vasilyu1983/AI-Agents-public

Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex. 140 skills, 28 agents, Agent Skills spec compliant.

87Stars on the repository
140Mods indexed here, across every type
10d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

software-desktop

121

vasilyu1983/AI-Agents-public

Skill Codex

Guides cross-platform and native desktop development with Electron, Tauri, Flutter Desktop, MAUI, and platform-native frameworks. Use when choosing a stack or packaging installers.

not rated 87 +3 10d ago A SkillSpector: pass 38 tokens original MIT

software-devtools

122

vasilyu1983/AI-Agents-public

Skill Codex

Designs developer tools, SDKs, CLIs, IDE extensions, and code generators. Use when shaping DX, typed clients, code generation, or package distribution workflows.

not rated 87 +3 10d ago C 38 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Designs transactional email systems and send infrastructure. Use when implementing resets, receipts, deliverability controls, templates, or inbound email handling.

not rated 87 +3 10d ago A SkillSpector: warn 32 tokens original MIT

software-frontend

124

vasilyu1983/AI-Agents-public

Skill Codex

Builds frontend applications across major web stacks. Use when implementing UI, fixing hydration or SSR issues, or setting up modern frontend architecture.

not rated 87 +3 10d ago A SkillSpector: warn 31 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Design local AI engines for iOS. Use when wiring Apple Foundation Models, local classifiers, extraction, summarization, grounded answers, and cloud fallbacks.

not rated 87 +3 10d ago A SkillSpector: pass 36 tokens original MIT

software-ios-design

126

vasilyu1983/AI-Agents-public

Skill Codex

Designs and audits native iOS interfaces. Use when reviewing or refining SwiftUI layout, typography, Liquid Glass, navigation, or dashboards on a freshly verified build.

not rated 87 +3 10d ago A SkillSpector: warn 37 tokens original MIT

software-ios-native

127

vasilyu1983/AI-Agents-public

Skill Codex

Guides native iOS with Swift, SwiftUI, UIKit interop, concurrency, and persistence. Use when building or reviewing iPhone/iPad apps after establishing runtime truth.

not rated 87 +3 10d ago A SkillSpector: warn 39 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Proves iOS build/install/launch truth and triages hangs, crashes, jank, memory kills, and stale builds. Use when simulator, bundle, or runtime performance state is in doubt.

not rated 87 +3 10d ago B SkillSpector: warn 46 tokens original MIT

software-localisation

129

vasilyu1983/AI-Agents-public

Skill Codex

Implements production-grade i18n/l10n for React, Vue, Angular, and Next.js with ICU format and RTL support. Use when setting up or debugging localisation.

not rated 87 +3 10d ago A SkillSpector: pass 39 tokens original MIT

software-mobile

130

vasilyu1983/AI-Agents-public

Skill Codex

Guides mobile platform selection and delivery across native and cross-platform stacks. Use when planning auth, push, deep links, releases, or app architecture for iOS/Android.

not rated 87 +3 10d ago A SkillSpector: pass 38 tokens original MIT

software-paas-hosting

131

vasilyu1983/AI-Agents-public

Skill Codex

Chooses PaaS compute hosting for apps, agents, bots, APIs, and workers. Use when picking Vercel, Fly.io, Railway, Render, Cloudflare, Deno, or container PaaS.

not rated 87 +3 10d ago A SkillSpector: warn 51 tokens original MIT

software-payments

132

vasilyu1983/AI-Agents-public

Skill Codex

Designs production payment and billing systems. Use when implementing Stripe, Paddle, Adyen, subscriptions, tax, marketplaces, or mobile purchase flows.

not rated 87 +3 10d ago A SkillSpector: pass 33 tokens original MIT

software-performance

133

vasilyu1983/AI-Agents-public

Skill Codex

Systematic profiling, load testing, performance budgets, and regression prevention. Use when diagnosing slow services, benchmarking systems, or preventing regressions.

not rated 87 +3 10d ago A SkillSpector: pass 31 tokens original MIT

software-realtime

134

vasilyu1983/AI-Agents-public

Skill Codex

Designs real-time and collaborative systems. Use when building chat, live dashboards, collaborative editing, notifications, WebSockets, SSE, or CRDT workflows.

not rated 87 +3 10d ago A SkillSpector: warn 35 tokens original MIT

software-search

135

vasilyu1983/AI-Agents-public

Skill Codex

Designs application search systems. Use when choosing engines, indexing, relevance tuning, facets, autocomplete, or search analytics.

not rated 87 +3 10d ago A SkillSpector: pass 27 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Provides application security guidance for design and implementation. Use when reviewing auth, data handling, supply-chain controls, or AppSec architecture.

not rated 87 +3 10d ago A SkillSpector: warn 31 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Designs cross-system target states and transition plans from business workflows and system boundaries. Use when comparing end-to-end solution options or phased migrations.

not rated 87 +3 10d ago A SkillSpector: pass 34 tokens original MIT

software-ui-ux-design

138

vasilyu1983/AI-Agents-public

Skill Codex

Designs and audits UI/UX systems with usability and accessibility requirements. Use when shaping flows, design systems, interaction patterns, or WCAG-aware product behavior.

not rated 87 +3 10d ago A Socket: passSnyk: passSkillSpector: warn 38 tokens original MIT

software-ux-research

139

vasilyu1983/AI-Agents-public

Skill Codex

Guides user research methods and research ops. Use when running interviews, usability tests, surveys, or A/B tests to de-risk product decisions.

not rated 87 +3 10d ago A SkillSpector: pass 35 tokens original MIT

vasilyu1983/AI-Agents-public

Skill Codex

Designs workflow automation with n8n, Langflow, Temporal, and Trigger.dev. Use when choosing automation platforms, durable runtimes, or custom code.

not rated 87 +3 10d ago A SkillSpector: pass 38 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: