agentleFS
Sign inStart free
rpraharajrpraharaj/ai-sdlc/skills/start-project/SKILL.md

start-project

Skill0 starsChanged 17 days agoMITView on GitHub

Start a new project from an empty or near-empty directory using the stack the user named. Use when there is no existing app, or the user says new project, scaffold, greenfield, or from scratch. Do not invent a stack they did not choose.

9 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 3

    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:

    Create the smallest runnable project they asked for.

    line 17
  2. Distinctive:

    Stop if there is a source tree with a manifest, lockfile, or more than bootstrap files.

    line 26
  3. Very specific:

    If any are missing, ask one blocking question listing the gaps.

    line 32
  4. Distinctive:

    Prefer the official init for the named toolchain.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 8 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

Start project

Create the smallest runnable project they asked for. Do not pick a framework for them. Do not add a product feature beyond hello + checks that prove it runs.

Is this the right skill?

SignalDo this instead
Workspace already has an applicationexplore-codebase / implement-change
Add an app in a monorepostay in the named package; match siblings

Stop if there is a source tree with a manifest, lockfile, or more than bootstrap files.

Required inputs

  • Language, kind (app / lib / CLI / service), and tools the user named

If any are missing, ask one blocking question listing the gaps. Do not recommend a trendy stack. Do not run a third-party create-* unless they named that exact tool.

Human decisions (do not invent)

  • The stack

Procedure

  1. Prefer the official init for the named toolchain. Match the package manager they named.
  2. One entry point that runs. One test that fails if the entry is broken, in that toolchain’s runner.
  3. Root README with Install / Run / Test from commands you actually used.
  4. Fill AGENTS.md from ../explore-codebase/references/agents-template.md using those commands.
  5. Load engineering-bar. Climb Minimum path. No extra CI unless asked. No secrets.

Output

  • Path: new project files + AGENTS.md + README.md
  • Session report: references/start-notes.md
  • AGENTS.md body: ../explore-codebase/references/agents-template.md

Quality bar

  • Stack is user-named
  • Test command was run or marked unverified
  • No extra dependencies you were not asked for
  • No secrets committed

Done

  1. Stack and kind
  2. Files created
  3. Commands run and results
  4. Next: write-prd if product is open, else shape-work

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