Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,343 indexed, measured the same four ways as everything else here.
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, when the…
★not rated 10
changed 3d agoASkillSpector: pass144 tokens
originalMIT
Agent-native payments via 1ly MCP. Use when the user needs x402 payment handling, to accept USDC for APIs/services, to pay for paid APIs, to create stores or paid links, need payment gateway for agents or to run agent-to-agent paid workflows. Supports Solana and Base. Capabilities include accepting USDC, marketplace…
A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor. Runs locally from the task-master-ai npm package. Needs 9 environment variables to run.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use when working with Creght sites or the Creght CLI, including pulling site code locally, pushing local changes, resolving sync conflicts, writing Creght-compatible React pages/components code, CMS, form, Auth, and Func backend integration, routing, styling, metadata, previewing, publishing, site templates…
Use when a plan, spec, design doc, brainstorm, or walkthrough needs review before anyone implements it — especially when it may be over-engineered, over-abstracted, or scoped past a lean MVP. Triggers include "review this plan", "is this over-engineered", "is this too much for an MVP", "sanity check this design"…
A skill for adding Mermaid diagrams to Markdown documents. Mermaid is a text format that turns descriptions into diagrams, and this skill supports dark and light themes, meaningful shapes, compact layouts, and reusable templates.
Use when coordinating multiple live Codex threads, maintaining a coordination heartbeat, routing work across implementation threads, inspecting cross-thread ownership or gates, or keeping a coordinated effort moving through PR, review, evidence, and human-action boundaries.
use this skill when coordinating complex multi-step or multi-agent work through an autonomous durable kanban dispatch protocol. use it when a user gives only an idea and expects the model to infer product requirements, ux flows, architecture, task decomposition, implementation, review, trace logs, and final results…
A step-by-step skill for writing Chinese short stories and saving the finished manuscript as a local Markdown file. It supports planning, drafting, self-checking, and saving.
Not legal advice and not a compliance opinion. Israeli cybersecurity regulatory framework guidance covering INCD (Ma'arach HaSyber) national directives, Bank of Israel Directive 364, the consolidated IT, information security and cyber framework that took effect 18/05/2026 and repealed Directives 357, 361 and 363, plus…
Create ASI-compliant skills with deterministic governance. This is not a general project planning tool; it is a skill creation workflow with explicit gates.
Use this skill when the user wants to search for phone numbers, check number availability, view regions/cities/DID types, check regulatory requirements, reserve numbers, cancel reservations, purchase phone numbers, or delete/cancel an owned virtual number via the 2Chat API. Trigger phrases include "search numbers"…
Record and retrieve structured project learnings using mulch CLI. Use when working on code and wanting to capture patterns, failures, decisions, conventions, references, or guides for future sessions.
Control macOS GUI applications via screen capture, mouse/keyboard automation, and accessibility element inspection. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, or inspect accessibility trees.
Detect malicious patterns in AI Agent skills — 13 detectors for backdoors, credential theft, data exfiltration, and supply-chain attacks. Based on SlowMist's ClawHub threat intelligence (472+ malicious skills). Pure Python, zero dependencies.
Manage local Obsidian vaults and markdown notes. Use when Codex needs to connect to local Obsidian vaults, register vault paths, or create/edit/refactor/search notes, frontmatter, links, tags, and attachments within a vault.
★not rated 10 9mo agoA57 tokens
copy · 100%MIT
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: