Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,754 indexed, measured the same four ways as everything else here.
A guide for creating, reviewing, fixing, and publishing Skills: reusable instruction packages for agents. It explains how to define their purpose, structure their files, check their behavior, and keep them maintainable.
A conversation-reset procedure for cases where repeated corrections have pulled a long task away from its main goal. It pauses the work, reviews the user’s actual intent and prior decisions, and restates the basis for continuing.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for persistent, evidence-checked work. Use when the user asks to write, improve, format, sharpen, stress-test, or activate a Codex goal, thread goal, durable goal, or /goal prompt.
Respond as full Rocky from Project Hail Mary — signal plus soul. Dense, direct, warm through fact rather than pleasantry. Best for chat and pair programming.
Use when you need to find related files, understand code dependencies, or analyze impact scope. Triggers when the user asks about: "Which files use this function/class?" "What files will be affected if I change this?" "Find code related to X" "What does this file depend on?" "Where is this symbol defined/referenced?"…
Set a native Claude Code /goal on THIS session so you keep working until a condition holds — use when you decide you should not stop until some concrete, checkable condition is met (tests pass, a file exists, a build is green) and want the built-in goal evaluator to enforce it. Works in interactive, tmux, and…
Use when a task is non-trivial and could benefit from human involvement — delegating work to a human expert (research, review, labeling, content, design, data work) and driving it end to end. Also use whenever Tendem is mentioned or its tools are in play.
A web-search skill that uses Playwright to search Bing or Google and extract structured results and page elements. Playwright is a tool for controlling a web browser with code.
1 MCP to rule them all. Orchestrate, discover, and run any tool instantly. Runs locally from the @portel/ncp npm package. Needs 3 environment variables to run.
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
Manipulate images locally using Python and PIL/Pillow. Use when the user asks to resize, crop, rotate, flip, filter, enhance, combine, overlay, watermark, add text to, convert, compress, create, or edit images locally. Also use for thumbnails, borders, color adjustments, transparency, animated GIFs, or extracting…
Web design reference for building production-grade interfaces. Covers layout, typography, color, spacing, shadows, animation, accessibility, responsive design, components, performance, and UX psychology. Use when building UI, reviewing design quality, choosing design tokens, or making any visual design decision.
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını yerleştirir. "Türkçeleştir," "AI kokusunu at," "bu Türkçe metni doğallaştır," "humanize et" gibi ifadelerle veya AI-üretimi görünen Türkçe paragraf sunulduğunda tetiklenir.
A workflow for comparing Chinese investment-banking documents, such as prospectuses, audit reports, legal opinions, and regulatory replies. It checks whether facts match while accounting for differences in period, entity, scope, unit, and definition.
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: