Skill

diagram-evolve

Use when the user has just added annotations to a diagram and is implicitly or explicitly asking for the diagram to be changed based on those marks — phrases like "fix this", "apply my notes", "make those changes", "address what I marked". Triggers on evolve/apply intent against an annotated tile.

npx claudepluginhub michaeldancurtis/prixmaviz --plugin prixmaviz

Tool Access

This skill uses the workspace's default tool permissions.

Preview

When the user has annotations on the focused tile and wants you to apply them:

SKILL.md

Similar Skills

cache-components

139.4k

Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.

cache-components

pdf

131.6k

Processes PDFs: extracts text/tables/images, merges/splits/rotates pages, adds watermarks, creates/fills forms, encrypts/decrypts, OCRs scans. Activates on PDF mentions or output requests.

11 files

document-skills

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitMay 9, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

diagram-evolve

Diagram Evolution

When the user has annotations on the focused tile and wants you to apply them:

Call get_focused_tile() for the diagramId.

Call get_annotations(diagramId, includeResolved=false) for unresolved annotations only.

Read each annotation's text field and its targetNodes/bboxData/point. Infer the user's intent:

"rename to X" → IR update_node patch on the target with new label
"remove this" → IR remove_node or remove_edge patch
"this should connect to Y" → IR add_edge patch
"add a retry path" → engine-specific structural change
"use a different shape" → IR update_node with new shape

Suggest 1-3 patches: "I'll rename Auth to AuthService, add a retry path from Auth to DB, and remove the orphan Logger node — apply?"

On user confirmation, call apply_patch with all the ops in one call (atomic).

After patches land, call annotations.update(annotationId, {resolvedAt: now}) for each annotation that was addressed — so they fade visually and don't show up as unresolved next time.

If you can't infer the user's intent from an annotation's text, ASK rather than guessing. Wrong patches are harder to undo than no patches.

Diagram Evolution

When the user has annotations on the focused tile and wants you to apply them:

Call get_focused_tile() for the diagramId.
Call get_annotations(diagramId, includeResolved=false) for unresolved annotations only.
Read each annotation's text field and its targetNodes/bboxData/point. Infer the user's intent:
- "rename to X" → IR update_node patch on the target with new label
- "remove this" → IR remove_node or remove_edge patch
- "this should connect to Y" → IR add_edge patch
- "add a retry path" → engine-specific structural change
- "use a different shape" → IR update_node with new shape
Suggest 1-3 patches: "I'll rename Auth to AuthService, add a retry path from Auth to DB, and remove the orphan Logger node — apply?"
On user confirmation, call apply_patch with all the ops in one call (atomic).
After patches land, call annotations.update(annotationId, {resolvedAt: now}) for each annotation that was addressed — so they fade visually and don't show up as unresolved next time.

If you can't infer the user's intent from an annotation's text, ASK rather than guessing. Wrong patches are harder to undo than no patches.