claude-prompts
5761Plugin Claude Code
Bundles 5 hooks, 2 MCP servers
Model Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 416,105 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Plugin Claude Code
Bundles 5 hooks, 2 MCP servers
Model Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'.
Skill Claude CodeCodex
Search, install and manage skills from ClawdHub.
agent37-platform/agent37-skills-collection
Plugin Claude Code
Bundles 1 skill · 129 tokens together
Generate a compact 'prompt request' one-pager that summarizes the current session for a pull request: one consolidated User block folding every ask and decision, plus one Assistant block summarizing what was built.
ZhanlinCui/Agent-Skills-Hunter
Skill Claude CodeCodex
A daily-news workflow that collects items from configured sources, creates summaries, and writes a dated digest. It uses a profile, settings, source methods, and a local SQLite database to track collected news.
treylom/prompt-engineering-skills
Plugin Claude Code
Bundles 11 skills, 4 commands · 1,016 tokens together
A prompt-engineering toolkit that turns ideas into executable prompts. It includes a prompt-generation command, model-specific guides for Claude, GPT, Gemini, and image models, and a prompt kit.
Skill Claude CodeCodex
This skill should be used when the user provides a Tushare API document URL and asks to generate a full plugin in this codebase, including extractor, schema, config, query service, and agent/MCP/http usage with testable curl examples.
RobThePCGuy/Claude-Patent-Creator
Plugin Claude Code
Bundles 17 skills, 16 commands, 13 agents, 2 hooks · 1,399 tokens together
Complete self-contained patent creation system - NO MCP server required. Uses Claude Code skills, agents, commands, and hooks.
Skill Claude CodeCodex
Create personalized triathlon, marathon, and ultra-endurance training plans. Use when athletes ask for training plans, workout schedules, race preparation, or coaching advice. Can sync with Strava to analyze training history, or work from manually provided fitness data. Generates periodized plans with sport-specific…
Plugin Claude Code
Bundles 12 skills · 1,766 tokens together
Advisor-facing systems and workflows. Teaches Claude how advisor platforms work so it can help design, evaluate, or integrate with them. Covers the full advisor workflow from onboarding through reporting.
Cursor rule Cursor
After relay-ai code changes, always build and npm link — Jacob does not run this manually.
Skill Claude CodeCodex
Implement OAuth 2.0 authentication flows including authorization code with PKCE, client credentials, and device code for secure API integration. Use when the user requests oauth 2 0 setup or provides relevant inputs for this workflow.
Skill Claude CodeCodex
Use compact wrappers when running routine Maven builds and tests, supported npm/Node test workflows, or Go tests. Select mvn-lite for supported Maven build and test workflows, npm-lite for npm run verify, npm run test:unit, or node --test, and go-lite for go test.
nerdai/llm-agents-from-scratch
Skill Claude CodeCodex
Compute a sequence for a given starting number by repeatedly calling the nextnumber tool until the value 1 is reached.
Skill Claude CodeCodex
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
Skill Claude CodeCodex
Search the web and query AI models via Perplexity AI using perplexity-web-mcp-cli. Supports CLI commands (pwm ask, pwm research), MCP tools (pplx), and Anthropic/OpenAI-compatible API server. Use when the user mentions "perplexity", "pplx", "pwm", "web search with AI", "deep research", "search the internet", or wants…
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task, before touching code. Produces detailed implementation plan documents with per-task design specs, acceptance criteria checklists, dependency graphs, and risk registers. Use for: (1) new feature implementation planning, (2) system migration/refactoring…
Skill Codex
Audit and fix UI quality issues across web apps, dashboards, landing pages, product sites, forms, dialogs, tables, component libraries, and rendered frontend flows. Use when the user asks for UI walkthrough, visual QA, pixel/detail review, dimensions, spacing, whitespace, color hierarchy, alignment, typography, icon…
MCP server Claude CodeCodexCursor +2
MCP server "civ6" as configured in lmwilki/civ6-mcp. Runs locally from the . Python package.
Skill Codex
A terminology helper for Vibe Coding tasks, where software is built from natural-language requests. It turns vague descriptions into clearer technical wording and identifies useful terms for interface, web, software, Git, AI-agent, or design concepts.
terryso/claude-code-playwright-mcp-test
Cursor rule Cursor
Cursor rule "cmd" from terryso/claude-code-playwright-mcp-test, covering command rules documentation, general execution principles, test case execution commands, mandatory report generation process and test suite execution commands.
Skill Claude CodeCodex
Browser automation skill for AI agents using the mb CLI. Use when the agent needs to browse the web, take screenshots, scrape text, fill forms, click elements, record screencasts, run JS in pages, or audit designs. Triggers on: "browse", "open a page", "take a screenshot", "scrape", "fill form", "click button", "web…
MCP server Claude CodeCodexCursor +2
MCP server "mcp-usecases" as configured in braincrew-lab/mcp-usecase. Runs locally from the mcp-usecases Python package.
Skill Claude CodeCodex
Cross-site scripting skill vision validation.
Skill Claude CodeCodex needs its repo
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.
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: