Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,006 indexed, measured the same four ways as everything else here.
Combines search results from multiple sources into coherent, deduplicated answers with source attribution. Handles confidence scoring based on freshness and authority, and summarizes large result sets effectively.
How to consult Claude Code as a second-opinion agent via the claude-agent MCP tools (claude, claude-reply, claude-result, claude-cancel). Use before brainstorming with Claude (aliases @claude, @claude-code), validating a plan, requesting an external code review, or any claude-agent tool call. Form your own analysis…
This enhanced skill should be used when the user asks to create an agent, automate a repetitive workflow, create a custom skill, or needs advanced agent creation capabilities. Activates with phrases like every day, daily I have to, I need to repeat, create agent for, automate workflow, create skill for, need to…
Build new MCP Apps (MCP servers with React UI output) using @modelcontextprotocol/ext-apps and the MCP SDK. Use when asked to scaffold or implement MCP App servers, add UI-rendering tools/resources, or migrate a standard MCP server to an MCP App with Vite single-file UI bundles.
Guides correct, budget-efficient use of the legacy roic.ai v2 REST API (https://api.roic.ai/v2) — query-string API-key auth, the symbol/CIK/CUSIP/ISIN identifier model, ticker and reference lookups, company profile/news/logo, earnings-call transcripts, the 11 fundamentals routes (statements, ratio groups, enterprise…
Audit and tune a Claude Code installation. Scans /.claude and /.claude.json for silently broken hooks, unused skills/plugins/MCP servers, stale memory files, orphan Claude/MCP processes, bloated telemetry, dead project entries, and contradictions in global or project CLAUDE.md. Produces a severity-ranked findings…
Browse the prompt-history diff viewer in neovim — show what code changed for each prompt of a Claude Code session. Use when the user wants to look back at prompt history, see the diff a prompt produced, open/close the history viewer, switch to another session, or list captured sessions. Requires the AIAgent neovim…
Evaluate AI agent configurations, plugin skill files, MCP server connections, and tool permissions for security risks. Use this skill whenever the user mentions scanning plugins, reviewing agent security, auditing AI tools, evaluating MCP configurations, checking skill files for vulnerabilities, prompt injection…
Persistent dual-layer memory engine with Notebook facts, curated RAG knowledge base, agent-driven knowledge graph, and general MCP helpers. Trigger proactively whenever user preferences, project conventions, technology stack choices, or architecture decisions are introduced, or when querying ingested documentation…
Search through Claude Code local chat history JSONL files to find information from past conversations. Use when the user asks "did we discuss X before", "what did we decide about Y", "how did we solve Z", or when context from a previous session would be useful. Searches all local session files efficiently via grep +…
Build production-quality Figma plugins from a natural-language description. Use this skill whenever the user wants to create, scaffold, modify, debug, or iterate on a Figma plugin — including FigJam widgets, Dev Mode plugins, and Slides plugins. Trigger on phrases like "build me a Figma plugin that…", "I want a plugin…
A tool for writing image-generation prompts in the style of internal seminar or workshop presentation materials. It supports complex layouts with 20–30 text elements and can produce prompts for visual-renderer.
Execute an approved plan or technical spec in Codex using complexity-based solo or multi-agent workflows. Use when the user wants implementation, especially with parallel agent teams.
WordPress theme and plugin development expert. This skill is triggered when users mention WordPress, theme, plugin, Gutenberg, WooCommerce, hook, shortcode, wpenqueue, addaction, addfilter, or related terms.
A configuration skill for Brain Fog Friendly, which changes the agent’s response style for lower mental effort. It asks the user to choose a supported language or disable the style.
Use when explicitly maintaining Project Knowledge Base: user asks to ingest/refresh/repair memory, a task is at final handoff/commit/PR/merge, or the KB needs bootstrap or full-refresh.
Build reactive, type-safe, production-grade backends. ALWAYS use this skill when the user asks to build, plan, design, or implement backend features, APIs, data models, server logic, database schemas, web apps, full stack apps, or mobile apps. This includes planning and architecture discussions — invoke this skill…
MCP server for AI-driven 3D modeling and print validation (FDM-focused). Agent-agnostic; works with any MCP client (Claude Code, Goose, Cursor, Codex, ...). Runs locally from the mcp-printable Python package.
★not rated 2 3mo 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: