New Modular Project

Creates a new Mojo or MAX project. Use when wanting to start a new Mojo or MAX project, initializing the `pixi` or `uv` environment to use Mojo or MAX, or when the user wants to begin a new Mojo or MAX project from scratch.

213 stars 22 forksOther Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add modular/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add modular/skills --skill new-modular-project
Manual install
git clone --depth 1 https://github.com/modular/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/new-modular-project ~/.claude/skills/new-modular-project

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

When the user wants to create a new project, first infer as many options as
possible from the user's request (for example, "new Mojo project" means
type=Mojo, "called foo" means name=foo). Then use a structured multiple-choice
prompt (not plain text) to gather only the **remaining unspecified** options in
a single interaction. Do NOT ask about options the user has already provided or
implied. The options to determine are:

- **Project name**: ask if the user hasn't specified one.
- **Type of project**: Mojo or MAX (infer from context if the user said "Mojo
  project" or "MAX project").
- **Environment manager**: `pixi` (recommended) or `uv`.
- **uv project type** (only when the environment manager is `uv`): full uv
  project (`uv init` + `uv add`, recommended) or quick uv environment
  (`uv venv` + `uv pip install`, lighter weight).
- **Channel**: nightly or stable. Default to nightly for MAX projects and
  stable for Mojo projects, and ask only if the user hasn't implied one.

Then follow the appropriate section below (`pixi` or `uv`) to initialize the
project and choose `max` or `mojo` as appropriate. Don't pin a version: each
channel already resolves to the right one.

MAX and Mojo ship together but number their releases differently, so their
version strings don't look alike. On the stable channel, `max` is `26.5`
while `mojo` is `1.0.0`; on nightly they're `26.6.0.dev*` and `1.1.0.dev*`.
That's expected, not a mismatch.

> [!NOTE]
Read the full skill on GitHub

Details

Skill name
new-modular-project
Repository
modular/skills
Path
new-modular-project/SKILL.md
Repo updated
18 November 2026

FAQ

What does the New Modular Project skill do?

Creates a new Mojo or MAX project. Use when wanting to start a new Mojo or MAX project, initializing the `pixi` or `uv` environment to use Mojo or MAX, or when the user wants to begin a new Mojo or MAX project from scratch.

How do I install the New Modular Project skill?

Claude Code plugin: /plugin marketplace add modular/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is New Modular Project popular?

It lives in modular/skills, which has 213 GitHub stars and 22 forks.

Related skills

Benchmark Model

213

modular/skills

Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garba

AI, LLMs & Agents22

Debug Model

213

modular/skills

Debug a MAX model that loads, compiles, serves, and generates tokens but whose output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong greedy tokens, logit cosine is high but argmax differs, or generation is coherent then diverges. Applies during an architecture port, a quantization bring-up, a multi-GPU conversion, or after a MAX upgrade. Triggers on "parity failure", "silent corruption", "logits match but tokens diverge", "top-1 mismatch", "greedy divergence", and "model serves but generates garbage". Not for

AI, LLMs & Agents22

Eval Model

213

modular/skills

Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.

AI, LLMs & Agents22

Slm Cache

278

qualixar/superlocalmemory

KV cache for repeated reads — call slm_cache_get(key) first; on a miss do the expensive operation then slm_cache_set(key, value, ttl_seconds) to store it; on a hit use the returned value directly; always fail-open (hit:false on any error, never raises); saves tokens when the same file, query result, or tool output is read more than once in a session.

OtherIn 1 list36

Okx Cex Trade

201

okx/agent-skills

Use when the user asks to 'buy BTC', 'sell ETH', 'place a limit order', 'place a market order', 'cancel my order', 'amend my order', 'long BTC perp', 'short ETH swap', 'open a position', 'close a position', 'set take profit', 'limit take profit', 'immediate TP', 'set stop loss', 'self-trade prevention', 'stpMode', 'auto-cancel on close', 'trailing stop', 'pending order', 'chase order', 'iceberg', 'TWAP', 'split order', 'large order', 'set leverage', 'check my orders', 'fill history', 'buy a call', 'sell a put', 'option chain', 'implied volatility', 'IV', 'Greeks', 'delta', 'gamma', 'event cont

Other29

Slm Recall

278

qualixar/superlocalmemory

Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.

OtherIn 1 list36

Browse the most popular Claude skills, all other skills, or write your own with the skills generator.