Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,644 indexed, measured the same four ways as everything else here.
The meta-skill that routes a task to the right Phoenix lifecycle skill and enforces the non-negotiable operating laws. Use at the start of any session or task to decide which Phoenix skill applies. Phoenix is a self-healing, token-efficient engineering harness — every stage verifies its work with an objective check…
Content quality assurance — the adversarial QA gate pack. Topic-delivery, internal-consistency, publication-readiness review, aggregate rewrite, writer self-review for contradictions, self-consistency sampling, an LLM quality rubric, and vision-QA for inline images and rendered preview screenshots. Use after a draft…
Plan, create, restructure, or execute Linear projects for audits, remediation, production hardening, and parallel agent work. Use when the user asks to create a Linear project, run the Linear skill, execute a Linear plan, organize multi-agent work, preserve a companion ledger, add milestones/dependencies, or close…
Integrate and troubleshoot the current Aftermath HTTP/OpenAPI and WebSocket API, including native perpetuals, CCXT, DCA and limit orders, pools, farms, staking, prices, auxiliary utilities, wallet/auth endpoints, and operational safety. Use for raw Aftermath API requests, endpoint schemas, API failures, and API-side…
Extrai o design system de um HTML/URL/print e gera um design-system.html canônico (11 seções, anatomia replicável, regras do/dont, tokens CSS, classes .ds-, WCAG AA, voz, versionamento) preservando 100% das classes/animações originais. Salva o DS mestre do seu OS em contexto/design-system.html e a referência extraída…
Orchestrate UI direction, composition, motion provider selection, implementation, and browser-proven quality for polished frontend work. Use when Codex needs to improve a visual surface with animation or interactive polish; when a request mixes design intent, component choice, browser validation, accessibility, or…
Use when you've drafted or improved a skill locally and want to publish it to a shared pack — walks through validating the draft, finding the target pack, running the promote script, and reviewing the staged diff before it ships.
This skill helps you set up automated synchronization of Claude Code plugins from multiple marketplaces into your own aggregated marketplace. It handles both GitHub Actions and GitLab CI/CD pipelines, including automated scheduling setup.
Gera copy de carrossel Instagram pro perfil @jp.asv (João Pedro Nascimento - Gestão com Claude Code / Claude Code) modelado nos posts de maior engajamento histórico. Use quando o usuário pedir 'gera carrossel jp', 'carrossel jpasv', 'copy de carrossel JP', 'post pro jp.asv', 'novo carrossel da campanha JP' ou…
Use when the user wants to turn today's trending HuggingFace AI models into a niche-mapped Instagram carousel. Pulls the trending list via headless browser, logs it to a local SQLite, picks the best fit for the user's niche, and produces 7 carousel slide prompts plus a master caption — all paste-ready for Higgsfield…
Create or upgrade premium branded websites, landing pages, mobile web experiences, and interactive sections using a curated motion-design catalog, reusable interaction primitives, brand-first art direction, responsive behavior, accessibility, performance budgets, and verification. Use when the user asks for a branded…
Run vLLM benchmark and profiling workflow in containerized environments. Provides automated model loading, concurrency sweep, torch profiling, and GPU kernel analysis. Works with AMD MI355X/MI300X and NVIDIA GPUs.
A Chinese-language topic tracker for social-media creators. It follows content ideas and trends across Xiaohongshu, Bilibili, WeChat official accounts, and Douyin.
This skill should be used when the user asks to "extract agent trajectory", "convert HAR to trajectory", "convert Vally trajectory", "get trajectory from session", "parse agent session", "convert Claude Code logs", "convert Copilot CLI logs", "convert Codex CLI logs", "extract ATIF", or needs to convert agent logs or…
Guide for creating effective skills. Use when: (1) Creating a new skill from scratch (2) Updating or improving an existing skill (3) Learning skill design best practices (4) Packaging skills for distribution (5) Understanding skill structure (SKILL.md, scripts, references, assets).
Lets the agent search, read and edit pages and databases in a Notion workspace. Runs locally from the @notionhq/notion-mcp-server npm package. Needs 1 environment variable to run.
★not rated 6 4mo agoA
tokens not measured
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: