gen-uml
Skill0 starsChanged 57 days agoMITView on GitHub
Use when you need a Mermaid diagram (architecture, flow, or sequence) generated from existing code, and a check that the diagram matches what was actually built.
In this repository14 other files it gives its agents.
- arch-barSkill
- commsSkill
- context-budgetSkill
- exploit-huntSkill
- gdprSkill
- perf-barSkill
- postmortemSkill
- security-barSkill
- spec-intakeSkill
- stack-gotchasSkill
- stacksSkill
- standardsSkill
- task-flowSkill
- ux-barSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Every box maps to a real module/function.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
gen-uml
Overview
Generate a Mermaid diagram from existing code — architecture, flow, or sequence — and verify it reflects what the code actually does, not what it was supposed to do.
Steps
- Read the real code for the slice you're diagramming (entry points, modules, call/data flow). Diagram what exists.
- Pick the diagram type that answers the question being asked (below).
- Emit Mermaid.
- Match-check (required): walk the diagram against the code one node/edge at a time. Every box maps to a real module/function; every arrow to a real call/dependency. Drop or fix anything you can't point to in the source. A diagram that quietly diverges is worse than none.
Types & examples
Architecture (modules/dependencies):
graph TD
UI[UI] --> UC[Use cases]
UC --> SVC[Services]
SVC --> REPO[Repository]
REPO --> DB[(Store)]Flow (a process / decision path):
flowchart TD
A[Receive task] --> B{Brownfield?}
B -- yes --> C[Explore code]
B -- no --> D[Brainstorm]
C --> D --> E[Plan]Sequence (interaction over time):
sequenceDiagram
participant C as Client
participant R as Repo
participant DB as Store
C->>R: save(entity)
R->>DB: update(blob)
DB-->>R: version
R-->>C: okOutput
The Mermaid block plus one line per diagram confirming the match-check passed (or listing what was corrected).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

