478 boosters for "du" — open source, verified from GitHub, ready to install
Execute verbatim. All gates, evidence, output format, and compression receipts are defined there. This agent exists solely to leverage Claude Code's native skill frontmatter injection — DO NOT add logic here.
Automatically inserts checkpoint calls into jamovi R functions to enable incremental result rendering and change detection during long computations. Useful for jamovi module developers seeking to improve user experience with progress visibility.
"name": "quantum-loop", "description": "Universal CLI orchestrator with multi-runner support. Autonomous spec-driven development with dependency DAG, parallel worktree execution, two-stage review gates, and modular merge hardening.", "name": "andyzengmath"
Generate professional, high-converting email copy using proven copywriting frameworks. Produces subject line variants with scoring, responsive HTML templates with dark mode support, plain-text fallback, and preheader recommendations. This sub-skill is invoked by the main skill when the user needs t
"description": "Spec-driven development for big features. When features get too big, plan mode gets too vague—leading to hallucinations during implementation. ShipSpec replaces vague plans with structured PRDs, technical designs, and ordered tasks that keep Claude grounded.", "repository": "https://
This sub-skill generates a complete email marketing strategy tailored to your business type, including: Invoked by from the main email skill. First, check if exists and contains business type. If not, analyze context signals:
"name": "prfaq-dev", "description": "Amazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making", "name": "Punt Labs",
A Claude agent designed to assist with product management tasks by leveraging library components and established patterns. Useful for product managers and teams seeking AI-assisted analysis, planning, and decision-making workflows.
CurlsBotSite is a Cursor rules booster for a Next.js haircare ingredient analyzer app, providing project-specific coding standards and architecture guidelines for TypeScript/React development. It benefits developers working on this specific project who need consistent style, testing, and library usage patterns.
"name": "laravel-api", "name": "Steve King", "email": "steve@juststeveking.com"
ADHARA is an LLM system prompt that enables early detection of learning friction by analyzing behavioral metrics like mouse hesitation, attention, and task performance against age-appropriate baselines. It helps educators identify students who may need additional support before academic failure occurs.
Total Recall preserves Claude Code session context before resets or token limits, enabling seamless context restoration across interruptions. Developers working on complex, long-running projects benefit most from avoiding context loss and rework.
"description": "Build your PMF context layer - reference files that capture the 'WHY' behind your product. Claude uses these files when building anything for your product.", "name": "Adi Shmorak", "email": "adi@adidacta.com"
"name": "arkhe-claude-plugins", "description": "Supercharge Claude Code with 118 specialized components — from deep reasoning and autonomous dev loops to DDD architecture, design system enforcement, and git workflow automation. 29 agents, 33 commands, 56 skills across 14 modular plugins." "source":
"name": "inclusive-design-skills", "description": "Agentic skills for designing accessible, inclusive products — from cognitive accessibility to adaptive interfaces, inclusive research, and accessibility decision-making.", "cognitive-accessibility",
"name": "medical-mcps", "version": "0.1.17", "description": "Comprehensive biological and medical research data integration server providing unified access to 13+ specialized databases including Reactome (pathways), KEGG (pathways/diseases), UniProt (proteins), ChEMBL (drug discovery), PubMed (liter
Transforms rough prompts into production-ready LLM prompts using advanced techniques like Chain-of-Thought and RAG optimization. Ideal for developers, AI engineers, and teams building LLM applications who need to craft effective prompts across Claude, GPT, Llama, and other models.
A TypeScript skill for integrating slimdown-js, a lightweight (~2.8 kB) regex-based Markdown-to-HTML parser, enabling developers to quickly convert Markdown to safe HTML without heavy dependencies on client or server.
Deep Research is an advanced web research booster using Graph-of-Thoughts methodology to investigate fast-changing topics through hypothesis testing, source triangulation, and multi-tier analysis. It's designed for users and developers needing rigorous, current information on evolving subjects.
This booster automates dependency management and security updates through Renovate configuration, with built-in auditing and deduplication tools. Teams benefit from reduced manual maintenance overhead and improved supply chain security.
"description": "Plan-to-code pipeline: automated planning with 5-actor verification, then TDD execution with parallel agents. Formerly beast-plan.", "name": "Dmitrii Malakhov" "skills": "./skills/"
Dux Lite provides a unified development ruleset for PHP backend, template, and controller code—enforcing naming conventions, parameter handling, and data output patterns. Teams using the Dux framework or similar PHP architectures benefit from standardized practices that improve readability and maintainability.
A photo generation skill that uses ByteDance Seedream 4.5 to create professional AI-enhanced portraits, group photos, and edited images across 8+ use cases. Useful for designers, marketers, and content creators who need quick, high-quality visual assets.
"name": "enterprise-team", "displayName": "Enterprise Team - Hire a Whole Company", "description": "Complete virtual company with 76 specialized AI agents across Engineering, Product, Infrastructure, Data, Security, Marketing, Sales, Finance, Legal, and People. Pipeline modes (Full/Sprint/Micro), De
