2,379 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.
MCP server Claude CodeCodexCursor +2
PromptLab is a free, lightweight, open-source experimentation tool for Gen AI applications. Runs locally from the promptlab Python package.
mightyhuman101/seedance2-skill
Skill Claude CodeCodex
A guide for writing prompts for Seedance 2.0, an AI video generator that can use text, images, videos, and audio as input.
Plugin Claude Code
Bundles 9 skills, 3 agents · 1,095 tokens together
Prompt engineering workbench with a Lean persona layer that cuts LLM output size, cost, and latency. Injects the Lean ruleset every session via SessionStart + SubagentStart hooks.
Jsebayhi/prompt-engineering-extension
Skill Claude CodeCodex
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
stevengonsalvez/promptregistry-mcp
MCP server Claude CodeCodexCursor
A Model Context Protocol server for managing prompts via stdio. Runs locally from the mcp-promptregistry npm package.
Skill Claude CodeCodex
Analyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger…
samibajwaisking/Token-Optimizer-Skill
Skill Claude CodeCodex
Maximize Claude's output quality while minimizing input token usage. Use this skill whenever a user wants to compress prompts, reduce token consumption, extract maximum output from Claude, write high-density instructions, optimize system prompts, or improve AI communication efficiency. Trigger on phrases like…
Skill Claude CodeCodex
Operate and evaluate Unified AI System through twelve governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.
IchenDEV/prompt-optimizer-plugins
Plugin Claude Code
Bundles 7 skills · 990 tokens together
Clarify and optimize prompts for GPT-6 Astra, GPT-5.6, Claude, Gemini, Kimi, GLM, and DeepSeek-V4.
Skill Claude CodeCodex
Transform vague prompts into precise, verifiable structured XML prompts that coding agents execute reliably. Modes: execute (default — generate then run) and plan (generate XML for review first). Use when the user says improve prompt, make this work better, prompt engineer, structure a request, plan a complex change…
comeonzhj/comeonzhj-cc-marketplace
Plugin Claude Code
Bundles 2 commands · 43 tokens together
A tool that extracts prompts from a project and analyzes how the related code implements them. A prompt is the instruction given to an AI system.
Plugin Claude Code
Bundles 1 skill · 69 tokens together
LEAP: LLM Engineered Application Pattern. A philosophy where code is a commodity — only prompts, schemas, and tests are source of truth. AI generates all application code on demand.
Skill Claude CodeCodex
Guard and improve prompts before expensive Codex, IDE, or CLI agent work. Use when a prompt is vague, broad, risky, costly, or should be optimized before implementation.
Skill Claude CodeCodex
Use when designing or reviewing AI/ML integration code — covers RAG pipeline design, prompt engineering, structured output with schema validation, tool use/function calling, LLM error handling, token budget management, hallucination mitigation, and AI/ML anti-patterns with examples in TypeScript and Python.
Skill Claude CodeCodex
A set of instructions for connecting an application to DeepSeek, an AI service that can generate text responses. It covers sending web requests, receiving normal or live-streamed replies, and handling connection errors.
Skill Claude CodeCodex
Reference Claude Code's prompt engineering patterns for AI/Agent development. Provides best practices for system prompts, tool design, agent orchestration, and safety.
Skill Claude CodeCodex
Discover and assemble a task-specific prompt from the embedded PromptKit catalog through the PromptKitty CLI. Use when the user wants to select a PromptKit template, compose a prompt for an engineering task, run an interactive PromptKit intake, write a requirements or design artifact, investigate a bug, review code…
Skill Claude CodeCodex
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
Plugin Claude Code
Bundles 12 skills, 1 hook · 591 tokens together
Declarative prompt composition via hashtag modes. Like CSS for Claude.
Trista3/claude-code-agent-teams
Agent Claude Code
AI capability analyst and prompt system designer for parent-child interactive products. Evaluates which AI features are feasible, designs safe AI interactions for families, and builds evaluation frameworks.
Skill Claude CodeCodex
Discover, install, and run reusable AI prompt skills from the BetterPrompt registry via the CLI (betterprompt / bp). Use when a user needs to find a prompt skill, generate AI output (text, images, video), or manage their skill library. Covers installation, auth, skill discovery, generation, and output review for…
Instructions file
Instructions for victor-aguilars/promptocop, covering promptocop, project overview, tech stack, project structure and rule system.
Skill Claude CodeCodex
Use when user asks to improve, refine, or rewrite a prompt for an AI system, or when framing a request that feels vague, overloaded, or logically unsound. Triggers: "improve my prompt", "rewrite this prompt", "make this prompt better", "help me ask this question properly", "this prompt feels off".
gquattromani/prompt-best-practices
Instructions file CodexOpenCode
AGENTS.md instructions for gquattromani/prompt-best-practices, covering prompt best practices, when to assess, task tiers, the 7 components and match the runtime.
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: