Browse skills

Use Avibe's local Computer Use CLI for carefully bounded desktop observation and actions.

The English summary is being prepared. Showing the original description.

Deliver Avibe, avibe-bot-backend, avibe-docs, avault, and vault-sandbox PRs from worktree and implementation through Codex review, CI, and Merge. Use it for implementation work on every Agent backend.

The English summary is being prepared. Showing the original description.

Run durable `vibe watch` waits for PR reviews, CI, files or external signals, then resume the Agent in the right Session.

The English summary is being prepared. Showing the original description.

Safely inspect and modify local Avibe configuration, routing, runtime settings, watches, scheduled tasks, Avibe Cloud remote access, and operational state. Also use it to report an Avibe bug, send product feedback, or file a feature request from the current conversation.

The English summary is being prepared. Showing the original description.

Build, inspect, update, restore, or share Avibe Show Pages for visual explanations, diagrams, reports, or interactive prototypes. Covers the page workspace and its Git history.

The English summary is being prepared. Showing the original description.

Use the official Sentry CLI to investigate issues, events, traces, and logs for Vibe Remote without committing Sentry credentials into the repository.

The English summary is being prepared. Showing the original description.

Use Avibe Vault for API keys, tokens, passwords, protected credentials, authenticated HTTP requests, or digest signing without exposing secret values to the agent.

The English summary is being prepared. Showing the original description.

Use Avibe Harness for durable Agent delegation, Sessions, scheduled Tasks, Watches, Runs, queues, and work that must continue beyond the current turn.

The English summary is being prepared. Showing the original description.

Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project rules, Agent system prompts, Skills, delegation briefs, and Task and Watch messages — using real run evidence. Use when an Agent misbehaves (stalls, over-asks, over-reaches, ignores or over-applies a rule), after a model or backend change, or when the user asks to review, clean up, or tighten prompts.

The English summary is being prepared. Showing the original description.