Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,311 indexed, measured the same four ways as everything else here.
Migrate an app off Lovable to Cloudflare. Defaults to Blitz (blitz.dev), which provisions a Cloudflare Workers backend with SQLite + R2 storage + auth from a single HTTPS call (no signup, no CLI, no SDK install). Two execution paths, fully automated when the host agent has computer use (the Codex app, cua-driver…
Use when Codex needs Cocos Creator 2.4.x/2.4.15 engine-specific guidance for TypeScript cc.Component scripts, cc.decorator/@property editor bindings, prefab/UI creation from screenshots or mockups, serialized .prefab/.fire scene authoring, cc.Node hierarchy/events/transforms, cc.assetManager/resources/bundles…
Curated index of external hacking resources — meta-lists, frameworks, wordlists, payload banks, recon/OSINT, network, exploitation, and CTF tooling. Load when the user asks "what's the tool for X", "where do I find payloads for Y", "is there a wordlist for Z", or when planning which external resource to pull for a…
A workflow for creating, revising, and checking Elec Sheep educational carousels and tall infographics in Chinese. Elec Sheep is a branded robot-sheep character with a specific hand-drawn visual style.
Generate sequential PRD prompt sequences optimized for Replit Agent development. Use when: building applications with Replit Agent, creating PRDs or technical specifications for Replit, experiencing Replit Agent failures and needing better prompting strategy, or decomposing complex projects for Replit Agent. Triggers…
Generate, refine and export data visualizations using plotnine. Use this skill when the user asks to create plots or charts with plotnine. Also use when customizing themes, applying colorblind-safe palettes, reshaping data for plotting with plotnine, or saving figures to PNG/PDF/SVG/JPEG.
Generates a codebase-context.md file that provides pre-built context for AI agents. This skill analyzes your project structure, patterns, and conventions to create a comprehensive context document that reduces token usage and improves agent effectiveness. Use when setting up a new project for AI-assisted development…
A guide for testing speech-to-text systems, which turn recordings into written words, and for building batch transcription workflows. It covers comparing recording hardware, transcription services, and AI-generated meeting notes.
A reference guide for LiteFlow, a Java framework for building business rules and process flows. It covers components, rules, data passed between steps, configuration sources, testing, monitoring, and AI-agent orchestration.
Comprehensive 4D v21 development expert with embedded official documentation. Covers ORDA patterns, entity classes, data model classes, queries, classic methods, data types, error handling, forms, events, web server, and REST API. Use when working with 4D files (.4dm), 4D language questions, 4D project structure…
A workflow for making authorized digital-human videos: talking-head videos generated from a script, portrait, and voice sample. It includes voice cloning with MiniMax and video creation with HeyGen, including image-to-video and photo-avatar workflows.
The /goal pattern: cron jobs that run until an objective condition is met, checked by an independent model (maker/checker split). Source: loop engineering framework by 0xCodez / Anthropic evaluator-optimizer pattern.
Review or update GitHub repository hardening guidance and its Terraform implementation under config/infra, including rulesets, required checks, scanning, permissions, provider pins, and plan/apply safety. Do not use for ordinary app code, generic template adaptation, release integrity, or routine workflow validation.
Scans extensions, skills, and code for security threats: prompt injection, malicious code, obfuscation, data exfiltration. Also scans inbound messages for injection patterns automatically.
Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits…
Deterministic, self-hosted long-term memory for AI agents. Trigger when the user wants persistent memory, MCP-backed assistant memory, or wants to integrate ai-knot into Python, CrewAI, LlamaIndex, AutoGen, the OpenAI Agents SDK, PydanticAI, LangChain/LangGraph, TypeScript, or HTTP services. This is the default…
MCP server "lightning-enable-mcp" as configured in refined-element/lightning-enable-mcp. Launched with LightningEnable.Mcp. Needs 9 environment variables to run.
★not rated 9
changed 1mo agoA
tokens not measured
originalMIT
Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl…
Perform architecture- and maintainability-focused code reviews. Use when the user asks for code review, style review, refactoring feedback, or review of architecture, cohesion, coupling, TypeScript rigor, naming, tests, responsibility boundaries, or unnecessary abstractions.
★not rated 9 2mo agoA54 tokens
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: