Prompts
Prompts for chat models, image and video models and coding agents, from open collections and NoviaHub's editors. Each keeps its author's credit and licence; the titles and summaries are ours.
- Agent Skills for Knowledge Work
Skills for knowledge work rather than just coding, covering a variety of cognitive approaches to problem-solving: brainstorming, critical thinking, problem diagnosis, design thinking, market research, deep reading, Socratic tutoring, and more.
- Universal Exam Cram Coach
A multimodal, grounded active-learning tutor engine for college textbooks. Mitigates AI hallucinations and diagram blindness with automated vector figure cropping, homework-solution auto-pairing, and cross-session persistent state. Benchmarked on STEM courseware to run on small m
- PLUR
Open, local-first engram memory for Claude Code. Engrams are plain-text YAML you can read, correct, and delete. The same memory is shared across MCP tools and multiple providers.
- Claude Code Local
Runs Claude Code fully on-device on Apple Silicon: a native MLX server speaks the Anthropic Messages API, so the unmodified claude CLI works against local Qwen, Gemma and Llama models with no cloud calls. Includes RAM-based model selection, a tool-call parser for local models' ou
- cc-semaphore
A lightweight session monitor for parallel Claude Code sessions. Aggregates running/waiting/idle status across sessions into the OS status bar or system tray, with the same experience on native Linux (GNOME Shell extension) and Windows (system tray via WSL). Also includes a scrip
- bough
Reads Claude Code JSONL session transcripts and draws a project's history as a creatively-styled diagram: a day, the tasks inside it, and every prompt, with the ones that ended in a commit marked. Segments work from pauses in the record rather than anything the user labelled, and
- Repowire
A live mesh network that connects Claude Code and other providers so they can talk to each other in real time. Built for emergent coordination. Agents discover each other and share context across project boundaries. Uses tmux sessions as the coordination layer with logical "circl
- napkin-to-blueprint
A five-stage pipeline of Claude Code slash commands and specialized subagents that turns a raw product idea into a build-ready blueprint: an interview-driven brief, researched feature definitions, per-feature specs with acceptance criteria, and an architecture with a database sch
- Agents Can Communicate (ACC)
Local, multi-provider agent communication tool. Adds hooks and a skill to exchange questions and reviews, and saves decisions, verification results and handoffs for later sessions. Each session keeps its own client, model, conversation and permissions.
- context-tax
A zero-dependency CLI (npx context-tax) that reads Claude Code session transcripts to measure what is sent on every turn before the first prompt: system prompt, MCP tool names, the skill listing and instruction files. It prices each item per use, counts skills sent without a desc
- Charrette
A Claude Code plugin with agent skills for designing software before code is written: brainstorm boards, plans cut into slices and run by subagents, working HTML mockups, development workbenches and layered pull request reviews. Every document renders live in a bundled local view
- wattop
Terminal monitor for Apple Silicon Macs that shows live Claude Code and Codex sessions, including subagent and workflow trees, with output tokens/s, context fill and estimated cost beside CPU/GPU power, temperatures and fans. Reads local transcripts.
- OctoShell
Terminal workspace for Windows and macOS, built on command blocks, that runs Claude Code in git worktrees, one per task, each with its own shell and dev server. Features include Strategy Mode (several agents plan a change before writing code), a Reviewer agent that reads each cha
- mirrord
Agent skills and a Claude Code plugin marketplace for mirrord, which runs a local process inside a live Kubernetes cluster's network, environment and traffic. Lets Claude verify changes against real services, databases and queues instead of mocks, with skills for config, CI, data
- Pinpoint
Local MCP server, Claude Code hooks and a Chrome extension for marking up a running app: clicking an element (or one in the iOS Simulator) and typing a change delivers the comment to Claude Code with the selector, DOM path, computed styles, component chain, source-file hint and a
- atelier
Claude Code plugin with eight design-automation skills driven by one schema-validated brand.json: design tokens for CSS, Tailwind, TypeScript and Figma, social cards, favicon and app-icon sets, responsive AVIF and WebP images, HTML-to-video recording, a WCAG 2.1 AA audit, and a r
- Consort
Spec-first, test-driven agent framework: runs the build loop against live Lakebase Postgres branches under a deterministic orchestrator, with human-approval gates.
- geo-sleuth
An agent skill that geolocates a photo with no readable text. Single-purpose Python scripts search and rank candidates using OpenStreetMap geometry, elevation skylines, satellite imagery and street view. The answer comes with a camera position, heading, error radius and an eviden
- Agent 007
A self-hosted office with a pleasing pixel-art UI where one manager agent, Billion, takes a mission, posts jobs to a board, and reviews and merges pull requests that Claude Code and Codex workers open from their own git worktrees. Accessible from desktop or mobile.
- Story Skills
Skills for planning and drafting fiction as markdown with YAML frontmatter: story bible, characters, worldbuilding, arcs, scenes, and chapters. Includes a dependency-free CLI whose continuity checker flags characters appearing after their death, payoffs placed before their setup,
- bdg (Browser Debugger CLI)
A CLI and Claude Code skill for UI debugging in Chrome using the DevTools Protocol, including DOM inspection, browser events, rendered styles, and detailed layout information.
- Gryph
Gryph is a security layer for AI coding agents. It hooks into Claude Code and enforces YAML policy rules that block, warn, or guide actions in real time, then logs every event to a local SQLite database for review and audit.
- Codeburn
Breakdown of local spend down by project, model, git branch and task. Tracks plan quotas, and identifies token waste, including unused MCP servers, verbose CLAUDE.md, repeated file reads, and more.
- claude-carbon
Tracks the carbon footprint of Claude Code sessions, feautring a live CO2 estimate in the status line, computed locally from token usage, next to the session cost.
Prompts come from public collections and keep their own licences and credits. NoviaHub is not affiliated with their authors; any image or video shown is a sample NoviaHub generated.