Diagram

---
name: diagram
description: Create, refine, or review explanatory diagrams and data charts. Use only when explicitly invoked.
disable-model-invocation: true
---

# Hope Diagram

Use only when the person invokes `$hope:diagram`, `/hope:diagram`, or the
host's equivalent skill command or picker. Continue follow-ups within that
invoked task without requiring another invocation. Ordinary requests and calls
from another skill do not activate this skill; continue authorized work through
the ordinary workflow. Reading a shared reference does not invoke its skill.

Make the relationship or quantitative claim easier to understand. When working
inside another task, preserve its scope, facts, evidence, artifact schema,
visual system, and completion conditions. Improve the existing result; create
another file only when the task needs one.

Read `references/diagram-standard.md` for visual selection, composition,
accessibility, and rendered verification. Also read `references/chart-standard.md`
when position, length, area, width, angle, or another visual property encodes a
quantity.

Use the smallest suitable format the host can render and the person can inspect.
Respect a requested format or an artifact's allowed visual kinds. Resolve
routine presentation choices from context and continue; ask only when the
choice would materially change the requested result.

Inside a Hope HTML artifact, inherit its Technical Record theme, typography,
and responsive shell. A standalone HTML visual uses the same dual-mode
language; read `../../assets/artifact-theme.mjs` and embed its current roles.

Inspect the rendered result at its intended size using the standard. Fix
material defects and recheck what the fixes affect. Finish when the result
meets its reading purpose and the necessary visual checks pass.
Return the finished artifact or review findings with material assumptions,
omissions, and verification gaps. A review request alone does not authorize
editing its target.