{"data":[{"slug":"scan-modules","title":"scan-modules","description":"Scan and cache project module structure for fast Claude context loading. Use /scan-modules:scan-modules to index your codebase, then Claude auto-loads the cache each session. Supports incremental updates via git diff and auto-update via post-commit hook. Works with Swift, TypeScript, Python, Go, and Rust.","developer":"fengzhyuan","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/fengzhyuan/scan-modules-plugin.git"},{"slug":"repoatlas","title":"repoatlas","description":"AI-friendly knowledge-graph toolkit for codebases. Seven Claude/Copilot skills that survey, map, validate, and query single repos or multi-repo workspaces as markdown — no runtime, no lock-in.","developer":"Thuan Tran","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/SmallChX/repo-atlas.git"},{"slug":"repo-visuals","title":"repo-visuals","description":"repo-visuals turns any open-source repo into a bespoke README hero — animated GIF or static PNG — through a structured discovery dialog. It scans the codebase, recommends a format that fits the repo's identity (terminal demo, product UI, brand wordmark, banner, diagram-as-hero), generates tailored HTML, previews it in your browser, and exports a retina-quality artifact ready to drop into the README.\n\nKey features:\n- Five-phase craft loop: discover → build → preview → export → output\n- Three operating modes (Auto / Semi-auto / Manual) that scale from \"decide nothing\" to \"decide everything\"\n- Format-aware: GIF for motion-worthy demos, PNG when stillness reads better, HTML when the README itself can host it\n- Retina capture via Puppeteer + ffmpeg; automatic file-size and dimension validation\n- Optional 4-rater scorecard (User / Claude / Code / AI-vision-blind) for measuring craft quality across runs\n- Optional upstream PR: detects ownership, forks if needed, opens a PR with alt-text included\n- Heroes already merged into HTMLHint, Terminal.Gui, ast-graph, and others","developer":"livlign","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/livlign/claude-skills.git"},{"slug":"repo-hygiene","title":"repo-hygiene","description":"A skills library that keeps codebases healthy as coding agents work in them. Repo Hygiene injects a bootstrap at session start and auto-triggers eight sub-skills at hygiene-relevant moments — when starting work in an unfamiliar repo, writing new functions, changing public APIs, drafting commits, and applying retroactive cleanup to existing projects. Complements Superpowers: where Superpowers handles workflow disciplines (brainstorming, TDD, planning), Repo Hygiene handles the lower-level habits that should hold across every change.","developer":"gg-mo","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/gg-mo/repo-hygiene.git"},{"slug":"reef","title":"reef","description":"Structured knowledge wiki generator for codebases. Auto-discovers services, APIs, schemas, and cross-system contracts, then deepens through guided Q&A. Obsidian-native, local-first.","developer":"Eunji Jung","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/eunji-jessi-jung/reef.git"},{"slug":"public-repo-readiness","title":"public-repo-readiness","description":"Audits a codebase for secrets, PII, internal infrastructure references, and licensing issues before open-sourcing. Produces a remediation plan.","developer":"dlewis7444","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/dlewis7444/public-repo-readiness.git"},{"slug":"preflight","title":"preflight","description":"Know exactly where your system breaks before you ship. Scans codebases, traces service calls, and simulates what happens when real users hit your system. Finds bottlenecks, cost cliffs, rate limits, and breaking points.","developer":"Nancy Chauhan","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Nancy-Chauhan/preflight.git"},{"slug":"pm-ai-partner-framework","title":"pm-ai-partner-framework","description":"AI-powered skills for Product Managers — 10 agent modes for thinking, writing, analyzing, building, and decision-making. Includes 4 workflow commands (/pm:plan-week, /pm:write-brief, /pm:prep-meeting, /pm:audit-codebase) and 3 automation hooks (quality gate, draft status, commit reminder). Turn Claude into your PM thinking partner.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"ahmedkhaledmohamed/PM-AI-Partner-Framework"},{"slug":"playwright-pro","title":"playwright-pro","description":"Playwright Pro turns your AI coding agent into a senior test automation engineer.\n\nInstead of generating tutorial-quality tests with brittle CSS selectors, Playwright Pro enforces battle-tested patterns from production test suites: role-based locators, web-first assertions, proper fixture architecture, and isolated test design.\n\nIt doesn't reinvent Claude Code — it orchestrates it. /pw:generate uses the built-in Explore subagent for codebase analysis. /pw:migrate delegates to /batch for parallel file conversion. /pw:fix leverages /debug for trace inspection. Every skill builds on what Claude Code already does well.\n\n55 ready-to-use test templates across 11 categories — authentication, CRUD, checkout, search, forms, dashboard, settings, onboarding, notifications, API testing, and accessibility. Each template includes TypeScript and JavaScript variants with parametrizable placeholders. Not generic stubs — real patterns like Stripe iframe handling, GraphQL mutation testing, and RBAC permission flows.\n\n3 specialized agents handle complex planning before a single test is written: test-architect maps your application surface, test-debugger diagnoses flaky failures systematically, and migration-planner creates ordered conversion plans from Cypress or Selenium.\n\n2 MCP integrations (TypeScript) connect to TestRail (8 tools) and BrowserStack (7 tools) for teams that need test management and cross-browser coverage. Both are optional — the plugin works fully without them.\n\nSmart hooks auto-validate every test file you write (catches waitForTimeout, hardcoded URLs, non-web-first assertions) and auto-detect Playwright projects on session start. Zero overhead — they run silently.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"alirezarezvani/claude-skills"},{"slug":"outside-in-code-review","title":"outside-in-code-review","description":"Systematic codebase exploration from surface artifacts to implementation detail, producing an actionable discovery report within ~1 hour.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ythirion/outside-in-code-review-skill.git"},{"slug":"ory-lumen","title":"ory-lumen","description":"lluminate your codebase with semantic search for code agents. Faster results with less tool calls. Works great in small and large code bases.","developer":"Ory Corp","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ory/lumen.git"},{"slug":"opsera-devsecops--community","title":"opsera-devsecops","description":"Opsera DevSecOps Agent — AI-powered architecture analysis, security scanning, compliance auditing, and SQL security for your codebase. Free trial included.","developer":"Opsera","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/opsera-agents/opsera-devsecops.git"},{"slug":"open-rx","title":"open-rx","description":"Open RX makes Claude actually good at building production web apps. 7 free skills (OTC tier) covering React architecture, Next.js App Router patterns, performance optimization, prompt engineering, UX copywriting, local SEO, and the rx-writer consultation system. Every skill is packed with real patterns from real codebases — not generic boilerplate. Upgrade to The Prescription ($1) for 17 skills and 27+ reference files covering UI components, animations, SaaS patterns, database ops, API design, testing, deployment, security, conversion optimization, and brand design.","developer":"CutTheChexx","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/CutTheChexx/open-rx.git"},{"slug":"onboard","title":"onboard","description":"End-to-end Claude tooling generator for existing codebases. Performs deep codebase analysis (languages, frameworks, conventions, complexity), walks you through an interactive wizard, then generates a complete suite of Claude artifacts — CLAUDE.md files, path-scoped rules, project-specific skills and agents, hook configuration, PR templates, and commit conventions. Unlike recommendation-only tools, onboard produces actual files tailored to your project's detected patterns and enforced configs. Includes drift detection via /onboard:evolve to keep tooling aligned as your codebase changes. Also serves as the generation engine for the companion forge plugin (new projects) via headless invocation.","developer":"Apurv Bazari","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ApurvBazari/claude-plugins.git"},{"slug":"memex-mcp","title":"memex-mcp","description":"Persistent memory for AI coding agents. Builds a temporal knowledge graph of your codebase from commits and source files, then serves it through 14 MCP tools so every Claude Code session starts knowing your architecture, recent decisions, and open problems — no more cold starts or context pasting. Bitemporal facts (every edge knows when it was true), two-regime confidence decay (unvalidated facts cross stale at exactly 30 days), hierarchical Leiden clusters keep get_project_context under 1500 tokens for any repo size, and human-in-the-loop validation. Backed by Neo4j + Graphiti + Gemini Flash. Also publishes to PyPI and npm.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/STiFLeR7/claude-plugins.git"},{"slug":"memento","title":"memento","description":"Memento gives Claude Code a real memory: persistent, searchable knowledge that survives across every session, every project, and every device. Your AI remembers your codebase, your team conventions, past decisions, and the conversations you have had with it. Memory is searchable from natural language and editable on the web.\n\nThe plugin adds nine commands (/wake-up, /recall, /remember, /sleep, /handoff, /pickup, /investigate-and-cache, /scan-environment, /frame), proactive memory skills, and session lifecycle hooks. Free to start. A Memento AGI tier adds 20 autonomous coding commands on top.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mementoagi/memento-claude-code-plugin.git"},{"slug":"mem0","title":"mem0","description":"Connect Mem0 to Claude to give your agent persistent memory across sessions. Claude can store user preferences, project context, and conversation history, then search, update, or forget them as new information comes in. Useful for coding assistants that remember your codebase conventions, support agents that recall customer history, research workflows that build context over weeks, or any use case where Claude resets back to zero today. Memories are scoped per user, agent, or session. Cloud-hosted, no local install.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mem0ai/mem0.git"},{"slug":"masa","title":"masa","description":"Teach your AI coding agent the MASA (Modular Agentic Semantic Architecture) framework — maximizes how well agents can understand, navigate, and safely modify your codebase.","developer":"Eduardo Machado Rezende","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/nicolasfmelo/masa-skill.git"},{"slug":"make-it-work","title":"make-it-work","description":"Skills that make Claude actually work in your project. Not just generally, but specifically, the way your codebase is built.\n\nBuilt for engineering teams working on large, complex codebases. Not greenfield side projects. When your codebase has history, domain rules, and legacy decisions baked in, \"generally smart\" isn't enough. Claude needs to know your project.\n\ngo-deep maps your codebase from the inside out and builds a layered documentation system so every Claude session starts grounded in your project's real structure, rules, and use cases. Not generic assumptions.\n\nclose-the-gaps acts as a Product Analyst before development begins: it finds every gap in a ticket (unclear language, missing edge cases, conflicting requirements), walks you through them one by one, and outputs a Gherkin-ready refined spec.\n\nThe cost of a vague ticket is paid in rework. close-the-gaps makes sure requirements are solid before a single line of code is written.","developer":"insideout-ai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/insideout-ai/make-it-work.git"},{"slug":"local-rag","title":"local-rag","description":"Local-first semantic search for your codebase and conversation history. Hybrid vector + BM25 search with cross-encoder reranking, AST-aware chunking for 6 languages, smart chunking for 30+ file types, conversation memory across sessions, code annotations, dependency graphs, and documentation gap analysis. No API keys, no cloud — runs entirely on your machine.","developer":"TheWinci","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/TheWinci/local-rag.git"},{"slug":"llm-wiki","title":"llm-wiki","description":"Maintains docs/wiki/ as a DAG of LLM-authored pages kept in sync with the codebase. Tracks code changes via PostToolUse hooks, reconciles stale pages through background agents, lints the wiki graph, and supports EIS (Executable Implementation Spec) authoring.","developer":"Pranav","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/esxr/llm-wiki.git"},{"slug":"lean-kg","title":"lean-kg","description":"Lightweight Knowledge Graph for AI-Assisted Development\nLeanKG is a local-first knowledge graph that gives AI coding tools accurate codebase context. It indexes your code, builds dependency graphs, and exposes an MCP server so tools like Cursor, OpenCode, and Claude Code can query the knowledge graph directly. No cloud services, no external databases.\nVisualize your knowledge graph with force-directed layout, WebGL rendering, and community clustering.","developer":"FreePeak","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/FreePeak/LeanKG.git"},{"slug":"jointjs-code-playground","title":"jointjs-code-playground","description":"A Claude Code plugin to create custom JointJS-powered interactive playgrounds.\n\nIt enables you to build code maps for library/codebase architectures, data explorers for database schemas, canvas builders for drag-and-drop visual composers, diff reviewers with inline commenting and call graphs, and site explorers for interactive website/docs sitemaps.","developer":"JointJS","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/clientIO/jointjs-claude-playground.git"},{"slug":"join-meeting","title":"join-meeting","description":"AgentCall turns any AI coding agent into a meeting participant. Install the `join-meeting` command, give your agent a meeting link, and the agent joins the call as a bot with a name and visual presence — it can talk, listen, screenshare, chat, and keep working on your codebase while in the meeting. Works with Claude Code, Cursor, Codex, Gemini CLI, Windsurf, OpenClaw, Junie, and 30+ other agent frameworks.\n\nModes:\n- Audio-only — voice presence for standups and 1-on-1s\n- Webpage-avatar — voice + animated visual presence\n- Webpage-avatar-with-screenshare — full presence for presentations and demos\n\nWhat's included: real-time transcription (English, more languages coming soon), interruption handling, 54 TTS voices across 9 languages, collaborative mode with GetSun voice intelligence for natural multi-party conversations, direct mode with Kokoro TTS for latency-sensitive 1-on-1 interactions.\n\nAPI key required (free sign-up, no credit card): https://app.agentcall.dev","developer":"AgentCall, Pattern AI Labs","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/pattern-ai-labs/agentcall.git"},{"slug":"ix-memory","title":"ix-memory","description":"Ix Memory connects Claude Code to Ix, a structured, persistent memory backend for codebases. Instead of reading raw source files to answer questions about your code, Claude queries a live knowledge graph — dramatically reducing token usage, improving accuracy, and enabling reasoning that scales to large, complex projects.\nAll analysis runs locally on your machine. No source code is ever transmitted to external servers.","developer":"Ix Memory","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ix-infrastructure/ix-claude-plugin.git"},{"slug":"ido4specs","title":"ido4specs","description":"ido4specs is the bridge between a strategic spec and GitHub issues. It analyzes your codebase, decomposes capabilities into implementation tasks with effort, risk, type, and dependency metadata, and produces a structurally-validated technical spec any downstream tool can consume.\n\nKey features:\n- Code-grounded decomposition - parallel Explore subagents ground every task in concrete files, services, and patterns from your actual codebase (not fabricated from the spec)\n- Structured output enforced by a bundled zero-dependency parser - every task carries effort (S/M/L/XL), risk (low → critical), type (feature/infrastructure), AI-suitability (full/assisted/pair/human), and dependency graph\n- Two-layer validation - deterministic structural parser + independent qualitative review before handoff\n\nBuilt for tech leads, staff engineers, and founder-engineers who want to skip the manual decomposition tax.","developer":"Bogdan Coman","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/ido4-dev/ido4specs.git"},{"slug":"hig-compliance-auditor","title":"hig-compliance-auditor","description":"Audits codebases and design systems against Apple's Human Interface Guidelines. Scans SwiftUI, UIKit, CSS, HTML, and JavaScript for HIG violations across iOS, iPadOS, macOS, watchOS, tvOS, visionOS, and Web/PWA targets. Generates structured compliance reports with severity tiers (Critical, High, Medium, Low), platform-specific guidance, accessibility audit results, and actionable remediation options. Applies fixes on user approval with inline attribution comments referencing the specific HIG guideline violated. Covers typography and Dynamic Type, semantic color systems, Dark Mode architecture, Liquid Glass material usage, layout and safe areas, touch target sizing, SF Symbols compliance, App Store Review Guidelines 2025/2026, and AI transparency requirements.","developer":"Om Rajguru","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/omrajguru05/hig-compliance-auditor.git"},{"slug":"hackflow-ppt","title":"hackflow-ppt","description":"AI-powered hackathon PPT generator for Claude Code. One /ppt command to\n   analyze your project codebase, choose from 6 stunning visual styles\n  (Gradient Glass, Apple Vision, Google Material, Microsoft Fluent,\n  Vercel Mono, Linear Mesh), and generate 4K presentation slides using\n  Gemini 3.1 Flash Image. Supports custom style creation — describe your\n  vision and AI writes a complete style template. Content is\n  auto-structured around 6 hackathon judging dimensions with storytelling\n   hooks for maximum pitch impact. Outputs a ready-to-present PPTX file.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/qwwzdyj/hackflow-ppt-skill.git"},{"slug":"gsd-plugin","title":"gsd-plugin","description":"Get Shit Done Plugin - handles large codebase contexts - structured workflow plugin for Claude Code with 60+ slash commands, 21 agents, MCP server, hooks, and cross-session memory","developer":"Jasper Nuyens","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jnuyens/gsd-plugin.git"},{"slug":"grill","title":"grill","description":"Grill runs six specialized agents (recon, architecture, error handling, security, testing, edge cases) in parallel against a codebase, then synthesizes their findings into one report with severity tags, file:line evidence, proposed changes, effort estimates, and explicit tradeoffs. Five review styles let you tune intensity from quick scan to Paranoid Mode. Eight optional add-on pressure tests target specific failure modes (concurrency, observability, dependency hygiene, etc.). Zero-findings is reported explicitly as `[GOOD]` — no padding with manufactured issues.","developer":"xiaolai","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/xiaolai/grill-for-claude.git"},{"slug":"graperoot","title":"graperoot","description":"Dual-graph code context engine for Claude Code. Builds a structural call graph and dependency graph of your codebase, then delivers precise file and symbol recommendations before Claude starts exploring. Reduces token usage by up to 60% and improves code accuracy by guiding Claude to the right files first. Supports TypeScript, JavaScript, Python, Go, Rust, Java, C/C++, and 10+ more languages. Install via pip, no source code required, fully compiled","developer":"Krishnakant","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/kunal12203/graperoot-plugin.git"},{"slug":"gortex","title":"gortex","description":"Your AI's live map of your codebase — every call, dependency, and contract indexed across your repos, shared across every running agent via a local daemon. Gives Claude Code 52 graph-aware tools so they answer \"what calls this?\", \"what breaks if I rename UserStore?\", or \"which services consume this endpoint?\" in one call instead of grepping for minutes. Real AST parsing across 92 languages — deterministic, zero LLM calls during indexing. Useful before refactoring, when tracing bugs across services, exploring unfamiliar code, or any time your agent reaches for Grep or Read. Returns precise answers tagged with confidence tiers (compiler-grade vs heuristic). Local-first, source-available, free under defined thresholds.","developer":"Andrey Kumanyaev","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/gortexhq/claude-plugin.git"},{"slug":"ghost-architect","title":"ghost-architect","description":"Codebase triage for Adobe Commerce and ecommerce platforms. Scans your project, categorizes risk by pattern, and gives your team a prioritized map of where to start — before you touch a line of code. Code never leaves your machine.","developer":"Ernst Wisner","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/EJWisner/ghost-architect-plugin.git"},{"slug":"gemini","title":"gemini","description":"Use Gemini CLI from Claude Code to review code, analyze codebases, or delegate tasks. Leverages Gemini's 1M token context window for whole-codebase analysis.","developer":"Alberto Resco Perez","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/arescope/gemini-plugin-cc.git"},{"slug":"first-principles-review","title":"first-principles-review","description":"A Claude Code skill that reviews codebases top-down: WHY (goal) → WHAT (architecture) → HOW (implementation) → improvements ranked by leverage. The antidote to surface-level LLM nitpick reviews.","developer":"Cody Hergenroeder","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/codyhxyz/first-principles-review.git"},{"slug":"fde-os","title":"fde-os","description":"FDEOS makes Claude operate like an experienced Forward Deployed Engineer.                                                                                                        It brings the judgment FDEs need that generic AI lacks: when to challenge\nthe brief, how to earn trust before touching code, how to build safely in\na codebase you did not create, and how to hand over clean when the\nengagement ends. 13 skills covering the full FDE lifecycle from first\nmeeting to final handoff. Enterprise overlays for healthcare (HIPAA),\nfintech (PCI-DSS), and government (FedRAMP) activate when the context\nis detected","developer":"Subash Natarajan","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-09T06:00:00.417Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/suboss87/FDEOps"}],"total":125,"page":2,"per_page":36,"observed_at":"2026-11-09T06:00:00.417Z","source_counts":{"web":529,"demo":12,"skills":5,"official":317,"community":2283,"knowledge-work":123}}