4,723 boosters for "r" — open source, verified from GitHub, ready to install
"description": "AI-assisted spec crafting through research, interviews, and multi-LLM review. Like Geppetto carved Pinocchio from wood, transform rough ideas into living implementation plans.", "name": "Leonardo Flores", "url": "https://github.com/leonardocouy"
A skill booster that helps developers add delightful UX moments—joy, personality, and unexpected polish—to interfaces, transforming functional designs into memorable experiences. Benefits product teams and frontend developers who want to elevate user engagement.
Heuristic scoring (no AI key configured).
"name": "semantic-search", "description": "Search your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.", "name": "Omar Drljevic"
"name": "phdtaketaketake", "description": "Connection-first PhD advisor matcher — finds the right advisor by network strength, not h-index. Evidence-first: every signal traces to a real source the agent fetched. Best-supported for physics / MSE; extensible to other STEM with field-specific caveats."
"name": "learnship", "description": "Agentic engineering done right — 49 structured workflows, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.", "name": "Favio Vazquez",
"description": "Use Claude Code As Is - native plugin leveraging built-in architecture", "keywords": ["workflow", "agents", "hooks", "native"],
"name": "claude-code-toolkit", "name": "Scott Spence" "description": "Productivity and ecosystem tools for Claude Code",
"name": "oh-my-claudecode-research", "description": "Research-team agents for Claude Code: supervisor, analysis-implementer, paper-writer, figure-descriptor, reviewer, literature-curator.", "author": { "name": "Young-Eun Lee" },
Use when organizing media files (movies, TV, anime) on NAS or local storage - cleaning junk files, merging scattered episodes, normalizing folder names to "Title (Year)" format, and verifying episode completeness against TMDB
A Claude Code skill that converts PDFs to Markdown format, supporting large files and Korean paths while avoiding common encoding issues. Developers working with PDF processing in coding tasks benefit from this automation.
"description": "Find funding opportunities, manage projects, grants, milestones, and updates on the Karma protocol", "url": "https://karmahq.xyz" "repository": "https://github.com/show-karma/skills",
You are a writing editor that strips AI-isms from Malaysian Bahasa Melayu writing. Content AI dalam BM ada "accent" sendiri, yang pembaca Malaysia boleh spot dalam 3 saat je. Kerja kau, buang accent tu, supaya tulisan bunyi macam manusia Malaysia betul-betul tulis, bukan bot. Detect the language of
A Windsurf IDE rule set designed to enforce Japanese-language communication in project interactions. Useful for Japanese-speaking development teams working with Cursor/Windsurf.
kube-audit-kit is a read-only Kubernetes security auditing skill that exports cluster resources, sanitizes metadata, and generates PSS/NSA-compliant audit reports. DevOps engineers and security teams use it to perform compliance reviews and identify security misconfigurations without cluster modification.
Rails Upgrade Assistant intelligently guides developers through Rails application upgrades from 7.0 to 8.1.1 by identifying breaking changes, deprecations, and providing step-by-step migration instructions. Essential for teams maintaining Rails applications and planning version transitions.
CortexGraph is a temporal memory system for AI assistants that implements human-like forgetting curves using local storage (JSONL and Markdown), enabling natural conversation memory across Claude, Cursor, and other platforms without explicit save commands.
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Implementer. Own code changes inside the agreed file scope and report concrete results. Prefer minimal diffs and include verification evidence. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Reviewer. Review correctness, regressions, maintainability, and test coverage. Do not modify code; report findings and recommendations. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Planner. Clarify scope, risks, dependencies, and execution order before code changes. Produce a concrete plan that an implementer can follow. Output a single JSON object (no surrounding text) that conforms to .
"name": "context-cascade", "description": "Context-saving nested plugin architecture for Claude Code. Playbooks contain skills, skills contain agents, agents contain commands. Only load what you need - context cascades down through layers on demand, saving 90%+ context space. Includes 224 agents, 17
<!-- AIOS-GENERATED: orchestrator-agents v1 --> Role: security-reviewer You are the Security Reviewer. Review auth, data handling, secrets, injection risks, and unsafe automation. Do not modify code; report security findings and mitigations.
An AI-powered MCP server that enables Claude to automate browser interactions using Playwright, allowing developers to build intelligent automation workflows directly within Claude and Cursor. Ideal for developers needing web automation, testing, and AI-driven browser tasks.
