Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,364 indexed, measured the same four ways as everything else here.
Intake de material aportado en proyectos nuevos (modo nuevo-con-material). Recibe el contexto del usuario (docs de APIs, flujos, lógica, resultado esperado), lo normaliza en un SYSTEM-MAP.md con referencias al material, deriva la Visión y siembra la sesión para que la entrevista solo cubra los huecos. Úsala cuando el…
YaparAI MCP Server — Generate images, videos, and music with AI directly from Claude Desktop, Cursor, and Windsurf. Runs locally from the yaparai Python package.
Drive a native mobile app (iOS Simulator / Android Emulator) from the terminal via Appium — snapshot the screen to get element refs, then tap/type/swipe/scroll by ref. Use when the user needs to automate, test, inspect, or interact with a mobile app: navigating screens, filling forms, tapping buttons, taking device…
Write Rank Math SEO-compliant WordPress articles in Traditional Chinese (or any language) that pass the Rank Math 100-point scoring system. Use this skill when user asks to write WP articles, blog posts, tutorials, product guides, or content that will publish to a WordPress site running Rank Math SEO plugin. Outputs…
Use this skill when the user wants to build a knowledge base for their project, create an Obsidian wiki from project data, analyze project structure for knowledge management, or mentions "obsidian-kb", "knowledge base", or "compile wiki".
Create standardized Recursive Loop Orchestration projects for autonomous or semi-autonomous agents. Use when the user asks to create, scaffold, initialize, package, harden, or standardize an agent loop, recursive task loop, multi-agent workflow, self-running agent, Ralph-style loop, auto-fixer, monitor, browser-based…
Use this skill when a substantial task should be delegated to a child CLI agent. It launches Codex, Claude Code, or Cursor Agent against a task directory, resolving the child runner from the parent CLI agent, writes progress scaffolding, supervises the detached run, provides status polling, and can run a task through…
Install or upgrade SDAD; migrate an existing SDAD project; recover or repair sdad-state.yaml, INDEX, ledger, or handoff consistency; run or interpret SDAD Doctor; or diagnose the SDAD control plane. Use only for SDAD-specific bootstrap, migration, repair, and Doctor operations.
Use when an agent needs to blend multiple evaluated quantitative factor signals into a single composite alpha signal (signal-level merge, not portfolio-level combination). Covers factor selection, redundancy removal, weighting, and composite evaluation.
Interroga a un PO o analista funcional para producir una User Story funcional y testeable siguiendo el formato del modelo de trazabilidad — o pule una US vaga existente. Se queda a nivel funcional/usuario y se niega a derivar en diseño técnico o a emitir una US con criterios no testeables. Al terminar la PUBLICA en el…
A research workflow for analyzing dividend yield and estimating the share price that would produce a chosen yield. Dividend yield compares a company's annual dividend with its share price; the workflow produces a self-contained HTML report that opens in a browser.
Use when scaffolding or modifying the structure of a FastAPI + SQLAlchemy backend service: setup.py, config.py, the db/, deps/, common/, api/ directories, the FastAPI app factory, lifespan, middleware, exception handlers. Triggers on edits to those files; on a new repo that's becoming a FastAPI service; on user…
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines…
Use when automating browser interactions with a web app that has a manifest.json or data-agent-id attributes. Use when the agent needs to find, target, or interact with specific UI elements by name, label, or purpose.
Scaffold a personal LLM wiki (Karpathy pattern) — multi-agent, MCP-ready, with SEO/GEO publish target. Compiles knowledge into a persistent wiki instead of re-deriving from raw docs on every query. One paste from any agent (OpenClaw, Claude Code, Codex, Cursor, Hermes) installs it.
Persistent memory and task coordination for AI coding sessions. Creates a .fireteam/ folder with mission context, task state, checkpoints, and handoff notes that survive session restarts, context limits, and crashes. Use this skill whenever the user wants to set up a fireteam, continue a fireteam, resume after a…
Use when context compaction warnings appear, after 8+ major tool sequences, after 3+ large file reads plus 2+ review cycles, when a sprint task closes mid-session with more work pending, or when the user asks for a handoff prompt or to start a new session (in any language).
THE single command for Tech Leads and Staff Engineers. Orchestrates the full sdd toolkit automatically — you never invoke other skills directly. Drives project and feature work through 4 adaptive phases (Specify, Plan, Tasks, Implement), auto-sizing depth by complexity. Activates the right tool at the right moment…
Use this skill whenever you need Filament implementation guidance, need to locate the right local Filament rule files, need official Filament docs, or are unsure which Filament-specific rule applies. This skill is the router for Filament resources, schemas, tables, actions, widgets, panel providers, CSS, and tests.
Audit and improve AGENTS.md / CLAUDE.md guidance files. Use this skill when the user asks to audit, polish, improve, shrink, refactor, fix, lint, or optimize AGENTS.md or CLAUDE.md; when they want to convert a bulky CLAUDE.md into a short AGENTS.md plus a CLAUDE.md bridge; when they want to create a starter AGENTS.md…
★not rated 4 4mo agoA113 tokens
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: