Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Check current Railway project status for this directory. Use when user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables or configuration queries - use railway-environment skill for those.
.claude/skills/davila7-railway-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -23% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 9% | 0% |
| case-08 | ✓→✗ | ▼ Worse | -54% | 0% |
| case-22 | ✓→✓ | = Same ✓ | -1% | 0% |
Check the current Railway project status for this directory.
Use the railway-environment skill instead when user wants:
Run:
bashrailway status --json
First verify CLI is installed:
bashcommand -v railway
If command -v railway fails:
> Railway CLI is not installed. Install with: > > npm install -g @railway/cli > > or > > brew install railway > > Then authenticate: railway login
If railway whoami fails:
> Not logged in to Railway. Run: > > railway login >
If status returns "No linked project":
> No Railway project linked to this directory. > > To link an existing project: railway link > To create a new project: railway init
Parse the JSON and present:
activeDeployments field)Example output format:
Project: my-app (workspace: my-team)
Environment: production
Services:
- web: deployed (https://my-app.up.railway.app)
- api: deploying (build in progress)
- postgres: runningThe activeDeployments array on each service shows currently running deployments with their status (building, deploying, etc.).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 4,683 | 1,395 | -70% | 1 | 1 | 0% | 653 | 648 | -1% | 0 | 0 | — |
case-15 | fail→fail | 4,699 | 4,915 | +5% | 1 | 1 | 0% | 763 | 629 | -18% | 0 | 0 | — |
case-16 | fail→fail | 6,927 | 4,990 | -28% | 1 | 1 | 0% | 1,049 | 689 | -34% | 0 | 0 | — |
case-03 | fail→fail | 8,713 | 4,702 | -46% | 1 | 1 | 0% | 1,371 | 674 | -51% | 0 | 0 | — |
case-01 | fail→fail | 3,061 | 4,425 | +45% | 1 | 1 | 0% | 278 | 677 | +144% | 0 | 0 | — |
case-02 | fail→fail | 5,094 | 4,425 | -13% | 1 | 1 | 0% | 819 | 678 | -17% | 0 | 0 | — |
case-14 | fail→fail | 4,880 | 5,480 | +12% | 1 | 1 | 0% | 670 | 661 | -1% | 0 | 0 | — |
case-04 | pass→pass | 9,132 | 11,139 | +22% | 1 | 1 | 0% | 1,494 | 1,780 | +19% | 0 | 0 | — |
case-05 | pass→fail | 6,998 | 7,227 | +3% | 1 | 1 | 0% | 1,050 | 804 | -23% | 0 | 0 | — |
case-06 | pass→fail | 5,336 | 6,748 | +26% | 1 | 1 | 0% | 875 | 950 | +9% | 0 | 0 | — |
case-07 | fail→fail | 3,017 | 3,152 | +4% | 1 | 1 | 0% | 441 | 604 | +37% | 0 | 0 | — |
case-08 | pass→fail | 11,572 | 4,196 | -64% | 1 | 1 | 0% | 1,451 | 663 | -54% | 0 | 0 | — |
case-09 | pass→pass | 5,375 | 3,115 | -42% | 1 | 1 | 0% | 987 | 903 | -9% | 0 | 0 | — |
case-10 | pass→pass | 6,560 | 3,026 | -54% | 1 | 1 | 0% | 1,157 | 920 | -20% | 0 | 0 | — |
case-11 | fail→pass | 7,761 | 4,348 | -44% | 1 | 1 | 0% | 1,492 | 1,078 | -28% | 0 | 0 | — |
case-12 | fail→fail | 8,527 | 5,660 | -34% | 1 | 1 | 0% | 1,363 | 629 | -54% | 0 | 0 | — |
case-13 | fail→fail | 5,782 | 4,983 | -14% | 1 | 1 | 0% | 212 | 649 | +206% | 0 | 0 | — |
case-17 | fail→fail | 5,659 | 5,041 | -11% | 1 | 1 | 0% | 913 | 684 | -25% | 0 | 0 | — |
case-18 | pass→pass | 4,709 | 2,688 | -43% | 1 | 1 | 0% | 814 | 823 | +1% | 0 | 0 | — |
case-19 | pass→pass | 2,979 | 2,852 | -4% | 1 | 1 | 0% | 320 | 779 | +143% | 0 | 0 | — |
case-20 | pass→pass | 4,315 | 1,745 | -60% | 1 | 1 | 0% | 684 | 749 | +10% | 0 | 0 | — |
case-21 | pass→pass | 2,469 | 2,049 | -17% | 1 | 1 | 0% | 352 | 658 | +87% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 9 counted toward the lift figure. The other 13 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -9 percentage points is the difference between those two pass rates over the 9 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.