Jev Desktop
codexAccelerate native Mac apps and browser workflows with TypeSafe Jev inside Codex Computer Use.
1 skill
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Accelerate native Mac apps and browser workflows with TypeSafe Jev inside Codex Computer Use.
1 skill
Persistent context for AI coding assistants
54 skills · 1 MCP server · hooks
Set up RevenueCat, integrate it, and access data.
26 skills · 1 MCP server
Deep Google Play subscription lifecycle skills for the RevenueCat Android SDK — purchases, plan and price changes, payment recovery, webhooks, security.
20 skills
Sixteen portable editorial-system skills for agents.
16 skills
A living knowledge base your agents build as they work. What they learn becomes source-cited wiki pages that refresh between sessions, so each new thread starts from your latest work.
11 skills · 1 MCP server · hooks
AI development skills for Even Realities G2 smart glasses apps — scaffolding, UI, input handling, device features, simulator testing, font measurement, and SDK/CLI reference for G2 smart glasses
12 skills
Search CNKI (中国知网) for papers by keyword. Use when the user wants to find academic papers on a topic.
1 skill · 1 MCP server
Search for academic papers on ScienceDirect. Use when the user wants to find papers by keyword on ScienceDirect/Elsevier.
1 skill · 1 MCP server
Search Web of Science by topic, author, title, DOI, or advanced query. Supports edition/database filtering and sort.
1 skill · 1 MCP server
Turn your own coding-agent sessions into verified Harbor eval tasks, with two human review checkpoints.
1 skill
Open-source Codex workflow collection with 60 agents, 232 skills, 75 legacy command shims, install profiles, repo conventions, validation checks, and documentation.
200 skills · 75 commands · 60 agents · 7 MCP servers · hooks
Manifest-driven workflows for inquiry, finite delivery, and optional project coordination. /figure-out investigates and reaches shared understanding, /define writes a finite Manifest with the intended Outcome, hard requirements and revisable working claims, and /do pursues the Outcome with fresh evidence while preserving source authority. Unattended execution uses host-native goal-setting when available, with a completion contract fallback. /auto chains those skills when that is the assigned work. /ticket-up preserves intent, evidence, scoped authority, and retained decisions in independently managed Tickets; /run-ticket investigates a Question or delivers Shaped work, and waits at retained acceptance before landing. /orchestrate runs a finite queue or pursues an assigned outcome within delegated authority, commissions useful work, reads designated result evidence, and records when to continue, wait, ask, or finish. Empty queues and completed implementations do not prove an outcome. Existing store and host facilities provide records and continuation; no scheduler is installed. /setup-project discovers existing direction, decisions, context, and work configuration, proposes scoped shared or private adjustments, and preserves standalone use. Product inquiry probes customer circumstances, alternatives, adoption, use, and the whole experience where relevant. Code, prompt, design, and writing reviews support the workflow. These instruction contracts and focused checks do not establish sustained project or business effectiveness.
21 skills
Tools for prompts and PRs alongside the manifest workflow. Includes collaborative PR walkthroughs, autonomous PR review that re-verifies a manifest gate by gate, author-side PR babysitting that drives the lifecycle toward green and mergeable, hill-climbing an existing artifact toward a goal through figure-out, define and do, gap-calibrated prompt engineering, standalone goals written from a Manifest, a figure-out read or any other source, cross-boundary context handoff, incremental teaching, and an eli5 explainer that renders any topic as big pictures and few words.
13 skills
Migration skills for web apps, frameworks, Cordova, SPM, Appflow, Ionic Enterprise SDK, and SQLite alternatives.
8 skills
Capacitor plugin development skills for SPM support and plugin major-version upgrades.
8 skills
Capgo cloud skills for CLI usage, live updates, hosted native builds, release management, and organization workflows.
7 skills
Run Markdown-defined agents and deterministic workflows.
4 skills
The String runtime as a Claude Code plugin. Installs the `string` MCP server (via npx — no manual install) and a skill that walks Claude through installing apps, calling actions, browsing pages as markdown, and recovering from errors.
3 skills · 1 MCP server
Generate design images worth building from: website comps, mobile screens, brand kits, and image-to-code.
4 skills
Build and maintain addons for Retail, Forever, and Classic progression with version-aware API research and shared Lua code.
39 skills · 1 agent
27 AI-ready skills for generating production-grade .NET code — Clean Architecture, CQRS, DDD. Works with Claude Code, GitHub Copilot, and Cursor.
29 skills
WEPPY AI Agent Plugin for Claude Code — MCP setup and workflow guidance for the WEPPY Roblox AI Toolkit.
6 skills · 2 MCP servers
Explains AI assistants how to use the revx CLI for crypto trading, market data, monitoring, and grid bots
7 skills
Use coSlash sessions, handoffs, agent launches, and diagnostics.
6 skills · 1 MCP server
Shared development tools for Submariner repositories
1 skill
Repo-local Codex plugin for the TMDB MCP server in this workspace.
1 MCP server
Complete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
21 skills · 30 commands · 1 MCP server · hooks
Canonical Claude Code publication for the standalone Hypermnesia MCP Viz server — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace, a consolidation kanban, and a curated knowledge/wiki browser. Read-only bridge over Cortex's shared PostgreSQL store and the ~/.claude artifacts; it renders, it never remembers. Restores the open_visualization and get_methodology_graph tools removed from Cortex; launch with /cortex-visualize.
1 skill · 1 MCP server · hooks
Set up adsctl and inspect, report on, monitor, and manage Meta advertising.
3 skills