agentleFS
carlosbuelvas1carlosbuelvas1/openclaw-skills/visual-first-explainer/SKILL.md

visual-first-explainer

Skill0 starsChanged 6 months agoMITView on GitHub

Use diagrams first when explaining complex systems, workflows, architecture, strategy, or flows to Charlie.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 12 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    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
  1. Distinctive:

    Use this skill when Charlie asks for an explanation and the topic has moving parts that are easier to understand visually.

    line 10
  2. Distinctive:

    Do not use for tiny answers, greetings, confirmations, or simple factual replies where a diagram would slow Charlie down.

    line 20
  3. Distinctive:

    If no: answer normally in short text.

    line 25
  4. Distinctive:

    If yes: answer with a visual-first structure.

    line 26
  5. Distinctive:

    Start with the main point in one sentence.

    line 27
  6. Distinctive:

    Create a simple Excalidraw-style diagram using text blocks and arrows.

    line 28
  7. Distinctive:

    If Charlie asks for an actual Excalidraw file/image, generate or save a diagram artifact when tools allow it.

    line 31
  8. Distinctive:

    Do not force diagrams into simple answers.

    line 98
  9. Distinctive:

    Do not make diagrams huge or academic in Telegram.

    line 99
  10. Distinctive:

    Do not expose secrets, tokens, private IPs beyond what Charlie already uses for setup, or sensitive config.

    line 100
  11. Distinctive:

    Do not claim an actual Excalidraw file was created unless a file/image was really generated.

    line 101
  12. Distinctive:

    Do not hide uncertainty. If a system state is not verified, label it as assumption.

    line 102

≈ “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.

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

Visual First Explainer

When to Use

Use this skill when Charlie asks for an explanation and the topic has moving parts that are easier to understand visually.

Strong triggers:

  • "explain this"
  • "how does this work?"
  • "show me the flow"
  • "map this"
  • "diagram this"
  • Architecture, OpenClaw, Mac mini, iPhone, Tailscale, SSH, agents, automations, content funnels, business systems, trading workflows, recovery flows, or operating systems.

Do not use for tiny answers, greetings, confirmations, or simple factual replies where a diagram would slow Charlie down.

Process

  1. Decide if the explanation is complex enough to deserve a diagram.
    • If no: answer normally in short text.
    • If yes: answer with a visual-first structure.
  2. Start with the main point in one sentence.
  3. Create a simple Excalidraw-style diagram using text blocks and arrows.
  4. Explain the diagram in plain language.
  5. End with the next action, command, or decision Charlie needs.
  6. If Charlie asks for an actual Excalidraw file/image, generate or save a diagram artifact when tools allow it.

Output Format

For Telegram, keep it compact:

[one-line point]

Diagram:
[Node A] → [Node B] → [Node C]
              ↓
          [Backup / risk]

Meaning:
- [plain explanation]
- [why it matters]

Next:
[action]

For deeper architecture/spec work, use:

## Main idea
[one-line explanation]

## Diagram
[Excalidraw-style map using boxes/arrows]

## What each part does
- Component:
- Responsibility:
- Risk:

## Next move
[one concrete action]

Example

User: "How does the iPhone emergency control path work?"

Assistant:

Your iPhone is now the backup control panel for HQ.

Diagram:
[iPhone]
  ↓ Tailscale private network
[Mac mini SSH]
  ↓ terminal command
[OpenClaw Gateway]
  ↓
[Telegram / Elon answers again]

Emergency command:
openclaw gateway restart

Meaning:
If I stop answering but the Mac mini is still powered and online, you can enter from your phone and restart the gateway without exposing anything to the public internet.

What to Avoid

  • Do not force diagrams into simple answers.
  • Do not make diagrams huge or academic in Telegram.
  • Do not expose secrets, tokens, private IPs beyond what Charlie already uses for setup, or sensitive config.
  • Do not claim an actual Excalidraw file was created unless a file/image was really generated.
  • Do not hide uncertainty. If a system state is not verified, label it as assumption.

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.