agentleFS
hellocrossmanwildhellocrossmanwild/Claude-skills-tools/skills/stack-check/SKILL.md

stack-check

Skill0 starsChanged 37 days agoMITView on GitHub

Recommends the simplest production stack for an app and estimates its monthly running cost. Use for 'what tools do I need', 'which stack', 'hosting' or 'how much will it cost to run'.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do people need to log in? (yes / no / later)

    line 12
  2. Distinctive:

    Start from this default and remove anything they don't need:

    line 19
  3. Distinctive:

    Check current pricing before quoting numbers: Use web search or the tool's own pricing page if you can.

    line 33
  4. Distinctive:

    Never sign anyone up for anything or enter payment details.

    line 45

≈ “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

Stack check

You're advising someone who doesn't code on which tools their app needs. Be plain, practical and honest about cost. Recommend the fewest tools that do the job.

1. Understand the app (ask one question at a time, with tap-to-answer options where you can)

  • What does the app do, and who uses it?
  • Do people need to log in? (yes / no / later)
  • Will it take payments? (one-off / subscriptions / not yet)
  • Does it need to send emails? (receipts, sign-in codes, newsletters / no)
  • Does it need to remember things between visits? (users, orders, content / no)
  • Roughly how many users in the first few months? (under 100 / hundreds / thousands)

2. Recommend the stack

Start from this default and remove anything they don't need:

JobDefault toolNeeded when
Stores the codeGitHubAlways
Puts it onlineVercelAlways
Remembers dataNeon (Postgres)Users, orders, content
Handles loginsClerkPeople sign in
Takes paymentsStripeMoney changes hands
Sends emailsResendReceipts, codes, notifications

Explain each kept tool in one line ("Vercel puts it on the internet"). Say clearly what they don't need yet (AWS, Kubernetes, microservices, writing their own login or payment code) and why: those solve problems at a scale they don't have.

3. Estimate the monthly cost

  • Check current pricing before quoting numbers. Use web search or the tool's own pricing page if you can. Prices change, so say what date you checked.
  • Flag the free plans that aren't free for them: for example, Vercel's free Hobby plan is for personal, non-commercial use, so a paid app needs the paid plan.
  • Separate fixed costs (monthly plans) from per-use costs (card fees per payment, emails over the free allowance).
  • Mention that building with Claude Desktop's Code tab needs a paid Claude plan, on top of the stack.
  • Give a simple total: "about £X–Y a month until you outgrow the free tiers, plus card fees."

4. Hand over

Finish with a short summary they can keep:

  • The stack, one line per tool
  • What it costs now, and what will make it cost more
  • What to set up first (GitHub, then Vercel)

Never sign anyone up for anything or enter payment details. Recommend only.

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.

Reviews can't be read right now.

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.