JSON, from a single FASTA input.

Scores genetic compatibility between all male-female pairings in a Genomebook generation, ranking optimal mating pairs based on heterozygosity, trait complementarity, and disease risk.

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.

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.

Integrates with the OpenAI API to build AI-powered applications using GPT models, embeddings, and function calling.

Provides guidance on using PyTorch for deep learning, covering tensors, autograd, nn.Module, DataLoaders, and best practices.

Builds a configurable scraping agent that collects data from APIs, HTML, or RSS, enriches it with Gemini AI scoring, and stores results in Notion, Google Sheets, Supabase, or local files.

Reference for building LLM-powered applications with the Claude API and Anthropic SDKs, covering model selection, parameters, streaming, tool use, and migration.

Runs a multi-agent adversarial verification loop where two independent reviewers must both pass before output ships, with a fix cycle for convergence.

Provides guidelines for building with Botpress's Agent Development Kit (ADK), covering project structure, primitives, CLI commands, and documentation lookups.

Indexes and searches local Markdown notes and docs with BM25 keyword search, vector semantic search, and local LLM reranking, all running offline without API keys.

Guides a conversation to design a new AI team member, generating agent identity files and optionally setting up performance reviews.

Create data-driven charts with Vega-Lite and Vega, covering bar, line, scatter, heatmap, area, radar, and word cloud visualizations from structured data arrays.

Provides guidance on using the ZVec in-process vector database for efficient similarity search and embedding storage in agent memory systems.

Generates YouTube videos from prompts, creates vertical Shorts from text, and converts long videos into Shorts using free tools like ffmpeg, edge-tts, and Pexels.

Discovers and evaluates community skills from skills.sh and awesome-openclaw-skills when local skills don't cover a need, scoring credibility and installing top recommendations with permission.

Generates images from text prompts using diffusion models, covering prompt engineering, inpainting/outpainting, ControlNet, and API integration for production workflows.

Diagnoses and fixes MCP gateway routing issues, health checks, and server connectivity problems.

Generate video clips with Google Veo (Veo 3.1 / Veo 3.0) via a command-line script, with options for duration, aspect ratio, and model selection.

Model any API with Swamp, test it, and enrich *Claw with new capabilities — full lifecycle from idea to working.

Transcribes audio from URLs or local files into text with speaker diarization, word timestamps, and multiple output formats via a command-line tool.

Search, explore, and run fal.ai generative AI models for image, video, audio, and 3D generation directly from the command line.

Generates creative launch blueprints for memecoins on pump.fun, including names, symbols, narratives, and buyback plans, with built-in safety guardrails.

Registers as a trading agent on zHive, fetches crypto signals, posts predictions with conviction, and competes.

Manages Ray clusters, jobs, Serve deployments, and distributed workloads via the Dashboard API and CLI, with discovery-first checks and safety guardrails.

封装阶段3的Copy Spec为可批量执行的提示词包，生成JSONL请求并调用APIMart API出图。

Predict continuous values from temporal sequences using aeon's time series regressors, covering convolutional, deep learning, distance-based, feature-based, hybrid, interval-based, and shapelet-based approaches.

Guides analysis of Neuropixels recordings from raw data to curated units, covering preprocessing, motion correction, spike sorting, quality metrics, and export.

Converts documentation websites, GitHub repositories, and PDF files into AI-ready skills for multiple LLM platforms.