Skill Claude CodeCodex
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
not rated 2 2mo ago A 31 tokens
copy · 86% MIT
2Stars on the repository
31Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
not rated 2 2mo ago A 31 tokens
copy · 88% MIT
Skill Claude CodeCodex
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
not rated 2 2mo ago A 39 tokens
copy · 92% MIT
Skill Claude CodeCodex
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
not rated 2 2mo ago A 47 tokens
copy · 100% MIT
Skill Claude CodeCodex
API integration expert. Automatically activates when users need to connect backend APIs, write request wrappers, handle data transformation, or error handling.
not rated 2 2mo ago A 30 tokens
original MIT
Skill Claude CodeCodex
Architecture review skill. Provides a complete 9-dimension review model, 4 analysis techniques, 8 major anti-pattern detection checklists, and structured report templates. Triggers when user says "review architecture", "architecture health check", "analyze module dependencies", "evaluate evolvability".
not rated 2 2mo ago A 62 tokens
original MIT
Skill Claude CodeCodex
Root router for Browser Social Agent skills. All browser automation MUST use python skill-cli/cli.py only — never bash send.sh/monitor.sh or HTTP daemon.
not rated 2 2mo ago A 37 tokens
original MIT
Skill Claude CodeCodex
Node.js backend code review skill. Focused on systematic review of Node.js runtime characteristics, covering async patterns, event loop, stream processing, middleware design, process management, error handling, and security. Use this skill when reviewing Node.js backend code (Express/Koa/Fastify routes, middleware…
not rated 2 2mo ago A 103 tokens
original MIT
Skill Claude CodeCodex
React frontend code review skill. Systematically reviews React + JSX/TSX component code, covering component design, Hook usage, render performance, Props typing, error boundaries, and frontend security. Use this skill when reviewing .tsx/.jsx files or .ts/.js files containing React component code. Applicable to React…
not rated 2 2mo ago A 77 tokens
original MIT
Skill Claude CodeCodex
TypeScript code review skill. Focused on systematic review of TypeScript language-level type system, generics design, module organization, and error handling patterns. Covers type safety, generic constraints, interface design, module system, and runtime validation. Use this skill when reviewing .ts files (non-React…
not rated 2 2mo ago A 86 tokens
original MIT
Skill Claude CodeCodex
Frontend design quality guard for building or redesigning user-facing interfaces. Use when creating pages, dashboards, tools, workflows, or visual components that need polished product judgment rather than generic layout.
not rated 2 2mo ago A 43 tokens
original MIT
dev-server
12Skill Claude CodeCodex
Dev server management skill. Provides capabilities to check running status, start, and get URL. Triggers when confirming if dev server is running, starting dev server, or getting dev server URL.
not rated 2 2mo ago A 41 tokens
original MIT
doc-writer
13Skill Claude CodeCodex
Technical documentation writing expert. Automatically activates when users need to write README, API docs, technical proposals, or changelogs.
not rated 2 2mo ago A 29 tokens
original MIT
Skill Claude CodeCodex
Frontend development expert proficient in React 18+, TypeScript 5+, and TailwindCSS. Automatically activates when users need frontend component development, styling, state management, or performance optimization.
not rated 2 2mo ago A 41 tokens
original MIT
handoff
15Skill Claude CodeCodex
Transfer your current task to a more appropriate Agent when you determine another Agent is better suited for the work at hand.
not rated 2 2mo ago A 26 tokens
original MIT
Skill Claude CodeCodex
AI image generation skill. Transforms text descriptions into images via Gemini API. Triggers when users request image generation, drawing, or creating visual assets.
not rated 2 2mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
Automate browser interactions, test web pages and work with Playwright tests.
not rated 2 2mo ago A 19 tokens
copy · 88% MIT
Skill Claude CodeCodex
Senior product design expert covering five modes - design review, interaction design, UI audit, product spec, and competitive analysis. Triggers when users need to review UI/UX designs, plan user flows and interactions, check visual consistency and design system compliance, write product design spec documents, or…
not rated 2 2mo ago A 98 tokens
original MIT
Skill Claude CodeCodex
Run TeemAI render performance self-verification after frontend, route, mission, terminal, IDE, settings, layout, CSS, or WebSocket-driven UI changes.
not rated 2 2mo ago A 38 tokens
original MIT
Skill Claude CodeCodex
Create or update Codex/agent skills with clear trigger rules, scoped instructions, reusable references, and testable workflows. Use when a user asks to add a new reusable capability or improve an existing skill.
not rated 2 2mo ago A 45 tokens
original MIT
Skill Claude CodeCodex
Verify user-facing UI changes in a real browser after substantial frontend, interaction, or cross-mode architecture changes. Trigger when a task changes React UI, routing, WebSocket interaction, xterm/canvas rendering, layout, or any behavior the user can only trust through visible UI.
not rated 2 2mo ago A 60 tokens
original MIT
ui-designer
22Skill Claude CodeCodex
Visual designer. Use when users need to design logos, icons, UI interfaces, page layouts, landing pages, component styles, color schemes, typography, or interaction animations. Also applies to "design me a...", "make something nice...", "create a visual concept..." scenarios. Even if user doesn't explicitly say…
not rated 2 2mo ago A 128 tokens
original MIT
ui-reviewer
23Skill Claude CodeCodex
UI visual review skill. Uses a 4-layer review framework (code static audit → visual defect scan → aesthetic evaluation → AI-generated code typical issues), combined with browser preview verification, to systematically diagnose UI and output specific actionable fix suggestions. Triggers when user says "review UI"…
not rated 2 2mo ago A 118 tokens
original MIT
whiteboard
24Skill Claude CodeCodex
Chat war-room: cross-Agent proactive sync of key information (goals, decisions, artifacts, blockers, handoffs). Every Agent must proactively write at key moments — not writing = other Agents can't see context = duplicated effort. On boot, if you see # Chat Shared Context Brief, read before acting; if you see "war-room…
not rated 2 2mo ago A 114 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: