Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 268,107 indexed, measured the same four ways as everything else here.
Use when user mentions papers, references, citations, Zotero, literature, bibliography, or needs to search, read, export, or organize documents. Handles all zot CLI operations including ranked search over Zotero collections.
Use when chatting in terminal, especially in terminal-first technical or business discussions, to ensure responses are terminal-friendly and visually structured.
Use this skill when an AI agent is connected to Horosa Skill through MCP, CLI, Cursor, Claude, Codex, OpenClaw, Open WebUI, or another local-first client and needs to call Horosa metaphysics tools, generate reports, store memory, or debug user-facing results.
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when you need to: (1) generate images from text descriptions, (2) edit existing images with AI, (3) compose multiple images into one scene. Supports 1K/2K/4K resolutions and up to 14 input images for composition.
A macOS-only document-formatting workflow that copies the layout of a reference Microsoft Word document to new content. It can reproduce settings such as fonts, sizes, spacing, alignment, page setup, styles, and themes.
A playbook for investigating browser JavaScript with MCP, a protocol for connecting an agent to external tools and data. It covers tracing signatures, observing pages, recreating missing local environments, analyzing inserted code, and simplifying syntax trees.
A way for Claude Code to recall relevant private work context from the local MemoryBread service before answering or taking action. The context may include past decisions, project history, viewed pages, writing preferences, work evidence, and previously captured details.
Scrape AI papers published by 28 big tech companies and AI labs in a given date window, with institutional attribution (lead vs. participating vs. intern). Use when the user asks "what did big tech publish recently", "what AI research has put out", "run the paper radar", or wants to inventory recent arXiv output by…
Research and plan first-time independent trips in China with bilingual, source-aware city data and official live-check entry points. Use for destination matching, attractions, visitor areas, itineraries, transport context, seasonal preparation, local culture and food, or emergency guidance; not for booking…
Use when reviewing, fixing CI for, approving workflows for, or merging AgentBro pull requests into dev/main, especially external contributor PRs where contributor attribution matters.
Use when turning resume materials and an optional job description into verified, approved content and a runnable React + Vite resume or portfolio site, or when redesigning an existing confirmed site.
A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research, and SAST — powered by Radare2, YARA, LIEF, Capstone, and more. Runs locally from the reversecore-mcp Python package.
★not rated 202▲
+1 yesterdayA
tokens not measured
originalMIT
Cria e evolui a animação de um slide como METÁFORA visual animada (o M de MIRA): destila o conceito, acha uma analogia concreta do cotidiano e a anima com loop interno obrigatório, em D3.js v7+ ou CSS 3D, no padrão dos decks de mira-templates/decks/ (glass-card, icon-hero, attribute-pills, replay-btn). Dois modos…
Design or review specx core scope boundaries in Python services. Use when deciding where code belongs across packaged scoped foundation bases, optional local foundation extensions, core/, capabilities, delivery, infrastructure, shared/, and ioc; when adding guardrails or splitting use cases, services, DTOs, schemas…
Scan the codebase and classify every fact by lifecycle stage — tag @draft, @spec, or @implemented based on what the code actually shows. Add missing facts, fix inaccurate ones, remove obsolete ones. Use when asked to discover facts, bootstrap or update a fact sheet, scan the codebase for truths, sync facts to match…
A skill for Meihua Yishu, a Chinese form of I Ching divination that uses hexagrams, including character-based readings. It responds to requests for fortune telling and related readings.
Context Coder: MCP server providing secure file system operations with relative path handling for AI context management. Runs locally from the context-coder npm package.
★not rated 201▲
+1 4d agoA
tokens not measured
originalMIT
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: