agentleFS
GavinGreenwoodGavinGreenwood/agentic-workflow-template/.agents/skills/run/SKILL.md

run

Skill5 starsChanged 44 days agoMITView on GitHub

Launch and drive this project's app for visual verification. Reads ports from env files, checks if servers are already running, starts them if needed, and guides Playwright-based screenshot and interaction.

  • Reads credentials
  • Installs packages

48 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use init, report and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    init

    Also in 4 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 5 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 4 projects that use this

  • +1 more from microsoft

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 9

    Distinctive

    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. Distinctive:

    Use this skill whenever you need to start the app and visually verify a UI change.

    line 8
  2. Distinctive:

    Read ports from the env files before doing anything else:

    line 16
  3. Very specific:

    If apps/web/.env is missing, copy apps/web/.env.example → apps/web/.env.local and fill in the required values, then re-read.

    line 23
  4. Distinctive:

    Do not loop or sleep-poll.

    line 48
  5. Distinctive:

    Use the current runtime's background-process option so the agent does not hang indefinitely.

    line 67
  6. Very specific:

    Before navigating, confirm that the current runtime exposes tools from the playwright MCP server.

    line 73
  7. Distinctive:

    If the server is disconnected, unapproved, or missing, report that exact setup problem before continuing.

    line 79
  8. Very specific:

    Use the Playwright MCP browser_navigate tool exposed by the current runtime to open the app:

    line 85
  9. Distinctive:

    Read the saved screenshot from the absolute project root path to visually verify it is not blank.

    line 98
  10. Very specific:

    If the app redirects to a login page, check apps/web/.env for test credentials:

    line 104
  11. Distinctive:

    If no auth is configured, skip this step.

    line 113
  12. Distinctive:

    Use snapshots (accessibility tree / DOM snapshot) to locate element references before clicking.

    line 133
  13. Distinctive:

    Use screenshots for visual before/after comparisons.

    line 134

“Common” is measured: kept by at least 6 in 10 of the 44 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

Run — Launch and verify the app

Use this skill whenever you need to start the app and visually verify a UI change.


Step 1 — Read the actual ports

This step is mandatory. Never skip it. Never assume a port.

Read ports from the env files before doing anything else:

grep -E "^PORT=" apps/web/.env 2>/dev/null || echo "PORT=3000"   # web port  (default 3000)
grep -E "^PORT=" apps/api/.env 2>/dev/null || echo "PORT=3001"   # API port  (default 3001)
  • If apps/web/.env is missing, copy apps/web/.env.example → apps/web/.env.local and fill in the required values, then re-read.
  • WEB_PORT = PORT value from apps/web/.env if present; otherwise default to 3000.
  • API_PORT = PORT value from apps/api/.env if present; otherwise default to 3001.

Every URL constructed in subsequent steps must use these values. Using any other port is wrong.


Step 2 — Check if servers are already running

Check both independently:

curl -s -o /dev/null -w "%{http_code}" http://localhost:<WEB_PORT>/
curl -s -o /dev/null -w "%{http_code}" http://localhost:<API_PORT>/healthz

Interpret the result as follows:

  • 000 — connection refused; the server is not running.
  • Any other code (200, 302, 401, 404, 503, etc.) — TCP connection succeeded; the server is up.
  • Both up → skip to Step 5.
  • One or both down → proceed to Step 3.

Do not loop or sleep-poll. One check only. If not ready, say so and let the user know to try again in ~10 s.


Step 3 — Start the dev servers (only if not running)

First check that dependencies are installed:

# If node_modules is absent or turbo binary is missing, install first
test -f node_modules/.bin/turbo || npm install

On Windows, run the command in PowerShell rather than Bash. Bash on Windows does not resolve local node_modules/.bin binaries, so next and nest will fail with "not recognized":

npm run dev

Use the current runtime's background-process option so the agent does not hang indefinitely. Then do a single readiness check after a short wait (~15 s). If still not responding, report it and stop — do not loop.


Step 4 — Verify Playwright MCP is available

Before navigating, confirm that the current runtime exposes tools from the playwright MCP server.

  • Claude Code and GitHub Copilot CLI use the root .mcp.json.
  • Codex uses .codex/config.toml.
  • GitHub Copilot coding agent provides its built-in Playwright MCP server.

If the server is disconnected, unapproved, or missing, report that exact setup problem before continuing.


Step 5 — Navigate to the app

Use the Playwright MCP browser_navigate tool exposed by the current runtime to open the app:

url: http://localhost:<WEB_PORT>/

Then use its browser_take_screenshot tool to confirm the page rendered:

type: png
filename: screenshot.png

Read the saved screenshot from the absolute project root path to visually verify it is not blank.


Step 6 — Handle authentication (if applicable)

If the app redirects to a login page, check apps/web/.env for test credentials:

grep -E "^(TEST_USER|TEST_EMAIL|TEST_USERNAME|E2E_USERNAME)=" apps/web/.env
grep -E "^(TEST_PASSWORD|TEST_PASS|E2E_PASSWORD)=" apps/web/.env

Fill in the credentials and submit. Wait for the redirect to the main app before continuing.

If no auth is configured, skip this step.


Step 7 — Drive the app

Navigate, click, and inspect as needed for the verification task. Key routes for this template:

RouteWhat it shows
/Landing / home page
/apiAPI root (NestJS)

Adjust routes to match the feature under test.


Step 8 — Screenshots and snapshots

  • Screenshots are saved to the project root (e.g. ./screenshot.png). Read them from the absolute path.
  • Use snapshots (accessibility tree / DOM snapshot) to locate element references before clicking.
  • Use screenshots for visual before/after comparisons.

Notes

  • The API exposes /healthz and /readyz for readiness checks (NestJS default from this template).
  • Next.js dev server starts on port 3000 by default; NestJS starts on 3001. Override with PORT= in the respective .env file.
  • npm run dev at the repo root uses Turborepo and starts both apps/web and apps/api concurrently.

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.