137 boosters for "cap" — open source, verified from GitHub, ready to install
A Playwright-based toolkit for testing local web applications, enabling developers to verify frontend functionality, debug UI behavior, and capture browser diagnostics. Essential for AI coding assistants building and validating web applications.
"name": "claude-mem", "version": "10.4.1", "description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
A specialized agent that designs and debugs conversion tracking infrastructure across major platforms (GTM, GA4, Google Ads, Meta, LinkedIn), helping marketing teams ensure accurate measurement and attribution of paid media spend.
A hands-on short-video editing coach that guides users through the complete post-production pipeline across CapCut Pro, Premiere Pro, DaVinci Resolve, and Final Cut Pro. Ideal for content creators, video editors, and filmmakers seeking professional-grade editing expertise and workflow optimization.
MCP Builder is an expert agent that designs, builds, and tests Model Context Protocol servers to extend AI capabilities with custom tools, resources, and integrations. Developers and AI engineers use it to rapidly create reusable MCP servers for APIs, databases, and workflow automation.
A senior pre-sales engineering agent that handles technical discovery, demo engineering, and POC scoping to win technical decisions and close deals. Ideal for B2B SaaS teams, sales leaders, and product managers who need to bridge technical capabilities with business outcomes.
A meta-guide that helps users create or update specialized skills to extend Codex's capabilities with domain-specific knowledge and workflows. Developers and AI agents building custom extensions benefit from this structured approach to skill development.
This booster enables OS-level desktop and window screenshot capture when users explicitly request it or when tool-specific capabilities are unavailable. Developers and AI assistants benefit from having a fallback capture mechanism for debugging, documentation, and UI inspection tasks.
Generates repository-grounded threat models that identify trust boundaries, assets, attack paths, and mitigations in application code. Ideal for security engineers and developers performing AppSec threat modeling on specific codebases.
Automates the conversion of conversations and decisions into organized Notion wiki entries, how-tos, and FAQs with proper linking. Ideal for teams wanting to systematize knowledge capture and avoid losing context from chats and notes.
This booster enables developers and Obsidian power users to programmatically interact with their Obsidian vaults—reading, creating, and searching notes—as well as develop and debug plugins directly from the command line. It's ideal for users who want CLI-based vault automation or are building Obsidian extensions.
Heuristic scoring (no AI key configured).
Yielding Bear provides a single unified API that routes every LLM request to the cheapest capable model across 16+ providers — saving 60-80% vs calling OpenAI, Anthropic, or Google directly. 1. Get an API key at https://yieldingbear.com/api 2. Set environment variable:
MIRIX is a Multi-Agent Personal Assistant with an Advanced Memory System. It features a six-agent memory architecture (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) with screen activity tracking and privacy-first design. 1. Follow PEP 8 strictly 3. Documentation
"description": "A Model Context Protocol (MCP) server for Grafana providing access to dashboards, datasources, and querying capabilities", "name": "Grafana Labs" "homepage": "https://github.com/grafana/mcp-grafana",
Try these methods in order. Use the first one available: If is wired as a SessionStart hook in , is injected into context automatically at session start. Skip step 1 below. To wire it: or run .
Diagnose and fix the most common Granola issues. Each error includes platform-specific symptoms, root causes, and step-by-step remediation. Granola captures audio from your device's system audio output (not via meeting platform APIs), so most issues trace back to audio permissions or device configur
Each agent inherits from and uses a shared object that stores: All providers implement the same interface, making them interchangeable at runtime: Switch provider via or CLI flag.
This booster claims to be a Vue.js ReCAPTCHA component, but the actual content describes an OpenSpec workflow tool unrelated to the stated purpose.
"name": "claude-reflect", "description": "Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically", "name": "Bayram Annakov",
Browse once, cache the APIs, reuse them instantly. First call discovers and learns the site's APIs (~20-80s). Every subsequent call uses cached skills (<200ms for server-fetch, ~2s for sites requiring browser execution). When the task touches docs, install guidance, eval claims, landing-page copy, r
"name": "antigravity-skills", "description": "Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.", "email": "guanyangsunlight@gmail.com",
provides cross-platform abstractions for: Persistent key-value storage: 1. Use Schema validation - Validate all external data
