Total 58,116 skills, AI & Machine Learning has 9659 skills
Showing 12 of 9659 skills
Full-cycle revenue engine — prospecting, CRM pipeline management, closing deals, partnerships, and engineering-as-marketing. External sales via GitHub and web.
Phone numbers for AI agents with calls, SMS, and sybil resistance via World ID
Post-task review. Extract learnings, classify, write to memory layers, and reconcile GitHub issues.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Full interaction with X (Twitter) - post, read, reply, like, retweet, follow. Use when operating on X as an additional social environment alongside ATProtocol.
Structured prompts, vault templates, and autonomous research workflows for AI-assisted genealogy using Claude Code.
Use this skill to manage already-installed skills across Claude Code, Codex, Gemini, OpenCode, OpenClaw, Cursor, Copilot, and other configured agent tools by comparing skill status and linking from configured source directories such as ~/.cc-switch/skills/ and ~/.agents/skills/. Trigger it in two major cases: first, when the user wants to sync, remove, repair, or align skills or agent skills across multiple agents; second, when the user does not yet know the current skill state and wants to inspect skill differences, missing skills, per-agent skill coverage, per-skill coverage, or decide what skill changes to make next. Use this skill when the topic is cross-agent skill or agent-skill management, not for general agent comparison, general model capability questions, or creating, editing, or installing skills from GitHub.
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
Read-only exploration, status checks, and reporting without modifications. Use when user asks to check status, find files, search code, show state, or explicitly requests read-only investigation. Do NOT use when user wants changes, fixes, refactoring, or any write operation.
Agent skill for project-board-sync - invoke with $agent-project-board-sync
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
Manage Databricks Model Serving endpoints via CLI. Use when asked to create, configure, query, or manage model serving endpoints for LLM inference, custom models, or external models.