Choose review-friendly visual explanations with ox viz. Use when creating or updating a PR description, especially for architecture, lifecycle, data flow, before/after, or multi-component changes; also use for plans, docs, reports, and design notes. Start a material PR description with `ox viz pr`; ask a known reviewer question through `ox viz pr --intent "<question>" --json`.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add sageox/agent-toolkit --skill ox-viz --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Ox Viz?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/sageox-ox-viz)More formats (shields.io, HTML) on the badges page.
---
name: ox-viz
description: >-
Choose review-friendly visual explanations with ox viz. Use when creating or
updating a PR description, especially for architecture, lifecycle, data flow,
before/after, or multi-component changes; also use for plans, docs, reports,
and design notes. Start a material PR description with `ox viz pr`; ask a
known reviewer question through `ox viz pr --intent "<question>" --json`.
---
<!-- Thin by design. The portable behavior lives in the visualization-guidance
floor of `ox agent prime` and the live `ox viz pr` output, which reach every
AI coworker. This skill adds only native activation ergonomics. Do not grow
this body into a second catalog or authoring guide. -->
For PR work, run `ox viz pr` before drafting. For a reviewer question, run
`ox viz pr --intent "<question>" --json`; apply the selected result's
`guidance`, then pull its recipe with `ox viz <id>`. For all other artifacts,
use `ox viz suggest "<intent>"` and do the same.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
