tribgames/mixdog/setup

Claude Code and agent skill by tribgames/mixdog

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Inspect or change persisted Mixdog settings through the built-in setup tool.

Install

npx vskill@latest install tribgames/mixdog/setup

SKILL.md

Mixdog setup

Match the request to one settings domain, inspect current state, use the supported setup action, and read its result as the change receipt.

The tool schema owns action fields and live values. This skill owns routing,
approval boundaries, UI handoff, and cross-domain distinctions.

Non-negotiable boundaries

  • Use the setup tool for persisted Mixdog configuration. Never edit

mixdog-config.json or internal stores directly; if the tool and UI expose no supported path, report that limitation. The one exception is the definition file a workflow or agent read_definition returns as path.

  • API keys, OAuth credentials, tokens, and usage sign-ins stay out of tool

arguments and the transcript. Open the Providers surface and let the user enter them.

  • Developer option "Allow all actions" (allowAllActions) can only be turned

on by the person in the desktop app; the tool refuses it even with riskAccepted:true, and remote enablement is refused too. Open developer instead.

  • A mutation follows the active workflow's approval rules. Status, catalog,

definition and MCP-config reads do not change persisted settings. Deleting a hook rule and forgetting provider authentication are destructive and need explicit approval; disabling preserves.

  • Notification permission/subscription, pairing credentials, and authentication

remain user-operated UI handoffs. Do not imitate them by editing storage.

  • Most changes affect new sessions. Report appliedToCurrentSession and

appliesTo exactly when the result supplies them.

  • Ownership: source edits, builds, installation deployment, releases and app

restarts are not setup's. Managed local-model installation and recovery belong to local-provider (same setup tool; ordinary route settings stay here), skill authoring to skill-creator, Core Memory entries to the memory tool. Read a definition before editing it.

  • Setup changes settings; it does not stop work. Use the owner: session

cancel (another session's turn, a routine run, a group room's exchange; a Browser/Computer takeover ends with its turn), agent cancel/close, task (background shell jobs); the user pauses or stops an active Goal from its controls. Setup only prevents more: set_automation_enabled false, fallbacks: [], cancel_quota_resume, set_builtin_enabled browser/computer off.

Core loop

  1. Select one status domain and inspect it. Do not start with the full summary

when a narrower domain answers the request.

  1. Decide whether the request has a supported mutation, requires a UI handoff,

or is not exposed.

  1. For a supported mutation, send only the fields the user intends to change.

Partial route and profile updates preserve omitted fields.

  1. Read the mutation result, including saved, scope, appliesTo,

appliedToCurrentSession, and requiresReload when present. Background installation receipts are not evidence of completed installation. Call the narrow status domain afterward only when the receipt does not already prove the persisted value.

  1. Report what changed and whether it applies now or in a new session.

Completion means the persisted state or UI handoff is evidenced, not merely that a call returned without transport error.

Distinctions to keep in mind

  • Main model, agent models, and Web Search model are separate routes. An

explicitly empty agent or Web Search provider restores Main inheritance; omission never resets it. Disabling an agent preserves its route.

  • Built-ins have installation state separate from enabled state; Visualize and

Media generation are toggle-only (set_builtin_enabled, no install step).

  • Unknown keys and retired configuration are diagnostics, not permission for

direct cleanup. Do not expose internal-only configuration as a supported user option.

Failure handling

  • A headless open returns opened:false; relay its guidance instead of

pretending a window opened.

  • Desktop requests require a single live claimant and a confirmed receipt.

A timeout or cancelled request is not success. If execution already started, inspect state before retrying; do not resubmit a possibly completed mutation.

  • Do not commit, deploy, restart, or update the app unless separately requested

and approved.

Resources

  • references/actions.md — read when selecting a mutation, explaining domain

behavior or change timing, or diagnosing MCP, plugin, or built-in failures.

  • references/surfaces.md — read when the user asks where a setting lives, a

secret must be entered, or no setup mutation exists.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/tribgames/mixdog/setup/badge)](https://verified-skill.com/skills/tribgames/mixdog/setup)

Something wrong with this skill or its page? Tell us.