Tricentis/mcp-skills / Tosca/Cloud/CLI/claude/skills/tosca-login
tosca-login
VerifiedLog in to Tosca Cloud, detecting configured URL from current config or prompting for one
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.4 KB |
SKILL.md
View on GitHub---
name: tosca-login
description: Log in to Tosca Cloud, detecting configured URL from current config or prompting for one
user-invocable: true
allowed-tools: Bash(toscactl *)
argument-hint: "[tenant-url]"
---
# Log In to Tosca Cloud
Authenticate with Tosca Cloud using browser-based login.
Always use `--json --silent` on every `toscactl` command.
## Steps
1. **Check current config.** Run `toscactl config --json --silent`.
2. **Determine the URL.**
- If `$ARGUMENTS` contains a URL, use it directly — skip to step 3.
- If the config output contains a tenant URL, show it to the user and ask: _"Use this URL to log in: `<url>`?"_
- If the user confirms, use that URL.
- If the user declines, ask them to provide a URL.
- If no URL is in the config, ask the user: _"Enter your Tosca Cloud tenant URL (e.g. `tenant.my.tricentis.com`):"_
3. **Login.** Run `toscactl login --url <URL> --json --silent`.
- Do **not** use `--headless` unless the user explicitly requests it — this opens the browser for PKCE authentication.
4. **Confirm.** Run `toscactl config --json --silent` and report the authenticated tenant and active workspace.
## Error Handling
- If login fails, suggest verifying the URL format (`tenant.my.tricentis.com`) and network connectivity.
- For CI/headless environments, mention that setting `TOSCA_CLIENT_ID` and `TOSCA_CLIENT_SECRET` environment variables enables non-interactive authentication.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |