Metamodern Skills — Development skill for Claude Code
Practical agent skills for prompting, writing, brand development, project work, and engineering.
How to install Metamodern Skills
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open davidvictor/metamodern-skills and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Metamodern Skills does
Practical agent skills for prompting, writing, brand development, project work, and engineering. Install individually in Codex and Claude Code.
Alternatives in Development
- LifeOS — ⛰️ The Life Operating System — an intent engineering platform that moves you from your current state to your i 18.7k ★
- Scientific Agent Skills — A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing 18.7k ★
- Create Handoff — You are tasked with writing a handoff document to hand off your work to another agent in a new session 10k ★
README
Metamodern Skills
Reusable working methods for **Codex and Claude Code**, from shaping a prompt to developing a brand, preparing a project, and delivering software.
[](https://github.com/davidvictor/metamodern-skills/actions/workflows/validate.yml) [](LICENSE)
These are the methods behind Metamodern's creative and technical work. Each skill gives an agent a focused workflow: what evidence to read, which decisions belong to the user, what to produce, and how to check the result. Install the ones you need. Your projects, private documents, accounts, and approvals stay yours.
Start with a better prompt
Use Metamodern Prompt to expand this idea in three directions.
Then combine the strongest parts and prepare a prompt for implementation.
Preserve my constraints and flag any conflicting choices.
**Metamodern Prompt** has five modes:
| Mode | Use it to |
|---|---|
| Clarify | Make your intention precise without adding scope. |
| Expand | Explore distinct, useful directions. |
| Combine | Bring selected directions together without losing their contributions. |
| Prepare | Turn the result into an actionable brief with an outcome, boundaries, and evidence of completion. |
| Learn | Save, research, correct, inspect, or remove local domain knowledge for future prompts. |
You can also **review, focus, split, or shorten** a prompt. Modes can compose. Preparing a prompt does not execute the task inside it.
Prompt includes focused domain references for UI design, front-end development, back-end/API design, domain and data modeling, automotive design, automotive engineering, copywriting, and marketing, alongside the existing apparel, furniture, business, and research references. It consults only the guides relevant to your idea; naming a domain does not start the underlying design,
Related Skills
Directional Prompting
Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill de
English Practical Writing
Agent skill (SKILL.md) for scoring and writing Chinese Gaokao English 小作文. Works with Claude Code, Codex, Curs
Harness Engineering Practice
Harness Engineering — a practical guide to the platform layer of coding agents (Claude Code & Codex): skills,
Claude Code Engingeering EN
This repository demonstrates how to use Claude Code to do real engineering work, not just writing code.
Claude Scholar
Semi-automated research assistant for academic research and software development. Supports Claude Code, OpenCo
Agent General Staff
A portable multi-agent engineering kit for Codex, Cursor, and Claude Code development workflows.
Related Agents
Rememora Developer
Use this agent when you need to work on Rememora development tasks — picking tickets, planning implementations
Router Sonnet
Worker subagent dispatched by the auto-model-router for standard development tasks — routine refactors, doc an
Monk Installer
Install, upgrade, and troubleshoot monk-agent plus Monk CLI/daemon for Claude, Codex, and Cursor users.