{"data":[{"slug":"code-review--demo","title":"code-review","description":"Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives","developer":"Boris Cherny","category":"productivity","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Demo"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/anthropics/claude-code/tree/main/plugins/code-review"},{"slug":"engineering--knowledge-work","title":"Engineering","description":"Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Knowledge Work"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/anthropics/knowledge-work-plugins/tree/main/engineering"},{"slug":"ireview","title":"ireview","description":"AI-to-AI code review router. Any OpenAI-compatible model reviews your code. No Codex CLI or Node.js required.","developer":null,"category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/ilang-ai/iReview.git"},{"slug":"review-all","title":"review-all","description":"Comprehensive, project-agnostic, multi-agent code review for Claude Code with verification to eliminate false positives.","developer":null,"category":"development","reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/ncoevoet/claude-review-all"},{"slug":"zsl-superpowers","title":"zsl-superpowers","description":"An opinionated end-to-end engineering workflow: grill yourself on the spec, write a PRD, slice it into vertical-slice issues, fan out parallel TDD, and ship one consolidated PR. Plus standalone helpers for triage, diagnose, code review, architecture cleanup, and prototyping.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/ZunoSmartLabs/zsl-superpowers.git"},{"slug":"wizard","title":"wizard","description":"Wizard turns any recurring task you do with AI into a reusable workflow (\"a spell\") that runs in one command. At its core it's a meta-builder: it interviews you about a task you already do, drafts a tested SKILL.md, and saves it to your personal library. Or point it at a chat session that worked and it'll infer the spell directly. Ships with 25 hand-crafted spells covering research, writing, decisions, planning, status updates, code review, debugging, and more — plus the meta-builder that lets you grow your own. Every generated spell is end-to-end-tested before being saved (Iron Law). MIT, no telemetry.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/redhuntlabs/wizard.git"},{"slug":"ultraship","title":"ultraship","description":"All-in-one builder toolkit for Claude Code. 22 automatic skills, 20 tools, 5 agents. Covers the full dev lifecycle — brainstorming, planning, TDD, code review, frontend design, SEO/GEO/AEO audits, Lighthouse performance, security hardening, and deployment. Skills activate automatically based on context. Run /ship to get a full ship-readiness scorecard.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/Houseofmvps/ultraship.git"},{"slug":"tap","title":"tap","description":"Cross-model AI agent communication protocol. Connect Claude, Codex, and Gemini agents through a shared file-based messaging layer. Features include: control tower orchestration, cross-model code review routing, broadcast/DM/CC messaging, agent heartbeat monitoring, mission tracking with kanban board, web GUI dashboard, and generational knowledge transfer through retros, letters, and findings.\n\nOther tools give agents instructions. tap gives them context.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/HUA-Labs/tap.git"},{"slug":"stackpilot","title":"stackpilot","description":"Sprint orchestration for Claude Code. Describe a feature, get production-ready code through an automated design→spec→plan→code→QA\npipeline. Drives Claude Code's native Agent tool for multi-agent execution with worktree isolation.\n\nIncludes 3 portable methodology skills usable standalone:\n• TDD Development — RED-GREEN-REFACTOR cycle with 4-phase root cause investigation\n• QA 12 Dimensions — two-stage code review + 12-dimension scenario test coverage\n• Architecture Review — codebase pattern analysis → decisive choice → implementation blueprint","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/9aoyang/stackpilot.git"},{"slug":"shipyard","title":"shipyard","description":"Turn your idea into working code — Shipyard runs Claude Code through a spec-driven agile sprint lifecycle: discuss features, plan sprints, build with strict TDD, review with adversarial multi-agent code review, and ship. State lives in a per-project plugin-data directory that is worktree-aware and cross-platform (macOS, Linux, Windows). Includes 12 commands, 6 specialized review agents, an investigator, and shipyard-logcap (a tee-and-rotate primitive that captures live verification commands so the orchestrator can re-analyze output without re-running).","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/Acendas/shipyard.git"},{"slug":"sextant","title":"sextant","description":"Sextant provides systematic, tiered workflows for common coding tasks — bug fixes, new features, refactoring, code review, test writing, and requirements refinement. Like a nautical sextant that helps navigators fix their exact position before charting a course, it helps Claude understand where it is in the codebase before making changes.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/hellotern/Sextant.git"},{"slug":"session-orchestration","title":"session-orchestration","description":"Coordinate parallel Claude Code sessions for complex features. Alpha plans the effort and assigns tasks. Beta and Gamma build in separate terminals. Delta verifies. Each session reads its task from a shared coordination file — no copy-pasting prompts between terminals. Keeps the human close to the effort during vibe coding. Alpha remains free during the build for brainstorming, research, questions, pivots, and architectural code reviews. Built-in wrap-up flow updates CLAUDE.md at the close of each effort so future sessions start with accurate context.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/alphonso77/claude-orchestration.git"},{"slug":"sdlc-kit","title":"sdlc-kit","description":"Spec-Driven Development for Claude Code. 11 skills for the daily PR loop — init, PRDs, ADRs, SDD specs (EARS), tasks, git worktrees, code reviews (Code Reviewer + AppSec dual-axis), retrospectives. Includes a PostToolUse hook that auto-indexes every .md save into a SQLite tracker. Self-contained HTML dashboard (Kanban + branch graph) included.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"vellus-ai/sdlc-kit"},{"slug":"saas-toolkit","title":"saas-toolkit","description":"The complete Claude Code toolkit for SaaS founders. 15 skills and 4 agents covering the full development cycle - from spec to launch. Build with Next.js, Supabase Auth, Vercel, PostHog, Polar.sh, and Vercel AI\n  SDK. Includes skills for project setup, auth, database, billing, UI, AI integration, analytics, security, landing pages, SEO, branding, content, deployment, and launch readiness. Agents: saas-mentor (guidance),\n  prd-writer (specs), saas-reviewer (code review), qa-tester (test plans).","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/dangogit/saas-toolkit.git"},{"slug":"rkstack","title":"rkstack","description":"Complete AI development workflow — 22 skills that guide the full cycle from idea to shipped code. Brainstorm a design, write an implementation plan, execute with TDD, debug systematically, get a two-pass code review, and ship with confidence. Includes a humanizer for natural prose, a security auditor (OWASP + STRIDE), and safety hooks that block destructive commands. Detects your project stack automatically and adapts.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/mrkhachaturov/rkstack.git"},{"slug":"review-mode","title":"review-mode","description":"Review Mode brings structured, annotation-based code review into your AI workflow. Instead of pasting feedback in chat, you review Markdown plans and documents directly in VS Code — adding inline comments, setting priorities, and threading replies — while your AI agent reads those annotations and implements changes automatically.\n\nThe workflow has three parts that work together:\n\n- Review Mode VS Code extension renders your file in a read-only WebView panel with a comment sidebar. Click any line to add an annotation, set its priority (low → urgent), and start a threaded discussion.\n- Review Mode MCP server exposes the annotation data to your AI agent. The agent can read all open comments, implement changes, mark comments resolved, and reopen the file for another review round.\n- This plugin gives your agent the skills and slash commands to run the full cycle: /review-mode to open a file, /update-plan to implement feedback on a document, and /implement-review to iterate on any file type.\nEach review cycle snapshots the file and migrates open annotations to their new line positions — so your unaddressed comments follow the content even as it changes. You can also compare any two revisions in diff view, or diff against git history.\n\nThe result is a tight loop: you annotate, the agent implements, you review again — without losing context across iterations.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/aurelio-amerio/review-mode-plugin.git"},{"slug":"quick-question","title":"quick-question","description":"Unity Agent Harness for Claude Code. Auto-compiles C# on every edit, runs EditMode/PlayMode test pipelines with error checking, and performs deep code review using Claude subagents — with each finding independently verified against source before fixing. Includes tykit, an HTTP server inside Unity Editor for AI agent control (run tests, play/stop, read console, inspect GameObjects). 20 slash commands covering the full dev loop from edit to ship. Optional cross-model review via Codex CLI for teams that want multi-model verification. macOS, Unity 2021.3+.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/tykisgod/quick-question.git"},{"slug":"pwp","title":"pwp","description":"Project Workflow Protocol — 11 systematic skills for debugging, code review, security audit, refactoring, migration, API design, performance optimization, project bootstrapping, testing strategy, deployment, and documentation lifecycle.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/shandar/pwp-plugin.git"},{"slug":"prodmaster-ai","title":"prodmaster-ai","description":"Full-stack engineering ops for Claude Code. One command (/prodmasterai) covers your entire dev lifecycle: orchestrate features into parallel tasks, run 11-phase QA with health scoring, enforce two-pass code review, deploy with dry-run and revert, audit security across 14 OWASP+STRIDE phases, scan dependencies for CVEs, benchmark Core Web Vitals, and run cross-model adversarial review. 31 skills, 4 active safety hooks. The plugin self-improves using velocity data from your completed cycles — no manual tuning needed.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/sujithkrishnan-dev/prodmaster-ai.git"},{"slug":"prism","title":"prism","description":"A Claude Code plugin that adds multi-profile code review, conventional commits, branching, and PR workflows to any repo. It auto-detects your stack and runs security, quality, performance, documentation, and testing reviewers in parallel. Works both locally via slash commands and as an automated CI reviewer on pull requests.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/SergiCoder/prism.git"},{"slug":"praxis-engineering","title":"praxis-engineering","description":"8 flagship engineering skills curated from the Claude Skills library, covering the full shipping flow: architecture (senior-fullstack), delivery (senior-devops, docker-development, terraform-patterns), security (senior-security), AI tooling (mcp-server-builder, rag-architect) and code review. Each skill is a self-contained folder with SKILL.md instructions, Python automation scripts (standard library only, no pip installs), reference knowledge and examples. Install once, get production engineering expertise across 8 domains.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"borghei/Claude-Skills"},{"slug":"phone-a-friend-paf","title":"phone-a-friend-paf","description":"Phone a Friend lets Claude Code call other AI coding backends for second opinions, code review, and multi-agent collaboration. It relays your prompt and repository context to Codex, Gemini, OpenCode, or local Ollama models, then brings the response back into your Claude session. Includes streaming, structured JSON output, session continuity, multi-agent orchestration with a web dashboard, and an interactive TUI. Useful when you want a different model's perspective without leaving Claude Code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/freibergergarcia/phone-a-friend.git"},{"slug":"orchestrator-workflow-plugin","title":"orchestrator-workflow-plugin","description":"A multi-agent development framework that splits project builds into phases using three specialized roles: an Orchestrator (plans and coordinates), Workers (implement code), and Reviewers (validate quality). Keeps your main agent focused on architecture while sub-agents handle implementation and code review through a structured delegation loop.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/DuckrOverload/duckr-plugins.git"},{"slug":"optibot--community","title":"optibot","description":"AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/Optimal-AI/optibot-skill.git"},{"slug":"octopus","title":"octopus","description":"AI-powered code review in Claude Code, powered by Octopus. Review PRs with natural language or slash commands, automatically fix review comments from the Octopus bot, and get security, bug, and code quality analysis — all without leaving your terminal.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/octopusreview/claude-plugin.git"},{"slug":"mistral-mcp","title":"mistral-mcp","description":"Exposes the full Mistral AI API surface to Claude Code through a local MCP server: 22 tools (chat, streaming, embeddings, OCR, vision, Voxtral transcription and speech, Codestral FIM, agents, moderation, classification, files, batch), 2 live-fetched resources (model catalog, voice catalog), and 6 curated prompts. Ships 5 namespaced skills optimized for everyday workflows: code review via Codestral, Conventional Commits messages in French, meeting minutes from audio or text, B2B invoice reminders in French, and a meta-skill that routes tasks to the right Mistral model. Auto-installs the mistral-mcp npm package on first use; API key is stored in Claude Code's secrets storage and never written to settings.json.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"Swih/mistral-mcp"},{"slug":"mister-anderson","title":"mister-anderson","description":"Beads development for humans — a structured, human-controlled development pipeline with task tracking, code review gates, and multi-agent orchestration","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/websublime/mister-anderson.git"},{"slug":"mentor-mode-for-claude-code","title":"mentor-mode-for-claude-code","description":"A Claude Code plugin that turns Claude into a coding mentor. Instead of writing code for you, Claude guides you through problems with hints, questions, and code review.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/theletterf/claude-mentor-mode.git"},{"slug":"magician","title":"magician","description":"Comprehensive software development lifecycle plugin that takes task from the idea to merged PR autonomously. Core capabilities:\n\n1. Dynamic Project Inspector\n\nOn every session start, it scans your project files (package.json, go.mod, Cargo.toml, pom.xml, etc.) and auto-assembles targeted knowledge (\"lore\") for every detected technology — no manual stack selection needed. Polyglot stacks get full coverage automatically.\n\n2. Full Autonomous SDLC (/manifest)\n\nOne command drives the entire flow with only 4 human approval gates:\n\n* /conjure — design dialogue (with an ability to strictly use design) → approved spec\n* /blueprint — implementation plan with parallelism map\n* /portal — git worktree isolation\n* /orchestrate + /ward — parallel agents with TDD\n* /certify — tests + types + linter + browser verification\n* /scrutinize → /absorb — multi-agent code review + integration\n* /seal — PR creation, loops until merged\n\n3. Self-Learning\n\nA Stop hook (chronicle-stop.sh) captures git diffs at session end, writes entries to a chronicle, and detects repeated patterns. After 3 occurrences, it offers to codify the pattern as a reusable skill via /inscribe.\n\n4. Team Memory Workspace\n\n.workspace/shared/ (git-committed, team-visible) holds context, roadmap, specs, and post-mortems. .workspace/local/ (gitignored) holds personal prefs and session state.\n\n5. Security Infrastructure\n\n* Hard deny rules in settings.json blocking pipe-to-shell, eval, credential access\n* sentinel-guard.sh PreToolUse hook scanning every Bash command for injection patterns\n* magician-scan standalone CLI for CI pipelines\n* /sentinel skill for full OWASP Top 10 + credential + injection audits\n\nSkill Set (20 skills)\n\nCovers: debugging (/unravel), performance (/accelerate), incident analysis (/autopsy), CI/CD (/deploy), security (/sentinel), and meta-tooling (/inscribe).","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/Alexander-Tyagunov/magician.git"},{"slug":"larch","title":"larch","description":"Larch is a multi-agent workflow automation plugin for Claude Code that orchestrates the full software development lifecycle — from design through merge — using collaborative AI agents. It provides six slash commands (/design, /implement, /review, /research, /loop-review, /alias) that coordinate up to 5 parallel agents (Claude subagents + Codex + Cursor) with a voting-based review system to adjudicate findings. Key features include: diverge-then-converge design planning where independent agents propose architectures before anchoring bias can set in; multi-round code review with a 3-agent voting panel (YES/NO/EXONERATE) that accepts or rejects each finding; end-to-end automation from feature design through PR creation, CI monitoring, Slack announcements, and merge; a reviewer competition scoring system that tracks finding quality; and systematic whole-repo review via partitioned slices. External tools (Codex, Cursor, Slack) are optional — the plugin degrades gracefully when they're unavailable.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/zhupanov/larch.git"},{"slug":"laravel-api-tool-kit","title":"laravel-api-tool-kit","description":"Production-grade rules and workflows for Laravel REST APIs built with essa/api-tool-kit. Teaches your AI assistant the\nexact patterns used in the package — so every controller, resource, action, filter, enum, and test it generates matches\nyour architecture from the first draft.\n\nIncludes 21 rule files covering models, controllers, requests, resources, actions, DTOs, filters, enums, repositories,\nevents, authorization, testing, database transactions, DDD structure, and anti-patterns.\n\nIncludes 8 guided workflows: build a full CRUD endpoint step by step, add filtering to an existing model, run a\ndefense-oriented code review, debug issues with data before code, test endpoints with curl and cross-reference against\nthe DB, and manage a per-project knowledge base.\n\nSupports both standard Laravel structure and Domain-Driven Design. Installs in one command: php artisan\napi-skill:install  Production-grade rules and workflows for Laravel REST APIs built with essa/api-tool-kit. Teaches your AI assistant the\nexact patterns used in the package — so every controller, resource, action, filter, enum, and test it generates matches\nyour architecture from the first draft.\n\nIncludes 21 rule files covering models, controllers, requests, resources, actions, DTOs, filters, enums, repositories,\nevents, authorization, testing, database transactions, DDD structure, and anti-patterns.\n\nIncludes 8 guided workflows: build a full CRUD endpoint step by step, add filtering to an existing model, run a\ndefense-oriented code review, debug issues with data before code, test endpoints with curl and cross-reference against\nthe DB, and manage a per-project knowledge base.\n\nSupports both standard Laravel structure and Domain-Driven Design. Installs in one command: php artisan\napi-skill:install","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/ahmedesa/laravel-api-tool-kit.git"},{"slug":"karimo-harness-engineering-agent-orchestration","title":"karimo-harness-engineering-agent-orchestration","description":"Harness engineering framework for Claude Code — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/opensesh/KARIMO.git"},{"slug":"imprint","title":"imprint","description":"Imprint creates a portable collaboration profile by learning how you work through natural conversation. On first run, it asks a few casual questions about your background, tools, and preferences. From there, it silently observes your behavior patterns across sessions and encodes them into a compact structured file (.dna.md) under 500 tokens.\n\nThis single file replaces eleven specialized skills: memory persistence across sessions, output compression, project onboarding, code review (with cross-model validation), architecture-first debugging, adaptive planning, milestone-based progress tracking, resource-aware testing strategies, SEO-conscious git workflows, and GEO-optimized copywriting.\n\nThe profile is a plain text file that works across all 19 SKILL.md-compatible agents. Switch from Claude Code to Cursor to Codex, the file comes with you. No vendor lock-in, no proprietary format, no external API calls.\n\nImprint gets better every session. User corrections become permanent preferences. Debugging lessons become permanent immunity. The more you use it, the less you need to explain.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/ilang-ai/Imprint.git"},{"slug":"hyperflow","title":"hyperflow","description":"Hyperflow turns a Claude Code session into a structured engineering workflow through eight chained slash commands. /hyperflow:spec runs a guided design session with structured questions\n  and section-by-section approval. /hyperflow:scope decomposes the design into a batched task file. /hyperflow:dispatch runs parallel persona-stitched workers under thinking-tier review at\n   every step. Multi-level code review (L1–L5), 15 composable personas covering security, frontend, backend, database, and more, six adaptive flow profiles tuned to task complexity.\n  Project memory persists across sessions so context, decisions, and learned conventions carry forward.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/Mohammed-Abdelhady/hyperflow.git"},{"slug":"html-skills","title":"html-skills","description":"Skills for Claude Code that make it output HTML files instead of plain markdown when HTML is the better fit — specs, system diagrams, ERDs, dashboards, slide decks, design tokens, code reviews, timelines, and more.\n\nSix of the skills are interactive: you click around in your browser, hit Submit, and the result comes straight back into the same Claude Code session as a notification.\n\nNo copying, no pasting, no switching windows.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/f-labs-io/agent-html-skills.git"},{"slug":"great-cto","title":"great-cto","description":"Full SDLC pipeline with 7 agents: architecture, code review, QA, security. Two decisions per feature, the rest is automated.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","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/avelikiy/great_cto.git"}],"total":87,"page":1,"per_page":36,"observed_at":"2026-10-13T18:00:00.395Z","source_counts":{"web":342,"demo":13,"skills":5,"official":315,"community":2284,"knowledge-work":123}}