By fadrienne
Data collection and automation skills: Apify scraping, browser automation, and Google NotebookLM programmatic access.
Scrape social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps business search with contact/review extraction, Amazon products/reviews/pricing, and multi-page web crawling with custom pageFunction extraction. File-based TypeScript wrappers filter data in code before it reaches model context (95-99% token savings vs MCP); parallel multi-platform queries; Google Maps -> LinkedIn lead enrichment. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business intelligence, multi-platform social listening, competitive analysis, lead generation, social monitoring, Apify actors, web crawl, extract contacts. NOT FOR X/Twitter operations (use _X), 4-tier progressive scraping with proxy escalation (use BrightData), parallel headless automation with auth profiles (use Browser), or real-Chrome bot bypass and computer use (use Interceptor).
Web browser automation with AI-optimized snapshots for claude-flow agents
Complete programmatic access to Google NotebookLM, including capabilities not exposed in the web UI. Use when creating notebooks, adding sources (URLs, YouTube, PDFs, audio, video, images), chatting with notebook content, generating artifacts (audio overviews, summaries, etc.), or downloading NotebookLM results in various formats.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A repo containing a personal knowledge vault and a collection of AI-powered tools.
An AI-enhanced personal knowledge management system built on Obsidian. Open the Obsidian Mind/ folder as your vault root in Obsidian. Features lifecycle hooks, slash commands for common workflows, and multi-agent support (Claude Code, Codex, Gemini).
See CLAUDE.md for the full operating manual.
A bundle of 20 Claude Code skills for the scientific research lifecycle, plus 13 reusable prompts and a 4-agent subagent team (researcher, reviewer, writer, verifier). Skills cover the full pipeline from literature search and hypothesis generation through paper writing, peer review, and compute orchestration.
Skills include: alpha-research, autoresearch, deep-research, literature-review, paper-writing, peer-review, paper-code-audit, replication, source-comparison, ml-training-recipe, docker, modal-compute, runpod-compute, eli5, jobs, preview, session-log, session-search, contributing, watch
See feynman/AGENTS.md for agent conventions and feynman/skills/ for individual skill docs.
A design skill for AI coding assistants that makes generated UIs look made, not generated. Use for building new pages, auditing existing designs, redesigns, and extracting design patterns from URLs or screenshots.
Key features:
See hallmark/SKILL.md for usage.
A memory-centric agentic system for the full scientific research lifecycle, powered by Claude Code. Handles everything from literature ingestion and idea generation through experiment execution to paper writing and conference rebuttal.
Key features:
See autosci/README.md for setup and usage.
Python automation client for Google NotebookLM. List, create, and interact with notebooks; add URL sources; chat with content; and generate audio overviews — all from the command line or Python scripts.
See notebooklm/README.md for setup and usage.
A business dashboard for tracking key metrics and performance indicators.
See thrive-hub/ for details.
An open-source AI-powered software factory by Garry Tan (YC President & CEO) that transforms Claude Code into a virtual engineering team. Provides 23+ specialized skills covering the full product development lifecycle — from strategic planning and design through QA, security audits, and shipping.
Key features:
See gstack/README.md for setup and usage.
A curated collection of 24 Claude Code skills for scientific research, adapted from the K-Dense-AI open-source library. Covers the full research workflow from literature discovery through data analysis, molecular modeling, and publication.
Skill categories:
See scientific-agent-skills/README.md for setup and usage.
Claude-flow v3 development skills: swarm orchestration, SPARC methodology, hooks automation, stream chaining, verification/quality, and the nine v3 architecture workstreams (CLI, core, DDD, integration, MCP, memory, performance, security, swarm coordination).
Audits AI instruction sets (CLAUDE.md, system prompts, skills) for over-prompting and prompt bloat.
GitHub workflow skills: code review, multi-repo coordination, project management, release management, workflow automation, repo importing, skill building, and pair programming.
AgentDB skills for vector search, memory patterns, optimization, learning plugins, and ReasoningBank adaptive-learning integration.
Research, reasoning, and writing skills: arXiv lookup, Fabric patterns, wisdom extraction, multi-agent debate, first-principles reasoning, root cause analysis, systems thinking, scientific writing, and story writing.
npx claudepluginhub p/fadrienne-data-tools-plugins-data-toolsA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 64 agents, 261 skills, 84 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
UI/UX design intelligence. Searchable local database with 84 styles, 161 palettes, 73 font pairings, 25 charts, and 17 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, Three.js). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.