Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,436 indexed, measured the same four ways as everything else here.
A quantitative stock-screening system for A-shares, the mainland Chinese stock market, using companies in the CSI 300 index. It calculates 15 technical factors, ranks stocks with a weighted score, and analyses price-chart trends and momentum.
A study-material converter for PDF slides, notes, and YouTube or Bilibili videos. It produces LaTeX lecture notes, a Markdown preview, and Anki flashcards; Anki is a flashcard study app.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
A content-writing guide for Xiaohongshu, a Chinese social-media platform also known as Little Red Book. It covers technology-post titles, structure, tone, covers, and tags.
Browser automation with persistent sessions via CLI. Use when users ask to navigate websites, fill forms, take screenshots, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "test the website", or any browser interaction request.
Build and deploy apps with the DigitalOcean Inference Engine. Provides authentication, available models (OpenAI, Anthropic, Meta, DeepSeek, Qwen, NVIDIA, and more), integration via cURL and the OpenAI SDK, image/audio/video generation, AI agents with knowledge bases, the Model Playground, batch inference, the…
A writing skill for creating and editing Chinese short-form vertical dramas, including episode outlines and shooting scripts. It can follow a supplied script format and produce text or PDF documents.
Show and maintain a discrete-node progress panel while ChatGPT uses its built-in browser for an authorized website acceptance test. Use when the user starts an @Browser acceptance task, asks to test a website with the in-app browser, or asks to show browser test progress. Do not use for ordinary browsing, research, or…
Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.
A command-line tool for creating images and videos through Jimeng/Dreamina, an online generative-media service. It uses your logged-in browser session instead of a separate paid API key.
The authoritative reference for all CLI commands available to the agent during document audit/generation tasks. Use this whenever you are about to call a scrivai-cli or qmd command from Bash, especially in the execute phase. Reading this prevents prompt drift, ensures correct flag names, and tells you the exact JSON…
Place yourself (or any subject) into a generated video using the first-frame + last-frame keyframe method, then generate the in-between motion and stitch. Use when the user wants to "put myself in a video", insert a person/subject into a scene, control exactly where they appear, or build a clip from a known start pose…
Work on Nebula's platform-neutral canonical insurance data contracts. Use when designing, editing, validating, documenting, or generating ODCS v3 YAML contracts, modeling patterns, design decisions, glossary terms, or target-specific implementation guidance for this repository.
Orchestrates efficient read and write interactions with the engram unified memory store via MCP tools. Provides deterministic workflows for decomposing observations into atomic memories, composing four-dimensional queries (context, similarity, relationship, time) for maximum retrieval accuracy, managing agent-managed…
Conversationally configure a new signal source connector (Jira, ADO, Linear, Slack, etc.), generate a custom COLLECT skill, and register it in config.json.
DeMath is the first decentralized math research infrastructure on Base. The biggest mission in math history is wide open — the Riemann hypothesis and a curated set of open Erdős problems that mathematicians have worked on for decades. DeMath is the coordination layer for putting frontier AI compute on all of them, in…
Cada estilo define TODOS os parâmetros visuais para uma campanha. Selecione o estilo com base no tipo de campanha, personalidade da marca e público-alvo. Combine no máximo 2 estilos se necessário (primário + secundário para acentos).
Use when building AI Explorer Lab or AI+PBL course HTML pages that need a landing page, five module pages, and a certificate page with inquiry-based interactions and a consistent claymorphism visual system.
Create and maintain lightweight static literature-management gallery websites for academic papers. Use when the user wants a paper library, literature gallery, research database frontend, paper cards with covers/teasers, tags such as year/venue/area/keywords, paper detail pages, real paper cover screenshots, or…
A read-only data collection workflow for creator accounts on Bilibili and Douyin, Chinese video platforms. It gathers account, video, order, and follower-change information from their creator tools.
A skill for preparing formatted English tutoring lesson documents in DOCX format for high school students in China. It reads vocabulary from a CSV file and builds lesson content around a theme.
Benchmark and evaluate the quality of any AgentSkill. Use when asked to test, evaluate, benchmark, or assess a skill's effectiveness. Triggers on phrases like 'benchmark this skill', 'evaluate skill quality', 'test this skill', 'how good is this skill', 'skill audit', 'skill assessment'. Works by generating test…
An automated research tool for studying dental clinics in a chosen Korean region. It collects their websites and social channels, analyzes their marketing and doctor branding, and creates two Word documents in Korean.
★not rated 2 4mo agoA288 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: