agentleFS
Sign inStart free
AvinavaAvinava/agentic-react-express-ts/skills/onboard-an-agent/SKILL.md

onboard-an-agent

Skill0 starsChanged 6 months agoMITView on GitHub

Use the first time an agent (or human) opens this repo. Installs deps, prepares the env, validates that the dev environment works, and points the agent at the right files.

  • Reads credentials
  • Installs packages

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:

    Use this skill the very first time you open this repo.

    line 8
  2. Very specific:

    If Postgres isn't running locally, install it (brew install postgresql@16 && brew services start postgresql@16 on macOS) or point …

    line 21
  3. Very specific:

    If db:setup errors, the most common causes are: wrong port, wrong user/password, or Postgres not running.

    line 46
  4. Distinctive:

    All four must pass before touching application code.

    line 57

≈ “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

Onboard an agent

Use this skill the very first time you open this repo. Five minutes from clone to "dev server running, tests green, ready to ship features."

Steps

1. Confirm prerequisites

node --version    # must be >= 22
which psql        # Postgres client should be installed
pg_isready        # Postgres should be running
git --version

If Postgres isn't running locally, install it (brew install postgresql@16 && brew services start postgresql@16 on macOS) or point DATABASE_URL at a remote instance later.

2. Install dependencies

npm install

This installs Node packages and wires up Lefthook (prepare script). After this, git commit will run the full pre-commit pipeline.

3. Configure environment

cp example.env .env

Open .env and confirm DATABASE_URL matches your local (or remote) Postgres. The default points to postgresql://postgres:postgres@localhost:5432/agentic_react_express_ts.

4. Initialize the database

npm run db:setup    # runs `prisma migrate dev` + `prisma generate`
npm run db:seed     # loads demo CRM data

If db:setup errors, the most common causes are: wrong port, wrong user/password, or Postgres not running. Fix DATABASE_URL and retry — do NOT delete the migrations directory.

5. Verify everything works

npm run typecheck   # zero errors
npm run lint        # zero warnings
npm run test:run    # all pass
npm run build       # production build succeeds

All four must pass before touching application code. If something fails, do not start coding — debug the failure first. The guardrails are the whole point.

6. Start the dev server

npm run dev

Open http://localhost:3000. You should see the homepage, then Contacts/Tasks/Projects with seeded data.

7. Read the rest

  • AGENTS.md — conventions, stack, scripts
  • skills/add-resource/SKILL.md — how to add a new CRUD resource
  • skills/self-correcting-loop/SKILL.md — what to do when a commit is rejected

You're done. Pick a task and start building.

Troubleshooting

SymptomFix
npm install fails with peer dep errorsConfirm Node >= 22 (nvm use)
prisma migrate dev says "Can't reach database"Check Postgres is running, DATABASE_URL matches
npm run dev shows blank pageCheck the server (:3001) is up. Browser DevTools → Network → look at /trpc/… calls
Pre-commit fails on a fresh cloneThe guardrails work — read self-correcting-loop

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