Skill UI

A public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, or decision-support agent based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Classifies evidence and recommends proportionate remedies.

AI Elements is a component library built on shadcn/ui designed to help developers build AI-native applications faster. It provides pre-built components for conversations, messages, tool displays, and prompt inputs. Ideal for creating chatbots, AI assistants, or any AI-powered chat interface. Supports React and Next.js with easy CLI installation and full customization options using Tailwind CSS.

Better Icons is a command-line interface tool that allows developers to search over 200 icon libraries via Iconify and retrieve SVG assets. It supports batch downloading, custom styling, and integrates as an MCP server for AI agents to streamline icon management in development projects.

This tool validates AI agent changes by running statistical regression tests to ensure performance doesn't degrade. It grades tool trajectories, detects flaky cases, and integrates with CI to block merges when significant regressions occur. Supports pass@k metrics and paired statistics for reliable evaluation.

This skill enables users to generate AI audiobooks from manuscripts or course text using the Beatra service. It supports voice cloning and text-to-speech narration. The package is pinned and verified for security. Users must authorize access before use. It works within Claude Code environments.

This skill executes a single iteration of an automated research experiment. It reviews historical results, decides on a specific code modification, edits the target file, commits changes via git, and evaluates the outcome. Users can specify an experiment or select from a list. The process ensures only one change is made per iteration to isolate variables, preventing evaluation script modification. It supports strategy escalation based on run count and reports keep, discard, or crash status.

This tool provides a unified cost view for AI agents like Claude Code, Codex, and Grok. It reads local logs to calculate spend, token usage, and cache hit ratios per provider and model. It flags unpriced models and supports filtering by time range, project, and provider. Output can be JSON or Markdown. All data stays local, ensuring privacy. Ideal for auditing AI usage costs and comparing provider pricing.

Create and manage monitoring alert rules for systems like Prometheus, MySQL, and Linux. Prefer importing validated integration templates before writing custom rules. Supports bulk imports or single metric alerts. Helps configure CPU, memory, and database alerts efficiently within Nightingale.

This skill enables publishing HTML files or static folders to a permanent public URL via a single curl request without account registration. It assigns a unique slug and provides a token for updates. Ideal for sharing reports, prototypes, or docs quickly. Supports unattended agent workflows. Note: Static files only, no server-side logic.

This skill generates, repairs, and validates queries for Nightingale Metrics and Log Explorers. It supports PromQL for Prometheus, SQL for MySQL and Doris, and Doris log queries. It verifies statements against the selected datasource before returning them, ensuring read-only safety and accuracy for monitoring and analysis tasks.

FlowKit is a Python library for analyzing flow cytometry data. It supports spillover compensation, logicle transforms, hierarchical gating, and GatingML strategies. Users can reproduce FlowJo 10 workspace analyses, generate reproducible gate counts, population percentages, and fluorescence summaries. Requires Python 3.13 and specific dependencies for scientific computing.