agentleFS
Sign inStart free
MelvynxMelvynx/ai-maxxing-skills/skills/brain/create-project/SKILL.md

create-project

Skill32 starsChanged 23 days agoMITView on GitHub

Start a new project in the user's brain after a short interview (what it is, the goal, where it stands, what exists, the next steps), placed in the right hub with its About.md and Roadmap.md. Use when the user types /create-project, says "nouveau projet", "crée un projet pour X", "I want to start X" or brings work that fits no project.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use json-canvas and webapp-testing.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • wangzhuofengSkill

    json-canvas

    Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

    Also in 3 projects that use this

  • JetBrainsSkill

    webapp-testing

    Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Interview: Ask only what the argument and the conversation did not already answer, one question per message, each with an example or …

    line 12
  2. Very specific:

    Save: Commit in the brain with git add -A and project: create <name>, and push when the brain has a GitHub copy.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Turn an idea or a new piece of work into a project folder any future session can pick up from one file. The brain is the folder named in the ## Brain section of ~/.claude/CLAUDE.md (default ~/brain). Talk to the user in their language, one short question at a time, with no jargon (never say "slug", "frontmatter" or "repo" to them). Write every file in English; only names (products, people, tools) stay as they wrote them.

  1. Read. Read the brain AGENTS.md (its hubs and rules) and every projects/**/About.md title and status. When an existing project or hub already covers this work, say so in one line and propose to continue it or add a sub-project inside it rather than a new folder.
  2. Interview. Ask only what the argument and the conversation did not already answer, one question per message, each with an example or choices. Accept short answers and move on when they skip one.
    1. What is it, in one or two sentences, and what does "done" look like? (for example "a landing page for my coaching offer, online with a payment button")
    2. Where does it stand? "Just an idea", "started", or "already well along".
    3. What already exists? Links, files, a folder with code, accounts, people involved, tools it uses. "Nothing yet" is fine.
    4. Is there a date or a rhythm? (a launch date, every week, no rush)
    5. What are the next 2 or 3 steps, or the first thing you want me to do on it?
  3. Place. Pick the hub from AGENTS.md that fits (a business, perso/...), or the projects/ root when none does, and a short folder name in lowercase with dashes (coaching-landing). Propose a new hub only for a new business or a big new area. Confirm place and name in one line, for example "I'll put it in projects/my-coaching/landing-page/, OK?".
  4. Create. Write About.md from references/about-md.md with only what they told you: "To fill" rather than a guessed fact, number or link. Put the date or rhythm and what exists under Key info (a code folder outside the brain stays where it is: write its path). Write Roadmap.md with the next steps as checkboxes, the first thing to do on top. Create files/, assets/ or output/ only with their first file, never empty. A new hub gets its own short About.md and a line in the Hubs list of AGENTS.md.
  5. Save. Commit in the brain with git add -A and project: create <name>, and push when the brain has a GitHub copy.
  6. Report. Tell the user in 3 lines where the project is, the first step, and that next time they just say "load project <name>". Offer to start that first step right now.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free