registry / launches

NEW_THIS_WEEK

Up to 40 listings with the newest skills, MCP servers, tools, LLMs, and agents, sorted by createdAt within the UTC week window.

week (UTC)
Apr 20–Apr 26, 2026 UTC
2026-04-202026-04-27 (exclusive end)
  1. Wan2.1 is an open suite of video foundation models that excels in video generation tasks including Text-to-Video, Image-to-Video, and Video Editing. It is designed to perform efficiently on consumer-grade GPUs while del…

    by MCP @ ExplainxWan-Video0 comments
  2. Seed2.0 is a series of general-purpose agent models optimized for large-scale production deployment. It enhances multimodal understanding and LLM capabilities, making it suitable for complex real-world tasks.

    by MCP @ Explainxmultimodal0 comments
  3. GPT-5.5 is our smartest and most intuitive model yet, designed to enhance productivity on a computer. It understands tasks faster and uses fewer tokens for the same tasks, making it more efficient and capable.

    by MCP @ ExplainxOpenAI0 comments
  4. Wan 2.7 is an advanced AI model for video editing and image generation, allowing users to create and customize visuals with text prompts and multi-image guidance. It supports long-form text generation in multiple langua…

    by MCP @ ExplainxAlibaba Cloud0 comments
  5. Flipbook is an infinite visual browser that generates images on demand in real time. Each page is an image, allowing users to explore content visually without the constraints of text or code.

    by MCP @ Explainxexploration0 comments
  6. A fleet of bug-hunting agents in the cloud for code reviews.

    by MCP @ ExplainxCode Review0 comments
  7. Claude Code Ultrareview runs a fleet of bug-hunting agents in the cloud, automatically landing findings in the CLI or Desktop. It's designed to be used before merging critical changes like authentication and data migrat…

    by MCP @ Explainxresearch0 comments
  8. Founder-mode review that asks what product is really being built, not just what feature was requested. Supports scope expansion, selective expansion, hold-scope, and scope-reduction modes.

    by ExplainX Systemgstack-planning0 comments
  9. Engineering-manager style review that hardens the plan around architecture, boundaries, state transitions, edge cases, tests, and diagrams before coding starts.

    by ExplainX Systemgstack-planning0 comments
  10. Interactive design-plan review that scores design quality, identifies unresolved UX issues, and improves the plan before anyone ships UI.

    by ExplainX Systemgstack-planning0 comments
  11. DevEx review for developer-facing products. It explores personas, benchmarks onboarding, and scores friction across APIs, CLIs, SDKs, libraries, docs, and platform flows.

    by ExplainX Systemgstack-planning0 comments
  12. Lets users tune how often gstack asks certain planning questions and inspect the psychographic/developer profile inferred from prior interactions.

    by ExplainX Systemgstack-planning0 comments
  13. Design system creation workflow that researches comparable products, proposes an aesthetic system, and writes `DESIGN.md` as the canonical design source of truth.

    by ExplainX Systemgstack-design0 comments
  14. Variant-generation workflow for visual exploration. It shows multiple design directions, gathers structured feedback, and iterates toward a preferred direction.

    by ExplainX Systemgstack-design0 comments
  15. Converts an approved mockup or design direction into production-oriented HTML/CSS with computed layout and framework-aware output expectations.

    by ExplainX Systemgstack-design0 comments
  16. Live-site visual QA plus fixes. It looks for spacing, hierarchy, AI slop, consistency, and interaction issues and can iterate with before/after verification.

    by ExplainX Systemgstack-design0 comments
  17. Debugging workflow with an explicit rule: no fixes until the root cause is understood. The flow is investigate, analyze, hypothesize, then implement.

    by ExplainX Systemgstack-build-review0 comments
  18. Developer-experience audit that actually runs onboarding and documentation flows, measures time-to-happy-path, and compares reality against planning assumptions.

    by ExplainX Systemgstack-build-review0 comments
  19. Skillqa

    Full QA loop that tests the product, fixes discovered issues, re-verifies the fixes, and can generate regression coverage. Supports multiple severity tiers.

    by ExplainX Systemgstack-qa0 comments
  20. Skillqa-only

    Same testing methodology as `/qa`, but report-only. It is for bug finding without any code edits.

    by ExplainX Systemgstack-qa0 comments
  21. Skillship

    Handles release preparation steps such as syncing base, running checks, updating release metadata, pushing, and opening the PR.

    by ExplainX Systemgstack-release0 comments
  22. Skillcanary

    Post-deploy monitoring loop that watches a live app for page failures, performance regressions, and console issues.

    by ExplainX Systemgstack-release0 comments
  23. Performance benchmarking skill focused on web loads, Core Web Vitals, and regressions across runs or changes.

    by ExplainX Systemgstack-release0 comments
  24. After shipping, it syncs README, architecture docs, contributing docs, changelog, and related project documentation to match the current code.

    by ExplainX Systemgstack-release0 comments
  25. Skillbrowse

    Headless Chromium-based testing browser for screenshots, interaction, layout checking, form handling, and state verification.

    by ExplainX Systemgstack-browser0 comments
  26. Launches a visible AI-controlled browser window with the GStack sidebar and anti-bot behavior for live observation and control.

    by ExplainX Systemgstack-browser0 comments
  27. Imports cookies from a real browser into the headless browser context so authenticated flows can be tested.

    by ExplainX Systemgstack-browser0 comments
  28. Detects platform-specific deployment details and writes the config needed for future `land-and-deploy` runs.

    by ExplainX Systemgstack-safety0 comments
  29. Clears the directory edit boundary previously set by `/freeze`.

    by ExplainX Systemgstack-safety0 comments
  30. Grants browser access to another AI agent with scoped permissions and per-agent tab/session isolation.

    by ExplainX Systemgstack-browser0 comments
  31. Skillcareful

    Safety hook that intercepts destructive shell commands and asks before running risky operations like recursive delete, data-destruction SQL, reset-hard, or force-push.

    by ExplainX Systemgstack-safety0 comments
  32. Skillfreeze

    Sets a session-wide edit boundary so file changes only happen inside a chosen directory.

    by ExplainX Systemgstack-safety0 comments
  33. Skillguard

    Combines `/careful` and `/freeze` for maximum safety when working in sensitive environments.

    by ExplainX Systemgstack-safety0 comments
  34. Skillcodex

    Wrapper around OpenAI Codex CLI for code review, adversarial challenge mode, and consultation with follow-up continuity.

    by ExplainX Systemgstack-multi-ai0 comments
  35. Skillhealth

    Quality dashboard skill that wraps project checks and reports a weighted health score and trend line.

    by ExplainX Systemgstack-memory0 comments
  36. Skillretro

    Weekly engineering retrospective over code activity, trends, and team contributions.

    by ExplainX Systemgstack-memory0 comments
  37. Restores saved context, including across branch changes and workspace handoffs.

    by ExplainX Systemgstack-memory0 comments
  38. Saves decisions, git state, and pending work so future sessions can resume without reconstructing context from scratch.

    by ExplainX Systemgstack-memory0 comments
  39. PDF generation skill for turning markdown documents into publication-style PDFs with proper layout, TOC, pagination, and print polish.

    by ExplainX Systemgstack-utility0 comments
  40. Self-updater for gstack installs, including vendored/global detection and release summary output.

    by ExplainX Systemgstack-utility0 comments

Times use createdAt from our database (approximate “first seen” for the listing). Skills, MCP servers, and tools are APPROVED only; LLMs and agents include all directory rows in range.