JSON-driven E2E browser test runner — no JavaScript test files needed. Parallel execution against a Chrome pool (browserless, CDP, Lightpanda, Obscura, Steel), 28+ built-in actions, visual verification, network debugging, flaky test detection, reusable modules, and a real-time dashboard. Includes 3 specialized agents.
★not rated 7 5mo agoA
tokens not measured
originalApache-2.0
Queue committed branches from parallel LLM coding agents in Git worktrees. Test the combined tree in a local merge queue, require approval for Git pushes, and recover interrupted pushes.
★not rated 7
changed 16d agoA
tokens not measured
originalMIT
Liquid Glass for Apple platforms: the material and its motion. Availability-pinned, SDK-verified rules for glassEffect, containers, morphing, toolbars, UIKit/AppKit glass, accessibility, Reduce Motion, Metal shaders, and Instruments profiling.
★not rated 7 3mo agoA
tokens not measured
originalMIT
A collection of artificial-intelligence skills for structured thinking, decision reviews, debates, writing, product work, design, and engineering leadership.
★not rated 7▲
+1 5mo agoA
tokens not measured
originalApache-2.0
On Point: the big idea in the first line, the one next action in the second, terse prose after. Substance, exact errors and security are never compressed.
★not rated 7 26d agoA
tokens not measured
originalMIT
Record, build, tailor, and review resumes in a single-column ATS-safe house style: keeps an honest experience record the user owns, generates a formatted Google Doc from that record, an interview, or an existing resume file, aims a copy at a specific job description, and audits any resume against a pre-submission…
Generate and repair authentic pixel art — sprites, animations, and tilesets — with Retro Diffusion. Includes the hosted MCP server connection and a workflow skill for cost-aware, game-ready generation.
★not rated 7 2mo agoA
tokens not measured
originalMIT
One memory. Every AI. Connects MemoryPlugin's memory server and teaches the agent to recall the user's long-term memory before assuming, and store durable facts before finishing.
★not rated 7▲
+1 3mo agoA
tokens not measured
originalMIT
Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Claude Code: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security…
★not rated 7
changed 6d agoA
tokens not measured
originalMIT
Claude Code plugin for OpenAI Codex subagents, GPT-6.1 Sol, Astra, Luna, parallel code review, adversarial review, and native follow-up sessions through a daemonless MCP server with read-only defaults and explicit full-access mode.
★not rated 7
changed 28d agoA
tokens not measured
originalMIT
Flox development environment and deployment plugin. Includes expert guidance for package management, services, builds and package distribution, containerization, environment composition and layering, and CI integration.
Personal WhatsApp MCP server built directly on whatsmeow. Local-only Go bridge with SQLCipher-encrypted storage, Python FastMCP layer, Whisper voice-note transcription, accent-insensitive Spanish search, LID name resolution, vault-native CRM auto-injection, prompt-injection scrubbing, and mandatory draft+confirm on…
Capture skills for PostgreSQL, MySQL, MongoDB, SQL Server, Alpaca, HubSpot, HTTP webhooks, and 148+ other connectors.
★not rated 7 7d agoA
tokens not measured
originalApache-2.0
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: