Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,329 indexed, measured the same four ways as everything else here.
A visual-design guide for turning articles, PDFs, screenshots, brand materials, or long text into cover images and educational infographics for Chinese social platforms such as WeChat, Xiaohongshu, and Douyin.
Parse Juniper SRX and Junos display-set or hierarchical configurations into the shared firewall schema. Use when input contains set security, zones, policies, address-book, from-zone, to-zone, NAT rule-set, chassis cluster, logical-systems, or routing-instances, including audit, conversion, diff, summary, and…
Guide a user through the FLOP genesis airdrop using the rules published on flop.finance. Use when the user mentions $FLOP, flop.finance, Technocore, technocore.chat, a FLOP testnet faucet, a miner or validator setup, or tclk. Creating a DID and posting in rooms does not earn an allocation. Before the 3 November 2026…
Diagnose lead routing health and grade it A through F. Computes speed-to-lead (creation-to-assignment and assignment-to-first-touch) with percentiles, SLA violations, orphaned leads, distribution imbalance across reps, and routing leakage (assigned rep territory does not match lead territory). Use when the user asks…
Research-first scouting agent skill that runs BEFORE any build decision, new dependency, new system, or feature request. Search existing solutions (codebase, dependencies, packages, GitHub repos, APIs, SaaS, templates) before writing code. Output a REUSE / USE / FORK / BUY / INTEGRATE / BUILD recommendation with a…
Turn approved requirements into an implementation plan with tasks and a test plan. Use when planning a substantial feature from approved requirements before any implementation begins. Skip for small local changes (implement directly with focused tests), security reviews, and convention checks.
Turn rough ideas or incomplete requests into self-contained prompts that another execution agent can run. Automatically select suitable expert roles and independent work methods, show the selection so the user can change it, ask one high-value clarification question at a time, incorporate project and user context, and…
Normative metadata schema v1 for all context-server records. Defines the kind registry (usermessage, report, plan, handoff, checkpoint, note, issue, upstreamissue, comment), required and optional metadata fields per kind, status vocabularies, the typed links object with its design rules, and the filter recipes that…
Attach Proof Engine proofs to LLM-wiki claims. Use for ingest (extract claims, look up or commission proofs, rewrite pages with badges) and lint (re-verify citations, detect contradictions, report stale proofs) steps in wiki pipelines. Trigger phrases: "ingest wiki page", "lint wiki", "{{prove:}} markers", "verify…
Expert Google Ads management — campaign analysis, budget optimization, keyword strategy, ad copy, Performance Max advisory, and account auditing. Activate when the user asks about Google Ads, PPC, campaigns, ad spend, ROAS, keywords, bidding strategies, or any advertising-related query.
This skill should be used when the user asks about "Hyprland configuration", "hyprland.lua", "hyprland.conf", "Hyprland Lua config", "hyprctl", "Hyprland keybinds", "Hyprland window rules", "Hyprland monitors", "Hyprland dispatchers", "Hyprland animations", "Hyprland workspaces", "Hyprland IPC", "Hyprland plugins"…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
MCP server for controlling HomeMatic smart home devices via the CCU JSON-RPC API. Runs locally from the ccu-mcp npm package. Needs 20 environment variables to run.
★not rated 9 3d agoA
tokens not measured
originalMIT
Frame screenshots and screen recordings in realistic Apple device bezels (iPhone, iPad, Mac, Apple TV) using the bezelbub CLI. Use when the user wants a screenshot or screen recording wrapped in a device frame / device mockup — e.g. "put this in an iPhone bezel", "make a device mockup of this recording", "export this…
Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.
Real SIM-card SMS verification for AI agents via VirtualSMS MCP server. TRIGGERS: SMS verification, OTP code, phone number, virtual number, SIM card, two-factor authentication, account verification, WhatsApp verify, Telegram verify, real SIM, agent phone, MCP SMS, virtualsms. Use when an agent needs to receive an SMS…
Real-time communication between Claude Code instances across machines and workspaces. Redis-backed channels with background task notifications for true push in VS Code. Runs locally from the mcp-agent-bridge npm package. Needs 2 environment variables to run.
★not rated 9▲
+1 16d agoA
tokens not measured
originalMIT
Skill "n8n" from rodaddy/mcp2cli, covering n8n, quick reference, usage and notes.
★not rated 9 19d agoA11 tokens
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: