Relewise/relewise-agent-plugins / plugins/relewise/skills/relewise-setup
relewise-setup
VerifiedSet up, verify, or repair Relewise Agent Gateway authentication. Use when a user wants to connect Relewise, sign in or reconnect with OAuth, diagnose MCP connectivity, configure a Personal Access Token, resolve missing Dataset access or Agent Gateway configuration, or check whether Relewise is already connected.
Relewise Setup
Never ask the user to paste a Personal Access Token into the conversation. Do not print, repeat, inspect, or place a token in command text, command arguments, output, logs, or repository files.
My Relewise is the web portal at https://my.relewise.com, separate from the AI client running this skill. When directing the user to portal configuration, say explicitly that the page opens in My Relewise and provide a clickable deep link. Use only the fixed My Relewise setup links.
Before any Agent Gateway call, activate and follow the installed relewise-agent-gateway skill from this plugin. Pass it the identity operation or MCP tool; do not resolve the CLI, choose a transport, or handle transport mechanics in this setup skill. This setup is idempotent: verify existing authentication before changing anything, and preserve a reusable route that works within the user's requested authentication method while checking Dataset readiness. For an explicit OAuth-only requirement, use the host-managed Agent Gateway MCP connection throughout setup and verification.
Set up or repair authentication
- Verify identity using the registered MCP tool
get_mefirst. If the tool is missing or fails, have the Agent Gateway skill perform its MCP connection preflight. Use the preflight findings to identify the required connection action. - If identity succeeds, retain its authentication metadata and candidate Datasets. Follow Dataset access and readiness for an empty Dataset list, a missing expected Dataset, or policy restrictions. For the intended Dataset, use
relewise-coreto verify details and effective policy. Report authentication success separately from readiness for Dataset operations. - For new connections or repairs, follow authentication setup, starting with the client's OAuth sign-in or reconnect flow when supported. Start the supported flow when available. Let the user complete browser sign-in and consent.
- If OAuth cannot start, report the observed connection or discovery failure and the next corrective action. Keep OAuth support unverified until the MCP preflight establishes it. For an OAuth-only request, keep setup pending on the identified OAuth blocker.
- Use PAT setup only when the user explicitly chooses it or the client/server is confirmed not to support OAuth. Existing authenticated fallbacks may be verified under the Agent Gateway skill's transport rules when the user has not restricted the authentication method. Let the user create, store, or replace any PAT outside the conversation. Use current official documentation for concrete client configuration steps.
- After sign-in, refresh the client's MCP connection or tool discovery as supported, then verify
get_me. If a client restart is needed, state that verification is pending until it restarts. Afterget_mesucceeds, apply step 2 to verify Dataset readiness. For PAT routes, verify identity after configuration; a changed environment variable may require restarting the client. If verification fails, explain the specific next corrective action without repeating unchanged steps.
The workflow is idempotent: every invocation starts by verifying the current configuration, and a working setup is never replaced merely because the skill was invoked again. Authentication is complete when the route is reusable without repeated sign-in or credential entry. Dataset setup remains pending until the intended Dataset and required policy are verified; use the completion states in the Dataset access reference.
Do not create, regenerate, revoke, or change the scope of a Personal Access Token on the user's behalf. Explain those actions and their consequences, link to the relevant My Relewise page, then let the user perform them there.
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |