rad-coolify
codexGuidance and local checks for self-hosted Coolify v4. Optional live actions need client-specific MCP setup and cannot guarantee a successful deployment.
10 skills · 1 MCP server
Text-first brainstorming for one person. It separates idea generation from evaluation and cannot guarantee useful ideas or correct conclusions.
Plugin rad-brainstorm in RadOrigin-LLC/rad-plugins. Commands read from the repo's manifest — 1 month ago.
brainstorm-sessionUse when the user explicitly wants to brainstorm, generate or expand ideas, explore alternatives, use a named creative method, or work from a blank or vague starting point. Do not use for a direct answer, root-cause interview, idea ranking, technical design, or implementation planning.
five-whysUse when the user wants a user-led root-cause interview for a repeated problem, failure, delay, defect, or other observed symptom. Do not use for open ideation, option ranking, or evidence-led code diagnosis.
idea-evaluationUse when the user already has two or more ideas and wants to compare, rank, test, or select among them. Do not use to create the first idea set, conduct a root-cause interview, produce a technical design, or plan implementation.
software-designUse when the user has chosen what software to build and wants a reviewable technical design or design spec before implementation planning. Do not use for open ideation, code implementation, project scaffolding, or brand and visual design.
Guidance and local checks for self-hosted Coolify v4. Optional live actions need client-specific MCP setup and cannot guarantee a successful deployment.
10 skills · 1 MCP server
An Agent Plugins 1.0.0 package for repository context, typed recall, handoffs, scoped checks, and guarded Git shipping in Codex. Its opinionated model and heuristics cannot prove code or production health.
10 skills
Guidance for one-person PARA organization, reviews, summaries, and handoffs. It has no sync service or app connector and can misclassify sparse notes.
7 skills
An Agent Plugins 1.0.0 package for evidence-backed implementation plans in Codex. It writes planning documents, not application code, and its checks cannot prove an architecture will work.
4 skills
Create, audit, and convert Agent Plugins 1.0.0 packages, then guide reviewed marketplace release. Agent Plugins 1.1.0 is a working draft, and local checks cannot prove support in every client.
4 skills
Draft, rewrite, edit, and proofread prose while preserving facts, citations, meaning, and deliberate voice.
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.