150 boosters for "cap" — open source, verified from GitHub, ready to install
"name": "moodle-dev", "description": "The most complete Moodle development toolkit: 13 skills, 8 slash commands, 2 subagents — covering scaffolding, XMLDB, capabilities, web services, Hooks API, AMD JS, PHPUnit, Behat, security, privacy/GDPR, performance, accessibility, themes, mobile, and cross-ver
"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"
An enhanced MCP server for Coolify that enables AI assistants to automate deployment, infrastructure management, and DevOps tasks directly through Claude, Cursor, or Windsurf. Ideal for developers and platform engineers managing self-hosted applications who want AI-assisted infrastructure automation.
"description": "FHE-encrypted organizational memory for teams. Capture and retrieve institutional knowledge with zero-knowledge privacy.", "name": "Sunchul Jung", "email": "zotanika@cryptolab.co.kr"
ICS is an interactive context file editor for Claude Code that provides templating, vim mode, and semantic analysis capabilities to help developers efficiently manage and organize project context. It benefits developers using Claude Code who need structured ways to maintain and edit context files for AI-assisted coding workflows.
"version": "5.10.0", "description": "Memory → Evaluation → Credential → Access Control for AI agents. Persistent memory with W3C Verifiable Credentials, capability-based access control, drift detection, and FSRS-6 spaced repetition.", "name": "kobie3717",
"name": "radar-suite", "description": "Six-skill audit suite for iOS/Swift codebases: data models, UI paths, data round-trips, time bombs, visual quality, and capstone grading. As of v2.0 every finding is classified on a 3-axis framework (real bug / scatter / dead code) with mandatory coaching citat
A system prompt for autonomous AI agents operating within local development environments using MCP servers, designed for developers building sovereign, locally-controlled AI systems with governance protocols.
"owner": { "name": "Covenant" }, "description": "Covenant plugins for Claude Code.", "name": "covenant-guard",
A macOS screenshot skill that captures application windows using ScreenCaptureKit, enabling Claude Code to document UI states and verify visual changes. Developers and users benefit from automated screenshot capture integrated into their coding workflow.
"name": "agent-recorder", "description": "Local-first flight recorder for Claude Code - captures MCP tool calls, subagents, and skills without recording prompts or chain-of-thought", "name": "Edyta Kucharska"
"name": "claude-rock", "id": "claude-rock", "name": "Truong Vu",
"name": "cre-skills", "description": "112 institutional-grade CRE skills covering ~97% of commercial real estate workflow steps. Deal screening, underwriting, structuring, due diligence, capital markets, market research, asset management, leasing, investor relations, development, disposition, sourci
"description": "Captures Claude Code run transcripts for debugging and review", "name": "Andre Bremer", "url": "https://andrebremer.com"
"$schema": "https://plugins.claude.ai/schema/marketplace.json", "description": "Browser automation and AI agent skills for Notte. Run real cloud or local browsers, scrape JavaScript-rendered pages with Pydantic-typed output, drive multi-step workflows behind auth and captchas, and deploy any browser
A migration guide for transitioning from deprecated hardcoded agents to a dynamic ConfigurableAgent system in a Rust-based agentic chatbot server. Developers maintaining or upgrading agent-based systems benefit from clear configuration patterns and best practices for multi-provider LLM setups.
The Weekly Recap Agent automatically generates comprehensive progress reports by scanning git repositories and project activity, helping developers track weekly achievements across multiple projects. Ideal for project managers, individual contributors, and teams who need structured weekly summaries.
Enables AI coding agents to control and test Compose Desktop applications via HTTP, automating UI interactions like clicks, text entry, and screenshots. Developers building or testing Compose Desktop apps with AI assistance benefit most.
"name": "ai-quick-starter", "description": "Bilingual Claude Code skill collection for repository engineering, research, refactoring, documentation, and capture workflows.", "email": "astro_air@126.com",
The plan-generator transforms high-level product requirements into executable project blueprints (genesis.xml files) with structured task DAGs and agent assignments. It's invaluable for cofounders and product teams who need to bridge strategic vision with concrete execution plans.
This booster helps developers quickly resume work on a SaaS UI Component Generator project by automatically reviewing project status, recent accomplishments, and next priorities from organized documentation. Ideal for teams returning to complex full-stack projects after breaks between sessions.
A Model Context Protocol server that enables Claude to create and manage collections of web entities (companies, people, papers) with automated search and enrichment capabilities via the Exa Websets API. Ideal for researchers, competitive analysts, and developers building AI-powered entity management systems.
Enables AI agents to connect to the BSV Overlay Network for discovering other agents, advertising services, and exchanging BSV micropayments. Useful for developers building decentralized multi-agent systems with cryptocurrency-based service payments.
PrismBench enables developers to create specialized LLM agents through YAML configuration for systematic evaluation of model capabilities using Monte Carlo Tree Search. Useful for ML engineers, researchers, and teams building production LLM systems who need comprehensive benchmarking and evaluation frameworks.
