agentleFS
PradnyeshpPradnyeshp/Claude-Skills/.claude/skills/diagram/SKILL.md

diagram

Skill2 starsChanged 4 months agoMITView on GitHub

Generate a Mermaid diagram from the codebase — architecture/module graph, entity-relationship, sequence, or flowchart — read from the actual code. Use when the user says "draw a diagram", "diagram the architecture", "generate an ER diagram", "make a sequence diagram", "visualize this flow", or "show how these pieces connect".

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ios-sync, benchmark-models and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 4 projects that use this

  • ShreyRaviSkill

    benchmark-models

    Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

    Also in 5 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 5 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 3 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 4 projects that use this

  • +2 more from ShreyRavi
  • +1 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 44 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Build the Mermaid source: Use clear node labels taken from real names (modules, classes, tables, endpoints).

    line 29
  2. Distinctive:

    Keep the Mermaid syntax valid and minimal.

    line 37
  3. Distinctive:

    Don't write files unless asked — output the diagram inline first, then offer to save it.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 44 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project layout

!ls 2>/dev/null

!git ls-files 2>/dev/null | grep -vE '\.(png|jpg|svg|lock|min\.)' | head -40 || find . -type f -not -path '*/node_modules/*' -not -path '*/.git/*' | head -40

Instructions

Generate a Mermaid diagram for what the user described in $ARGUMENTS. If the type or subject is unclear, pick the most useful diagram for the request and say why; ask only if you genuinely can't tell what to draw.

Choose the diagram type

  • Architecture / module graph (graph TD/flowchart) — how top-level components, services, or modules depend on each other. Default when the user says "architecture" or "how it connects".
  • Entity-relationship (erDiagram) — data models/tables and their relationships, with key fields and cardinality. Use for "ER diagram", "schema", "models".
  • Sequence (sequenceDiagram) — the ordered interaction between participants for a specific flow (request → handler → service → db). Use for "sequence" or "the X flow".
  • Flowchart / state — branching logic or a state machine within a function or feature.

Method

  1. Read the real code for the chosen subject — module imports/dependencies, schema/model definitions, or the call chain of the named flow. Trace actual relationships; don't draw an idealized architecture.
  2. Build the Mermaid source. Use clear node labels taken from real names (modules, classes, tables, endpoints). For ER diagrams, include primary/foreign keys and cardinality (||--o{). For sequence diagrams, order the calls as they actually execute and include returns where meaningful.
  3. Keep it legible. Group or collapse detail when a full graph would be unreadable — show the meaningful structure, not every file. Note what you abstracted.
  4. Output a fenced ```mermaid block so it renders. If the user wants it persisted, offer to write it into the README or a docs/ file rather than assuming.

Rules

  1. Diagram what the code actually does — every node and edge must trace to a real module, model, or call. Don't invent components or relationships.
  2. Mark anything inferred or uncertain (e.g. a dynamically-resolved dependency) rather than drawing it as fact.
  3. Keep the Mermaid syntax valid and minimal; prefer a readable subset over an exhaustive but unreadable graph.
  4. Don't write files unless asked — output the diagram inline first, then offer to save it.
  5. Briefly explain the diagram after it: what the main nodes are and how to read the key relationships.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.