Skip to content

Skillselionwith God's help

By phase

IdeaResearch & spot demand
ValidateScope & prototype
BuildFrontend, backend, MCP
ShipTest, review, deploy
LaunchDistribution, SEO, ASO
GrowAnalytics & retention
OperateMonitoring & uptime

By type

Skills
Marketplaces
MCP servers
Workflows

Skills Marketplaces MCP Learn Brief

Browse all tools →By phase

Idea Validate Build Ship Launch Grow Operate

Explore

Skills
Marketplaces
MCP
Learn
Brief

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

Email address

unsubscribe anytime.

Skillselion

An independent, curated directory of AI-coding tools for solo builders - skills, MCP servers, marketplaces and workflows for Claude Code, Codex and Cursor, organized by the indie build journey from idea to operate.

ResourcesBrowse Skills Browse MCP Servers Browse Marketplaces Browse Workflows Best-of shortlists Glossary State of AI Skills 2026 Weekly Brief

CommunityAbout Learn Feedback Privacy Policy Terms Cookie Policy Accessibility Cookie settings

Last updated June 10, 2026 · © 2026 Skillselion. Skillselion is an independent project and is not affiliated with Anthropic, OpenAI, Cursor, Claude, Claude Code, or Codex.

Skills/IMSUS/PI EXTENSION MINIMAX CODING PLAN MCP

imsus/pi-extension-minimax-coding-plan-mcp

1 skill · 520 installs · 13 stars · GitHub

Install

npx skills add https://github.com/imsus/pi-extension-minimax-coding-plan-mcp

Skills in this repo

1Minimax Image UnderstandingMiniMax Image Understanding is an agent skill for the MiniMax coding-plan MCP extension that tells your coding agent when and how to call the understand_image vision endpoint. Solo builders install it when screenshots, mockups, or photographed docs carry information that is awkward to type out—stack traces in a PNG, layout bugs, chart trends, or text locked inside an image. The skill keeps usage disciplined: pass a focused prompt and a reachable image_url, receive content in the standard JSON response shape, and avoid redundant VLM calls when the thread already contains the same pixels as text. It sits in Prism’s AI and agent-building aisle as an integration skill, not a general chat habit. You need MiniMax API hosting configured on the MCP side; the skill does not replace local vision models. Use it across frontend iteration and ship-time debugging when visual evidence is the fastest path to a fix.520installs