agentleFS
Sign inStart free
MelvynxMelvynx/ai-maxxing-skills/skills/setup-convex/SKILL.md

setup-convex

Skill32 starsChanged 24 days agoMITView on GitHub

Sign the user in to Convex from macOS, Linux or Windows through the browser, so the agent can create Convex projects, deploy backends and set env vars. Use when the user wants to connect Convex, npx convex login status fails, or before create-software needs a database.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you got this skill from a link instead of a local folder, install nothing else from the repo: fetch a file only when a step needs it, …

    line 8
  2. Very specific:

    Make sure Node works (node --version, v20 or higher).

    line 10
  3. Very specific:

    If npx convex@latest login status already shows a signed-in account and a team, skip to step 4.

    line 11
  4. Distinctive:

    Start the login in the background, with the output in a file you can read:

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Connect the user's Convex account to the Convex CLI on this machine so the agent can create and deploy backends. Do every step yourself and only ask for what needs a human (creating the account, approving the login). Talk to the user in their language, short messages, no jargon (never say "CLI", "deployment key" or "device" to them).

If you got this skill from a link instead of a local folder, install nothing else from the repo: fetch a file only when a step needs it, with curl -fsSL https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/setup-convex/<path> -o <scratch>/<file>, and read another skill it names only when you reach it, from https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/<skill-name>/SKILL.md.

  1. Make sure Node works (node --version, v20 or higher); if not, run the setup-node skill first. Convex runs through npx, nothing else to install.
  2. If npx convex@latest login status already shows a signed-in account and a team, skip to step 4.

  3. Start the login in the background, with the output in a file you can read:

    npx -y convex@latest login --no-open --login-flow poll --device-name "$(hostname)" < /dev/null > <scratch>/convex-login.txt 2>&1

    Read the link (and the code if one is shown) from that file and give it to the user (open it in Chrome AI when setup-dev-browser is done). If they have no Convex account, they create one on that page with GitHub or Google, then approve the device and say "done". Check npx convex@latest login status until it shows their team.

  4. Prove it: npx convex@latest login status lists their account and at least one team. Do not create a project now; create-software creates one per app with npx convex dev --once.

End with a short check list, a check or a cross on each line: Node works, signed in to Convex, team <name> found. Then tell the user in one line that the agent can now create the database and backend of their apps.

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