Tools

Semantic search over past Claude Code, Codex and other agent sessions: indexes each conversation when it ends and recalls past discussions, decisions and trade-offs via MCP tools and a subagent. Embedding and search run locally. By the author of Superpowers.

Develops an original visual language for a brand, campaign, publication, site or product. Without looking at contemporary design, it builds ten typography-only HTML directions; once you lock one, it turns it into a production system. Not for routine UI fixes or existing design systems.

AI agents collaborate via the ADDIE instructional design model: enter a course name to get a syllabus, LaTeX slides, lecture scripts and assessments, convertible to editable PPTX. Open-source code for an EACL 2026 paper; needs an OpenAI API key, LaTeX for PDFs and Node.js for PPTX.

Official Tavily skills: let agents search the web, extract page content, discover site URLs, crawl in bulk and run cited deep research through the Tavily CLI (tvly). Install the CLI first; search and extract have a limited no-login tier, other features need sign-in or an API key.

Design token CLI (formerly Cobalt UI): reads W3C DTCG tokens for color, type, spacing and more, validates them and generates CSS, Sass, JS/TS, Swift, Tailwind and other code via plugins. Runs in CI so design specs flow into code automatically. Needs a Node.js project.

Lets agents work with Salesforce orgs authorized on your machine: SOQL queries, metadata deploy and retrieve, Apex test runs and permission set assignment, plus toolsets for LWC development. Maintained by Salesforce; authorize your org with the Salesforce CLI first.

Lean 4 theorem-proving plugin with workflows to draft, formalize, prove, disprove, review and golf proofs, plus mathlib search, axiom checks and safety guardrails, helping mathematicians and teachers produce machine-checked proofs. Needs Lean 4 and mathlib; pairs well with lean-lsp-mcp.

Research guardrails for PhD students: reproduce arXiv papers, debug training anomalies with evidence, compare runs at matched epochs, check paper-code consistency, verify BibTeX, find literature gaps and predict reviewer comments. No MCP or extra dependencies; mostly for ML research.

Typed as /bro, has the agent re-explain its previous reply in plain, casual language without answering anything new or calling tools, keeping paths, commands and numbers verbatim and replying in the original language.

Design engineering skill that steers agents away from generic AI-looking UI when building dashboards and landing pages, reviews interfaces for usability and adds motion and polish. npx installs the skill only; slash commands, MCP quality gates and review agents need the CLI or plugin.

Anthropic's official healthcare plugin for the US system: extract data from clinical notes, assign ICD-10 and CPT/HCPCS codes, review prior auths, screen for fraud and draft trial protocols, with hosted CMS, NPI and PubMed connectors. FHIR access needs API rights; clinicians must review.

Deploys HTML or full-stack projects generated by agents to Tencent Cloud EdgeOne Makers and returns a public URL; supports both the international and China sites. Maintained by Tencent Cloud EdgeOne (formerly EdgeOne Pages MCP); sign in via browser or set an API token.

Two skills for the MCM/ICM and China's CUMCM math modeling contests: solver breaks down problems, picks models from a 95+ scenario decision matrix and gives Python or MATLAB templates; paper coaches abstracts, model validation and formatting from winning papers. Needs Python or MATLAB.

Install the QGIS MCP plugin from the QGIS plugin repository and agents get 125 tools to manage layers, edit features, run processing algorithms, style maps, build layouts and atlases, and run SQL across layers; supports QGIS 3.28 to 4.x. Needs QGIS and uv; no repo download required.

Creates a blueprint-style animation that explains UX decisions step by step for case studies and posts: rebuilds changed parts between Before and After screens, or annotates each module of one screen. Reproduces Figma frames 1:1; CC BY-NC 4.0, non-commercial only.

Official FinLab quant skill: lets agents use FinLab data (mainly Taiwan stocks, plus US, Japan, Korea and Hong Kong) to write stock-picking strategies, run backtests and analyze factors. Needs a FinLab account (free tier has a daily data cap), Python 3.10+ and uv. Not investment advice.

Makes a product film (landing-page loop, launch video, promo, demo reel) in code with Remotion, reusing the product's own design system, components and voice. It interviews the user first, then writes the story, syncs scenes to music beats, reviews stills in loops and verifies the final render.

Applies a Scandinavian visual system: black-and-white neutrals with alpha ink for hierarchy, restrained sans-serif type, generous spacing, clear page chapters and minimal decoration, without sacrificing clarity or accessibility. Has apply, review, prototype and deep modes; manual invoke only.

Lets agents run local ComfyUI workflows to generate images, audio and video, regenerate from earlier results with new parameters, check the queue and switch models. Install and start ComfyUI, then clone this repo and run the server with Python (port 9000 by default).

Hands Figma node layout, styles and images to AI coding tools to turn into high-fidelity HTML/CSS, React or Tailwind code, and downloads design images locally. Needs a Figma personal access token; sends basic usage stats; switch to the plugin version if you hit Figma API rate limits.

Resend's official email CLI: send email and manage domains, API keys, contacts, broadcasts and webhooks, with automatic JSON output outside a terminal and a bundled agent skill. Needs a Resend API key; a free plan is available.

McNeel's official Rhino MCP: lets Claude, Codex and other agents model, edit and organize layers in Rhino and Grasshopper, for architectural concepts and product forms. Needs licensed Rhino 8 or 9; install Rhino-MCP-Platform from the package manager and connect with MCPConnect.

One learn-faster command turns Claude Code into a learning coach: builds a syllabus for your level, schedules spaced review, sets exercises and tracks progress, with an exam-prep mode. Needs uv and Claude Code; Codex: run learn-faster init --agent codex (lighter onboarding).

Generates and edits images with Google's Gemini image model (Nano Banana) at up to 4K, keeping multiple characters consistent, rendering accurate text and setting aspect ratios. Needs a Gemini API key (or Vertex AI) and uv. Community project, not by Google.