Score your Claude Code environment on a fun 0-10 ladder (Tourist → Swarm) calibrated to the quickstart's 4 systems — Context, Skills, Integrations, Orchestration. Two front doors - an interactive quiz (zero setup, shareable) or a silent scan of your repo. Outputs a next-level roadmap plus a branded HTML dashboard or a…
A Chinese-language tool for analysing rotation and strength among sectors in China's A-share stock market. It compares sector rankings, leading stocks, trading activity and changes over time from two data sources.
Use OpenCode as a meta-subagent for heavy coding work. Offload engineering tasks to OMO's multi-agent harness so Hermes stays focused on planning, memory, and orchestration.
Generate or edit images with GPT Image 2.5 through Codex/ChatGPT subscription authentication instead of OPENAIAPIKEY. Use for text-to-image, reference-image editing, or visual assets when the user wants local Codex auth, especially when no native image tool is available. Do not use for official OpenAI API-key billing…
Build an award-winning "3D scroll" website of ANY kind from ONE prompt — product launch, portfolio, agency, contractor/home-services, restaurant, real estate, personal brand, event, app, etc. Generates a high-end cinematic hero visual + clips (360° orbit, fly-through, reveal, explode, parallax) fitting the site's…
Use when a Hermes agent must perform public-source research, source scouting, evidence grading, competitor/tool comparison, community-signal analysis, or decision-ready brief writing without private data or credentials.
Compile and execute a goal, existing plan, active run, or Research Routes packet through the vNext Coordinator, Task Lanes, WorkUnits, and Workflow Packs.
General-purpose LinkedIn automation – fetch profiles, search people and companies, send messages, manage connections, create posts, and more. Use when the user wants to interact with LinkedIn.
Design ObjectStack automation — Flows (visual logic), Triggers, Approvals, state machines, and the jobs (defineJob) / webhooks (defineWebhook) stack collections. Use when the user is adding .flow.ts, wiring an event-driven rule, modelling an approval chain, or building an interactive screen flow / wizard…
Guidance for automating computer-aided design (CAD), software used to create technical drawings and 3D models. It covers connecting to AutoCAD and compatible CAD programs, creating files offline, and handling drawings, layers, dimensions, blocks, and models.
Multi-agent web research for any coding agent. Use for anything requiring current information from the internet — news, trends, product/service/company facts, statistics, people, places, events, APIs, library behavior, or 'what is X / how does X work' questions. Also use to search a local knowledge store of previously…
This skill should be used when the model's ROLETYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation…
Carries a hackathon from its published rules to a submission-ready project. Extracts every rule and constraint first, ranks ideas that all comply, and builds toward the exact deliverables the judges expect. Use when a mission is given a hackathon link or an inline hackathon brief. Do not use for general coding or…
An orchestrator for producing whiteboard infographic explainer videos from a topic or script. It coordinates planning, generated board images, animation controls, video rendering, and validation into one project package.
A Chinese-language tool for managing posts or notes on the “说说笔记” service through its web API, with an optional MCP connection. MCP is a way for software tools to expose actions to an AI assistant.
Build AI voice assistants and phone agents with Vapi. Use this skill when users want to create voice agents, phone bots, IVR systems, outbound calling campaigns, or any voice-based AI application.
Use when changing CADIS protocol messages, event schemas, content routing, HUD protocol, approval payloads, model catalog events, or compatibility rules.
Guided multi-phase workflow to design, red-team, optimize, and generate a batch of claude-queue jobs. Walks the user through scoping, target discovery, prompt design, variable extraction, CSV generation, priority config, job generation, adversarial review, token efficiency, and launch. Triggers on: "create a batch"…
A daily review generator that reads Claude Code session logs and turns the day’s work into a page-turning book. The review includes sessions, completed work, produced files or commits, lessons, and next actions.
Replicate motion effects from reference videos. Use when user wants to copy/clone/replicate an existing motion effect, compare generated effects with originals, or iterate on effect accuracy.
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: