JointJS-powered interactive playground skills — (1) code map visualizations for library/codebase architecture (supports local codebase analysis), (2) data explorer diagrams for database schemas and entity models (supports local schema files), both on a shared graph-explorer framework — (3) canvas builder for…
Universal channel plugin for Claude Code with 21+ platform adapters. Connect via WebSocket (default) or use built-in adapters for Telegram, Discord, Slack, WhatsApp, Signal, iMessage, IRC, Google Chat, LINE, Feishu, Matrix, Mattermost, MS Teams, and more. Full hook event forwarding, permission relay, and bidirectional.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Automatically selects one of five Claude Code effort levels while preserving claude.ai subscription billing. Learn more at https://www.promptrail.ai/plugins.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Multi-agent orchestration system for software development with human-in-the-loop checkpoints. Implements the QRSPI pipeline: Questions, Research, Structure/Design, Plan, Implement + Review, Pull Request.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Local-first evidence-based career decision support for Japan job seekers: confirmed facts, conflicts, unknowns, verification, and user-controlled next actions.
★not rated 6
changed 10d agoA
tokens not measured
originalMIT
Claude Code plugin for the Marketing Manager platform — 37 Link Platform MCP tools for strategy, pages, links, analytics, tracking, routing, and deployment on 10x.in. Includes 25+ skills, 7 agent roles, and 5 slash commands.
Build apps with Supabase as the backend. Equips AI agents with schema-driven workflows, RPC-first data access, edge functions, auth, RLS, and multi-tenancy.
★not rated 6 3mo agoA
tokens not measured
originalMIT
Loop Engineering portable: bucle autónomo que revisa un proyecto por flujos de ejecución (GitNexus), escribe tests (test-first), arregla lo seguro en worktrees aislados, lo verifica con un evaluador adversarial independiente y abre PRs — nunca auto-mergea. Incluye la skill /forja y 4 subagentes…
★not rated 6 4mo agoA
tokens not measured
originalMIT
Blindfolds the LLM from your secrets. Stores API keys, tokens, and passwords in your OS keychain. The LLM works with placeholders, never sees actual values. Kernel-level sandbox enforcement on macOS.
★not rated 6 yesterdayA
tokens not measured
originalMIT
Rook — an MCP bridge for Rhino 3D and Grasshopper, with skills for designing, planning, and executing parametric definitions and LLM-powered Chirp components.
★not rated 6
changed 22d agoA
tokens not measured
originalMIT
Convert pixel-exact design mockups (e.g. HTML from Claude's design tool) into production Tailwind / shadcn-on-Radix components that use a real token system instead of arbitrary values like text-[13.5px].
★not rated 6 4mo agoA
tokens not measured
originalMIT
UI/UX design review skill based on FormFactor design school methodology. Reviews designs against professional standards for visual hierarchy, spacing, typography, color, layout composition, and Figma best practices.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Strict issue-ledger and exit-gate system that prevents false completion claims. Uses your signed-in Codex as an independent reviewer - Claude cannot claim 'all fixed' until every finding is actually closed.
★not rated 6 7mo agoA
tokens not measured
originalMIT
Opinionated basic Claude Code setup with intelligent context injection, language-specific guides, project knowledge, and encoding validation.
★not rated 6 1y agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: