DI

diagram-driven-execution

Follows a provided Mermaid diagram step-by-step, managing task states through a deterministic tracking system.

Install

mkdir -p .claude/skills/diagram-driven-execution && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14423" && unzip -o skill.zip -d .claude/skills/diagram-driven-execution && rm skill.zip

Installs to .claude/skills/diagram-driven-execution

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use this skill when the user supplies a mermaid diagram that represents a process the agent must follow step-by-step with deterministic tracking. Two modes via session SQL todos table (both produce the Copilot visual plan widget): simple (mode="simple"; up to 15 nodes, agent reads diagram from context, inserts todos+todo_deps, no parse script, no gates/loops) and advanced (default mode="advanced"; gates with multi-way routing and escalation, bounded loops via pre-expansion, deterministic parse via parse-diagram.py). Activate on: "follow this diagram", "execute this workflow", "enforce these steps", "track against this state machine", "drive this process", "run this mermaid as a plan", "step me through this flowchart", or any moment a diagram is the source of truth for a procedure. Does NOT execute node bodies; node work is delegated to subagents, tools, or the calling thread.
888 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • →Execute Mermaid diagrams step-by-step
  • →Track process with deterministic SQL-backed storage
  • →Enforce transition order between diagram nodes
  • →Delegate node work to subagents or tools
  • →Handle gate nodes with multi-way routing
  • →Pre-expand loop nodes into sequential iterations

How it works

The skill interprets a Mermaid diagram as a process contract, initializing an execution plan in a SQL store. It then drives nodes to completion, enforcing transition order and delegating node work.

Inputs & outputs

You give it
Mermaid diagram representing a process, optional step annotations
You get back
Execution plan in SQL store, completed diagram nodes, delegated tasks

When to use diagram-driven-execution

  • →Following a multi-step workflow diagram
  • →Enforcing process transitions for complex tasks
  • →Driving state-machine based operations

About diagram-driven-execution

This skill uses Mermaid diagrams as a process contract. It manages task transitions, enforces order, and delegates node work to subagents or specific tools.

>-

When not to use it

  • →When the diagram contains unsupported v1 grammar syntax
  • →When `dde-simple` mode is used with gate or loop nodes
  • →When re-planning an existing diagram with the same `design_id`

Limitations

  • →Discipline-based enforcement only - no script-level transition gate.
  • →`dde-simple` rejects gate/loop nodes at grammar-check time (B10).
  • →v1 grammar excludes subgraphs, composite states, classDefs, click handlers

How it compares

This skill uses Mermaid diagrams for deterministic, SQL-backed process execution and tracking, which differs from manual process management or less structured workflow automation.

Compared to similar skills

diagram-driven-execution side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
diagram-driven-execution (this skill)04moReviewAdvanced
draw05moReviewBeginner
printable06moReviewAdvanced
fritzing-custom-component-workflow04moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry