codex

Scan agent skills for security issues before adoption. Detects prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks.

Last Updated : 2026-01-21 Version : @vercel/blob@2.0.0 Skill Version : 2.1.0

Best practices for writing effective AI video generation prompts via inference.sh .

Wireframes and prototypes bridge the gap between ideas and implementation, enabling teams to test concepts, get feedback, and refine designs before costly development.

Status : Production Ready ✅ Last Updated : 2026-01-21 Dependencies : cloudflare-worker-base (recommended) Latest Versions : wrangler@4.58.0, @cloudflare/workers-types@4.20260109.0 Official Docs :

Generate correct Drizzle ORM schemas for Cloudflare D1. D1 is SQLite-based but has important differences that cause subtle bugs if you use standard SQLite patterns. This skill produces schemas that work correctly with D1's constraints.

Always load Debugging skill for reference

Integration reference for Plankton (credit: @alxfazio), a write-time code quality enforcement system for Claude Code. Plankton runs formatters and linters on every file edit via PostToolUse hooks, then spawns Claude subprocesses to fix violations the agent didn't catch.

Automate infrastructure provisioning, configuration management, and application deployment across multiple servers using Ansible playbooks, roles, and dynamic inventory management.

Source details, install context, and public review data are available on the full page.

Use this skill for operational diagnostics: message delivery investigation, webhook delivery debugging, error triage, and WhatsApp health checks.

Generate a complete SEO package for local business websites. Produces meta tags, structured data, robots.txt, and sitemap.xml.

Single tool feishu_drive for cloud storage operations.

Multi-Version Concurrency Control. Work in progress, not production-ready.

Start every session with context. Your Working Memory is a daily briefing synthesized from your knowledge base.

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

Use XcodeBuildMCP tools instead of raw xcodebuild , xcrun , or simctl .

Execute steps in order. Prefer the simplest configuration that meets the user's constraints.

Use the Navigator widget to push and pop routes using platform-specific transition animations ( MaterialPageRoute or CupertinoPageRoute ).

Use this workflow to generate the raw data required for size analysis.

Balance your testing suite across three main categories to optimize for confidence, maintenance cost, dependencies, and execution speed.

Bootstrap a complete SwiftPM macOS app folder, then build, package, and run it without Xcode. Use assets/templates/bootstrap/ for the starter layout and references/packaging.md + references/release.md for packaging and release details.

Generate high-quality text-to-speech audio using GLM-TTS service via the uvx zai-tts command. Before using this skill, you need to configure the environment variables ZAI_AUDIO_USERID and ZAI_AUDIO_TOKEN , which can be obtained by login audio.z.ai and executing localStorage['auth-storage'] in the console via F12...

Add server-side environment variables to configure default values for user settings.