Total 51,031 skills, AI & Machine Learning has 8547 skills
Showing 12 of 8547 skills
Generate images using Google's Gemini API. Use when creating images from text prompts, editing existing images, or combining reference images for AI-generated visual content.
Claude-Codex-Gemini tri-model orchestration via ask-codex + ask-gemini, then Claude synthesizes results
Integrate PICA into a LangChain/LangGraph Python application via MCP. Use when adding PICA tools to a LangChain agent, setting up PICA MCP with LangChain, or when the user mentions PICA with LangChain or LangGraph.
ALWAYS invoke this skill at the START of every session before doing any other work. This skill ensures the host project has agent governance rules (skill routing, pre-implementation protocol, issue tracking conventions) installed in its context file. It is idempotent — if rules are already present, it exits silently. Without this skill running first, other swain skills (swain-design, swain-do, swain-release) will not be routable.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
Technical guide for creating a new Paperclip agent adapter. Use when building a new adapter package, adding support for a new AI coding tool (e.g. a new CLI agent, API-based agent, or custom process), or when modifying the adapter system. Covers the required interfaces, module structure, registration points, and conventions derived from the existing claude-local and codex-local adapters.
Concise, structured summaries of news articles (~30 sec read time). Captures key points, context, bias/gaps, and open questions. Use when user shares article URL or asks to summarize news content.
Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
Generate AI videos, images, speech, and music using varg. Use when creating videos, animations, talking characters, slideshows, product showcases, social content, or single-asset generation. Supports zero-install cloud rendering (just API key + curl) and full local rendering (bun + ffmpeg). Triggers: "create a video", "generate video", "make a slideshow", "talking head", "product video", "generate image", "text to speech", "varg", "vargai", "render video", "lip sync", "captions".
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.
Measure and improve the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For deployment, use agent-platform-deploy.