Find the open-source solution that fits.

Provide an App Store Connect API key, app ID, and configuration file to automate build attachment, listing metadata, screenshots, pricing, age rating, review details, subscriptions, and final review submission. The commands are designed to be rerunnable and include readiness checks for missing requirements. Apple still requires two manual web steps: publishing the app's data-collection declarations and attaching a first-time subscription to the version.

make-playbook helps an indie maker diagnose where a product is stuck across idea, build, launch, growth, monetization, automation, and exit. Claude Code loads the relevant checklist, asks questions about the actual app, and ends with a concrete next step; an optional MAKE.md file tracks progress over time. It is an original companion inspired by Pieter Levels' MAKE, not a substitute for the book.

Distill mode researches a public figure's own words, documented decisions, outside accounts, failures, and criticism to create a sourced profile of recurring principles and where they break down. Apply mode uses that profile as one lens on a concrete decision and states what the framework misses. Nine profiles are included; creating new ones requires research access, and the result is not presented as the person's private view or a final verdict.

Mascot Illustration is a Claude Code skill for making 16:9 illustrations for Chinese article bodies. It keeps an original chibi girl as the recurring protagonist, uses her to perform the main action, and leaves generous white space for a few handwritten Chinese labels. The visual system favors bold black linework, flat color, and no shading, giving article images a consistent gentle style.

Point Mirrorframe at a live URL or local page to capture styles, assets, motion, and interaction state machines, then generate a self-contained React and CSS reconstruction. It replays viewports and interaction states, compares pixels per node, and records explicit failure or skip reasons instead of hiding gaps. Use it only on pages you own or may legally copy; drag interactions, complex physics, and live canvas rendering remain outside full reconstruction.

apple-search-ads-conquest researches rival apps, builds competitor keyword sets, and uses a zero-dependency Node toolkit to create Apple Search Ads campaigns that start paused. It also includes organization discovery, authentication, keyword inspection, and a local daily performance check. Running it requires Node 20, Apple Ads account-admin access, a keypair, and environment credentials; review the budget and targets before enabling a campaign.

This self-paced course moves from computing and Python foundations into core and applied bioinformatics, algorithms, and modern AI for science. It includes skills checks, worked assignments, real public-data case studies, visualizations, and 213 Claude Code skills. The compilation is explicitly limited to private, non-commercial educational use and is not intended for redistribution or resale.

Velk helps C++ applications define components through interfaces with typed properties, events, functions, and metadata. Runtime implementations live in a shared library while consumers depend on stable public contracts, allowing internals to evolve without rebuilding every client. Its registries, plugin loading, object factory, and dense storage suit modular systems that need runtime extension and introspection.

Rails Best Practices Skill guides Claude to apply community practices from rails-bestpractices.com when reviewing or generating Ruby on Rails code. It focuses on recurring problems in time handling, persistence results, query efficiency, parameter validation, and security, and can be used from Claude Code, Claude apps, or API workflows.

Once installed, the skill gives Claude Code or Claude Desktop working knowledge of Digital Samba's REST API, embedded SDK, JWT authentication, and common integration patterns. It can assist with room management, embedded calls, webhook handlers, and troubleshooting while drawing on included examples. The repository is guidance for a coding agent, not the conferencing service itself, and users still need a Digital Samba account and Developer Key.

Version Sync compares Node.js version declarations in `.nvmrc`, `package.json`, Dockerfiles, GitHub Actions workflows, and Docker Compose files. It can report mismatches or update every supported file to a target version, either as a Claude Code skill or a standalone TypeScript command. Dry-run previews and optional backups help control bulk changes.

This OpenSkills package guides an AI agent to create or revise Draw.io-format diagrams, including flowcharts, architecture diagrams, network topologies, UML, ER diagrams, and mind maps. The generated files can be opened and refined in Draw.io after creation, making the skill useful for turning written descriptions into structured diagrams.

This skill organizes the TOGAF ADM method, content framework, and governance practices into a working reference for architects and AI agents. It helps plan activities and deliverables from architecture vision through business, data, application, technology, migration, and change management, while also covering viewpoints, architecture principles, and ABB-to-SBB modeling.

The main utility in ai-tools is skill-get, a unified manager for finding and installing Claude Code skills across several directories, direct Git or HTTP URLs, and local paths. It can also update, list, package, and unpack skills at project or user scope. Its configured search order keeps broad GitHub search as a fallback to reduce collisions between similarly named skills.

Anti-Fraud Skill guides a coding agent in combining server-side verification, client-manipulation checks, and behavioral signals for registration flows. Weighted risk scores can trigger rejection or shadow banning, while adjustments for password managers and keyboard-only users aim to reduce false positives. The examples fit common JavaScript stacks, and encrypted timing tokens require an AUTH_SECRET with AES-256-GCM support.

Use this skill to design or refactor WordPress PHP code with clearer responsibilities. It adapts repository patterns, service layers, domain-driven design, SOLID principles, and modern PHP practices to WordPress hooks and plugin or theme development rather than treating them as framework-neutral abstractions.

win11-admin gives Claude Code PowerShell procedures for Windows 11 Pro and Enterprise administration, including registry changes, services, Group Policy, Defender, firewall rules, local users, updates, debloating, and performance tuning. Its guidance emphasizes creating a restore point, backing up affected registry keys, supplying rollback commands, and identifying components that should never be disabled before making system-level changes.

Give the skill a GitHub repository, project notes, or a plain-language description, and it reshapes the work for recruiters, hiring managers, and technical interviews. Outputs can include executive summaries, technical deep dives, Mermaid architecture diagrams, and STAR interview stories. It is aimed at engineers and architects who need to explain a project’s design and impact clearly.