Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 271,420 indexed, measured the same four ways as everything else here.
Legacy routing table for hosts without native skill discovery: maps a request to the right specialist skill and defines composed flows such as review followed by a security pass. Use when running the pack on a pre-Agent-Skills setup, such as plain rules files or a custom orchestrator, that cannot match skills by…
Produces a complete, executable plan for restructuring a codebase from a monolithic layer-by-type layout (flat components/, hooks/, services/, utils/...) into feature-driven architecture (features/ / + shared/). Use when the user wants to refactor, restructure, or migrate an app from monolith to…
A checking procedure for work products such as project documents. It checks that required sections exist, contain real content, and point to files or references that actually exist.
Multi-phase deep research with parallel retrieval agents. Use when the user asks for in-depth research, analysis, comparison, market intelligence, or any query that requires systematic evidence gathering from multiple sources with citations and confidence scoring. Triggers on: "deep research", "research this"…
Use this skill for VitePress sites that publish Cursor rules, commands, and agent skills through docs/scripts/generate-docs.mjs (bootstrap from template/generate-docs.mjs and template/config.mts when starting fresh). Apply it when editing docs/.vitepress/config.mts and themeConfig.nav, sidebar.generated.mts…
A skill for creating and running teams of AI agents from a natural-language request. The description is written in Korean and refers to research teams and the /kkirikkiri command.
Finish a PAI→Soma migration by placing PAI's imported life-OS content correctly: keep the Purpose compartment as a lean 4-field distillation, promote the rich imported categories (beliefs, mental models, decision frames, challenges, lessons) into Soma memory as recall-able notes, and protect the curated purpose.md…
A set of strict CSS and React component guidelines for replicating the highly dense, micro-indexed, and smoothly expanding auto-hiding scrollbar side panel UI seen in DeepSeek's chat history timeline.
Use after any user request that might entail more than a single tool call or anything more than quick, shallow thinking. This surfaces relevant memories that are VITAL to recall for a good user experience and a greater chance at first-pass success for the user's request.
Skill especializada em programação full stack, cobrindo JavaScript/TypeScript (web, Node.js, Foundry VTT), Python (IA, automação, agentes LLM), arquitetura de sistemas, bancos de dados relacionais e NoSQL, e boas práticas de engenharia. Use esta skill sempre que o usuário pedir para escrever código, revisar bugs…
Generate complete, installable Drupal 11 modules. This plugin transforms Claude into a senior Drupal architect with deep knowledge of Drupal 11 core APIs, modern development patterns, and best practices.
MCP server providing a persistent Python sandbox for token-efficient codebase exploration across MCP clients. Runs locally from the rlm-tools Python package. Needs 1 environment variable to run.
★not rated 8 7mo agoA
tokens not measured
originalMIT
USE WHEN you need a structured OLAP slice of a large codebase, log stream (including multi-GB .gz), CSV export, sitemap or HTML crawl, or an SDD artefact catalog — WITHOUT reading raw file bodies into the context window. Single-pass aggregator: streams input, folds records into an in-memory cube by user-picked…
Use this skill when designing database schemas, optimizing SQL queries, scaling database infrastructure, implementing search features, or working with database-specific capabilities (PostgreSQL or MySQL). This is the definitive reference for database engineering in Laravel 13 applications.
Retrospective reconciler that scans the source tree against module-map.yml and docs/modules/, emits MM- findings into .paqad/module-map/drift.json, and surfaces user-approvable deltas. Issue.
Portable control-plane workflow for AI coding agents. Use for non-trivial software work that needs bounded scope, task dependencies, workspace isolation, least-privilege tools, deterministic verification, independent review, rollback, release safety, resumable state or multi-agent coordination. Scale down for small…
An MCP server providing voice status reports using OpenAI TTS (text-to-speech) API. Runs locally from the voice-status-report-mcp-server Python package.
★not rated 8 1y 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: