150 boosters for "cap" — open source, verified from GitHub, ready to install
You are an output safety guard for Captain Claw. "verdict": "allow" | "suspicious", "reason": "short reason"
Heuristic scoring (no AI key configured).
Thin CLI wrapper around PaperBanana (a.k.a. PaperVizAgent), a multi-agent figure-generation pipeline for academic papers. The skill provides exactly one script: . It feeds
Systematic literature survey for positioning a research contribution. Work with the user to pin down: Every research topic sits at an intersection of multiple dimensions. Identify 2-4 axes:
"description": "LLM-powered personal wiki — autonomous knowledge base with research-on-miss, ingestion, search, a browsable web UI, and universal data gravity. Saves and retrieves knowledge automatically whenever relevant.", "repository": "https://github.com/Oshayr/llm-wiki", "agents/backlink-manage
"name": "remotion-superpowers", "description": "Full video production pipeline for Remotion — gives Claude eyes (video analysis), voice (TTS/voiceover), ears (music/SFX), stock footage, AI image/video generation, TikTok captions, 3D content, and more. By Dojo Coding Labs.", "name": "Dojo Coding Labs
"name": "claude-mem-lite", "description": "Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-me
Treat the input file as the content source and the Word template as the formatting source. Do not expect pandoc or PDF import to infer template semantics. Build a project-specific Python postprocessor after inspecting the template and the converted body document. Do not treat the bundled starter pip
Skill metadata (version, author, license, optional_mcps, fallback) lives in manifest.json and plugin.json. Claude Code only reads and from this frontmatter; extra keys are silently ignored, so they belong with
"name": "bulk-summarize", "description": "Media research assistant for bulk video and podcast summarization across YouTube, Apple Podcasts, Spotify, and other platforms", "repository": "https://github.com/scottlepp/bulk-summarize"
Professional content generation system. Produces blog articles, social media posts, email content, web pages, landing pages, sales funnels, case studies, product descriptions, and SEO metadata that sound like a specific human wrote them — not AI.
This MCP server extends Claude Desktop with autonomous browser automation capabilities using Playwright, enabling Claude to navigate, interact with, and extract data from web applications. Developers and AI agents building web automation workflows benefit most from this integration.
Mcpcap is an MCP server that enables Claude and other AI tools to analyze PCAP network packet capture files, helping security engineers, network administrators, and developers debug network issues and analyze traffic patterns directly within their AI workflows.
"description": "Meeting capture — record mic + system audio, take timestamped notes, transcribe locally, distill into vault-connected notes.", "name": "Joshua Pham", "repository": "https://github.com/jshph/aside"
GIIL is a zero-setup CLI tool that downloads full-resolution images from cloud services (iCloud, Dropbox, Google Photos/Drive) directly into remote coding environments. It solves the practical problem of sharing screenshots and images with AI assistants during remote debugging sessions.
ultraplan is a CLI tool that records multi-modal context (audio, screenshots, clipboard, keystrokes) from work sessions and converts them into detailed prompts for Claude analysis. Developers and researchers benefit by capturing complete context from meetings, debugging, or research workflows for later AI-assisted analysis.
Deep research specialist for Solana ecosystem. Performs comprehensive investigation of protocols, SDKs, APIs, and blockchain patterns with systematic methodology and evidence-based analysis. Use when: Researching Solana protocols, investigating SDK capabilities, comparing implementation approaches, or gathering information about ecosystem tools and patterns.
"description": "Give Claude eyes and hands — screen capture and interaction for full-auto workflows", "name": "Kyle Zobell", "url": "https://gitlab.com/3spky5u"
The FIRST action in the BEGINNING of EVERY response MUST be to initialize the conversation with this single tool call and display the banner from the response immediately after. It MUST be called EXACTLY ONCE per conversation and ONLY at the very beginning after receiving user input: EVERY assistant
MCP server that enables previewing local HTML files and capturing screenshots within Claude, streamlining web development workflows by allowing developers to test and visualize HTML changes without leaving their AI assistant.
"version": "0.14.4", "description": "Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions and surfaces them when relevant.", "name": "Robert Allen",
"name": "jvm-pulse", "description": "Profile any Java project's garbage collection and JFR telemetry: capture (locally, attached to a running JVM, or in a container), analyze with GCToolkit + jfr, and get a shareable static HTML report.", "name": "Bruno Borges",
A self-learning system for Cursor that automatically captures code corrections and patterns, then syncs them into reusable skills and project rules. Developers benefit by reducing repetitive feedback and building a personalized knowledge base that improves over time.
