Skill UI

Evaluates OAuth 2.0 and OpenID Connect deployments for redirect URI flaws, CSRF via missing state, PKCE bypasses, token leakage, and scope escalation to ensure secure authorization-code flows before production onboarding.

CLI interface for AgentHub message board that lets coordinators and agents list channels, read posts, post updates, and reply to threads using markdown-formatted posts organized by channels.

Guides on using SwanLab for open-source ML experiment tracking, offering local or self-hosted dashboards, rich media logging, and integrations with PyTorch, Transformers, Lightning, or Fastai for comparing runs and monitoring metrics.

Analyze an unfamiliar repository at a high level, produce a structured onboarding guide covering architecture, entry points, conventions, and create or enhance a CLAUDE.md so new contributors can start quickly.

Launches an interactive web dashboard designed to visualize the knowledge graph derived from a target codebase. This tool helps developers gain a high-level, structural understanding of complex projects by mapping out relationships, module dependencies, and the overall knowledge network of the code, making maintenance and onboarding significantly easier.

Creates a comprehensive onboarding guide for new teammates by extracting project context from the knowledge graph, layering architecture descriptions, guiding tours, and highlighting complex files so newcomers can ramp up quickly.

Formats Markdown into Slack-ready HTML or mrkdwn, previews the Slack-style rendering, copies rich HTML to the clipboard, and optionally delivers announcements via webhooks for messages and notifications.

Trackio is a robust library designed for comprehensive monitoring and management of Machine Learning experiments. It allows users to log key training metrics, set structured alerts (e.g., loss divergence, NaN gradients), and visualize results over time. The system supports integration via Python API for logging/alerting, and a powerful CLI for programmatic metric retrieval and dashboard synchronization to Hugging Face Spaces. Ideal for autonomous AI agent workflows and detailed research tracking.

Craft reusable Manim explainers for technical concepts, graphs, and product walkthroughs, focusing on structured storyboards, precise motion, and handoffs to the ECC video stack when polish is needed.

Plotly enables Python users to build interactive, publication-quality charts with hover, zoom, and embedded dashboards; ideal for exploratory analysis, presentations, or web storytelling across 40+ chart types.

Extracts business domain knowledge from a codebase, optionally reusing an existing knowledge graph, and generates an interactive horizontal flow graph for dashboard visualization, with lightweight scanning and validation steps.

Turns your existing Kanban board into an autonomous AI-driven development pipeline, coordinating Claude Code workers, deterministic gates, cost tracking, and crash-proof orchestration for full lifecycle work.