agentleFS
xAIKnown publisherxai-org/customer-education-workshops/ledgerly/.cursor/skills/start-ledgerly/SKILL.md

start-ledgerly

Skill3 starsChanged 7 days agoApache-2.0View on GitHub

Start the Ledgerly Next.js app on port 43173, seed SQLite only when the database is missing or empty, open the app in the Grok Build Browser, and open the native Runbooks canvas. Use when the user asks to start the server, start the application, run the demo app, open Ledgerly in the browser, or seed if it has not already been seeded.

  • Installs packages

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If node_modules is missing:

    line 14
  2. Very specific:

    Never run prisma migrate or npm run db:reset from this skill.

    line 43
  3. Very specific:

    If a terminal already has npm run dev on 43173, or http://127.0.0.1:43173 responds, leave it.

    line 47
  4. Very specific:

    Do not lsof | kill a busy 43173 — that is a reset, not a start.

    line 57
  5. Distinctive:

    After the server is Ready (or already responding), do both of these even when the server was already running.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Start Ledgerly

Bring up the app. Do not reset demo state, restore files, or kill a healthy server.

Listen on 43173. Schema URL is file:./dev.db in prisma/schema.prisma. Seed is idempotent (prisma db push then Fieldnote data) but skip it when data is already there.

1. Dependencies

If node_modules is missing:

npm i
npx prisma generate

2. Seed only if needed

The database needs seed when prisma/dev.db is missing, Prisma cannot query Customer, or customer.count() is 0.

npx tsx -e '
import { PrismaClient } from "@prisma/client";
const prisma = new PrismaClient();
try {
  const n = await prisma.customer.count();
  console.log(n > 0 ? "seeded" : "empty");
} catch {
  console.log("missing");
} finally {
  await prisma.$disconnect();
}
'
  • seeded — do not seed.
  • empty or missing — run npx prisma db seed.

Never run prisma migrate or npm run db:reset from this skill. Those belong to reset-demo-state.

3. Start the server

If a terminal already has npm run dev on 43173, or http://127.0.0.1:43173 responds, leave it. Report the URL.

Otherwise start in the background:

npm run dev

Request host/all permissions if bind fails (uv_interface_addresses or similar). Wait until the log shows Ready / http://localhost:43173.

Do not lsof | kill a busy 43173 — that is a reset, not a start.

4. Open the application, then the native Runbooks canvas

After the server is Ready (or already responding), do both of these even when the server was already running.

  1. Open the Grok Build Browser (cursor-ide-browser) to http://localhost:43173. Use position: "active" so the browser is visible. This tab is the Ledgerly application. Leave it there. Do not use an external browser. Do not open a second browser tab for the runbooks. Do not open the in-app /runbooks route.
  2. Open the native Runbooks canvas. Read ~/.cursor/skills-cursor/canvas/SKILL.md. Read runbooks.canvas.tsx from this app root and write it with the file tool onto the workspace canvases path (overwrite if it exists):

    /Users/<user>/.cursor/projects/<workspace>/canvases/runbooks.canvas.tsx

    Then open that file (open_resource). Do not embed HTML. Do not open runbooks.html. The committed file is generated from runbooks/meta.ts by npm run runbooks:export; do not hand-edit it. This is the same numbered-steps canvas present-runbooks opens.

    The canvas is native cursor/canvas UI:

    • Catalog tabs for 101 / 201 / 301 / 401 (useCanvasState runbooks-track, default "101")
    • Numbered steps (Step 1, Step 2, …) in one scrolling list under section headings
    • Optional-feature checkboxes on 301 (runbooks-features), on by default
    • Copy on each prompt card (navigator.clipboard)

    runbooks.html is a fallback only if the native canvas cannot open.

5. Confirm

Report http://localhost:43173, the canvas file path, that catalog tabs are 101 / 201 / 301 / 401, and whether you seeded or skipped seed. The browser tab is the Ledgerly dashboard. The canvas shows Catalog tabs, numbered steps, and Copy on each prompt.

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.