Browse Skills

Creates or improves custom skills for OpenChatCut agents by capturing workflows, writing SKILL.md files, and testing with realistic prompts. Use when building reusable AI workflows or onboarding repeated tasks.

Break down each shot and turn the analysis into a storyboard reference. Use when the user wants shot-by-shot film analysis, director logic, cinematography breakdown, or a storyboard-style reference from a video.

Generate video clips using AI models like Seedance 2.0, Kling, and MiniMax Hailuo. Supports text-to-video, image-to-video, transitions, multi-shot, and video editing/extending.

Optim Agent helps coding agents tune configurable system parameters against a measured scalar objective. Use it when reading the project can improve trial selection for training, inference, research, or other expensive black-box evaluations.

Optim Agent optimizes configurable system parameters against a measurable scalar objective. Use it when you need to run the canonical optimization workflow for tuning machine learning or other systems.

Optim Agent is used to optimize configurable system parameters against a measurable scalar objective. Use it when you need to tune settings and follow a canonical optimization workflow before running experiments.

Config Audit runs a data-backed review of Claude Code configuration through the Agent Monitor API. Use it to check surface counts, overlaps, and hooks that execute shell commands.

AI Health Analyzer combines health data, detects anomalies and trends, and estimates risks from multiple dimensions. Use it to generate health reports, answer questions, and get personalized suggestions.

WellAlly Tech imports health data from Apple Health, Fitbit, Oura, CSV, or JSON and standardizes it for local use. It also recommends relevant WellAlly.tech knowledge base articles based on the imported health data.

Auto Research decomposes a strategic question into parallel research threads and synthesizes findings into actionable analysis. Use it for market, competitive, or technology questions that need evidence from multiple sources.

Harvest captures session corrections, stable facts, process lessons, and skill gaps for later human review. Use it at the end of a session or from a staging hook when you want to propose durable knowledge without writing it automatically.

Loop Engineering defines shared patterns for iterative Claude Code skills, including verifiers, stop conditions, and context management. Use it when designing or debugging a loop that searches, retries, scans, or gates progress.