2,080 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Plugin Claude Code
Bundles 2 skills, 2 commands, 2 agents · 147 tokens together
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
chang9852/role-prompt-designer
Skill Claude CodeCodex
Design and generate AI Agent role/personality definitions using the SOUL/IDENTITY/AGENTS three-layer prompt architecture. Use when: (1) Creating a new AI Agent persona from scratch, (2) Writing or editing SOUL.md, IDENTITY.md, or AGENTS.md files, (3) Designing role prompts for AI assistants, chatbots, or autonomous…
Command Claude Code
This page describes the llm.agent automation command in Cerb, which interfaces with Large Language Models (LLMs) to maintain conversation history and manage tool use. The command automatically handles authentication, API calls, chat history, and tool invocation. To use this command, you provide a systemprompt, one or…
specklesystems/speckle-docs-NEW
Skill Claude CodeCodex
Compress LLM instruction sets, system prompts, rules, and guidelines to reduce token count while preserving behavioral intent. Use this skill whenever the user wants to shorten, truncate, optimize, or compress prompts, system instructions, CLAUDE.md files, custom instructions, rules, guidelines, or any instruction set…
Skill Claude CodeCodex
Find a curated AI prompt template for any task — writing, image generation, video, or code. Use this skill when the user wants a ready-made prompt template (not a one-shot request). The skill queries a configurable prompt library backend via a documented /api/skill/ HTTP contract and returns the best match with…
KazunariNakayama/raycast-extensions
Cursor rule Cursor
A set of Cursor rules for developing Raycast extensions. Raycast is a macOS launcher that can run small extensions and commands.
arango-solutions/arango-sparql-py
Cursor rule Cursor
NL→SPARQL pipeline rules — Turtle prompts, providers, fewshot, tenant guardrails.
Plugin Claude Code
Bundles 1 skill · 64 tokens together
Track and audit LLM prompts from Claude Code with deterministic scanning, repository-aware review, visual diffs, and human notes.
Skill Claude CodeCodex
Use when the user asks to "write a prompt for DeepSeek", "compose a DeepSeek prompt", wants to send a task to a DeepSeek model, needs to launch a DeepSeek subagent. Also use when explicitly named: DeepSeek. Trigger on any request to draft, refine, or assemble a prompt targeting a DeepSeek-family model — for either…
kirill-sviridov/agent-dev-skills
Plugin Claude Code
Bundles 4 skills · 299 tokens together
Opinionated skills for building and debugging LangGraph agents and for prompt engineering: pick a stack, write a spec, debug a broken graph, and write better prompts.
Plugin Claude Code
Bundles 6 skills · 1,841 tokens together
A collection of Chinese-language skills for prompt engineering, turning images into prompts, creating multiple object views, planning interior and exterior camera views, and making seamless PBR textures for Midjourney.
sckim-ai/claude-visual-generator
Skill Claude CodeCodex
A tool for writing image-generation prompts that explain a central concept through a technical-report-style visual. It is intended for materials such as government-funded project reports, academic journals, and technical proposals, and works with visual-renderer.
MCP server Claude CodeCodexCursor +2
MCP server for JYMP - combines codebase files into LLM prompts. Runs locally from the @mahendra189/jymp-mcp-server npm package.
Plugin Claude Code
Bundles 7 commands, 1 hook · 97 tokens together
Dual-axis coaching on every Claude Code prompt: improves prompt quality and target-language expression.
manzxiao/text-to-image-prompt-optimizer
Skill Claude CodeCodex
A skill for writing and improving prompts for AI image-generation tools such as Gemini, Midjourney, Stable Diffusion, DALL-E, and Leonardo.ai. A prompt is the text that describes the image an AI should create.
Skill Claude CodeCodex
Build, debug, and optimize The Agent API / Universal SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing The Agent API code between The Agent model versions. TRIGGER when: code imports google-generativeai/@google/generative-ai; user asks for the The Agent API, Universal…
albert850904/gpt-image-2-skill
Skill Claude CodeCodex
A prompt-writing skill for creating, rewriting, classifying, or improving prompts for GPT-Image-2, an image-generation model. It includes style templates, prompting techniques, and guidance on avoiding common prompt problems.
MCP server Claude CodeCodexCursor +2
Generate A+ prompts for ChatGPT, Claude, Midjourney — built for agents & workflows. Runs locally from the @prompeteer.ai/mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
Trazum as an MCP server: let an agent price and budget its own prompts before it sends them. Runs locally from the @trazum/mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Fabric AI patterns. Runs locally from the @angrydad67/fabric-mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Scores your prompts against your real codebase — context-aware prompt intelligence. Runs locally from the prompyai-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff. Runs locally from the promptlint-mcp npm package.
Cursor rule Cursor
Prompt Compression - enforces token-efficient formatting when writing AGENTS.md, CLAUDE.md, or system prompts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: