skilld
All skills
simota avatar

/canvas

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Visualizing code, specs, or context as Mermaid, ASCII, or draw.io diagrams: flowcharts, sequence/state/class/ER, Journey Maps, personas, coverage heatmaps. Use to reverse-document systems visually.

Ask your Agent

Use this Skill: https://skilld.dev/gh/simota/agent-skills/canvas

This session only. Nothing lands on disk.

referencec4-model.md

≈331 tokens on demand. Your agent reads this file only when SKILL.md points to it.

C4 Model Delta

Purpose: Canvas-specific level and clarification contract. General C4 notation is model-known; source names and relationships must come from the repository or supplied architecture.

Level Contract

Level Use Default audience
Context System boundary and external actors Product / leadership
Container Deployable or runtime units Engineering / operations
Component Internals of one container Implementers / reviewers
  • Default to Context or Container and draw exactly one level per diagram.
  • Limit Component scope to one container. Route code-level structure to Canvas class rather than inventing a C4 L4 view.
  • If Structurizr DSL exists, derive names and relationships from it.

Clarification Gates

  • ON_C4_LEVEL: Context / Container / Component.
  • ON_C4_SCOPE: whole system / one service / one container.
  • ON_C4_AUDIENCE: product / engineering / operations / mixed.

Ask only when the unresolved choice would materially change the diagram; otherwise use the safest narrow default and state it.

Verification

  • One level and one system boundary per diagram.
  • Real actors, containers, components, and relationships only.
  • Scope and audience stated in the title or note.
  • Syntax and accessibility follow canvas/SKILL.md REVIEW gates.

Source: SKILL.md on GitHub

Third-party checks

No alerts13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The skill provides comprehensive visualization and reverse-engineering capabilities using Mermaid and other diagramming tools. It possesses a potential attack surface for indirect prompt injection by processing untrusted project code, though it includes best-practice instructions for source disclosure and uncertainty marking. It also documentedly uses well-known external rendering services like Kroki for processing diagram DSL.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    14 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/canvas