MoltenView

v1.0.0

Push persistent visual views (charts, metrics, lists, progress bars) to MoltenView Mac app. Use when agent output benefits from visual display that persists...

0· 114·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for goldcote/moltenview.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "MoltenView" (goldcote/moltenview) from ClawHub.
Skill page: https://clawhub.ai/goldcote/moltenview
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install moltenview

ClawHub CLI

Package manager switcher

npx clawhub@latest install moltenview
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (push persistent visual views to MoltenView) match the runtime instructions: they show how to send JSON to a MoltenView Unix domain socket. The skill does not request unrelated binaries, credentials, or config paths.
Instruction Scope
Instructions are narrowly scoped to constructing JSON payloads and sending them to a MoltenView socket (nc -U). They reference a socket path under the app's container and an optional MOLTENVIEW_SOCKET env var. They do allow sending arbitrary JSON content to the app, so the agent could display any data you give it — ensure you trust the agent and the data it will send.
Install Mechanism
No install spec or code files are present; this is instruction-only, so nothing is written to disk by the skill itself.
Credentials
The skill requires no secrets or external credentials. It suggests an environment variable (MOLTENVIEW_SOCKET) for convenience; this is proportional to the local IPC-based integration.
Persistence & Privilege
always is false (good). The skill can be invoked autonomously by the agent (disable-model-invocation is false) — which is platform default — meaning an agent could push persistent views without further user prompts. That is expected for this kind of integration but is a behavior you should consider before enabling autonomous agents.
Assessment
This skill simply documents how to send JSON to a MoltenView Unix socket to create persistent UI elements in the MoltenView Mac app. It doesn't ask for secrets or install code. Before installing, confirm you (or your agent) actually use MoltenView on macOS and trust the agent to create UI: the agent can push arbitrary content (text, links, images, charts) which will persist in the app and could be used to display sensitive data or misleading UI. If you allow autonomous agent invocation, restrict what data the agent may send and verify the socket path in MoltenView settings. If you don't use MoltenView, there's no benefit to installing this skill.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

🔥 Clawdis
chartsvk974v0egzdk8901b5yyw2ft2eh83th8wdashboardvk974v0egzdk8901b5yyw2ft2eh83th8wlatestvk974v0egzdk8901b5yyw2ft2eh83th8wopenclawvk974v0egzdk8901b5yyw2ft2eh83th8wvisualvk974v0egzdk8901b5yyw2ft2eh83th8w
114downloads
0stars
1versions
Updated 4w ago
v1.0.0
MIT-0

MoltenView Skill

Push structured data to MoltenView — a persistent visual canvas for AI agents.

When to Use

USE this skill when:

  • Displaying charts, metrics, or dashboards
  • Data that should persist (not scroll away)
  • Live-updating information
  • Visual summaries the user will reference

DON'T use when:

  • Simple text responses suffice
  • One-time data that doesn't need persistence

Socket Path

export MOLTENVIEW_SOCKET="/Users/$USER/Library/Containers/com.goldcote.MoltenView/Data/.moltenview/view.sock"

Push a View

echo '{"action":"push","data":{"title":"Dashboard","source":"openclaw","sections":[{"id":"s1","header":"Metrics","items":[{"id":"i1","title":"Sales","subtitle":"$12,450"}]}]}}' | nc -U "$MOLTENVIEW_SOCKET"

Required Fields

  • data.source — Agent name (string)
  • sections[].id — Unique section ID
  • sections[].items[].id — Unique item ID
  • sections[].items[].title — Item title

Supported Item Types

Set type on each item (omit or "text" for default):

TypeKey Fields
texttitle, subtitle, detail, badge
chartchart.chartType (bar/line/pie/area), chart.dataPoints [{label, value, color}]
gaugegauge.value, gauge.min, gauge.max, gauge.label, gauge.color
progressprogress (0.0-1.0), subtitle
metrictitle (label), subtitle (big value), detail (change), metricColor
linkurl (https/mailto), title, subtitle, icon
imageimageBase64, icon (SF Symbol), title

Example: Push a Chart

echo '{"action":"push","data":{"title":"Sales","source":"openclaw","sections":[{"id":"s1","header":"Revenue","items":[{"id":"c1","type":"chart","title":"Monthly","chart":{"chartType":"bar","dataPoints":[{"label":"Jan","value":100},{"label":"Feb","value":150},{"label":"Mar","value":200}]}}]}]}}' | nc -U "$MOLTENVIEW_SOCKET"

Example: Push Metrics

echo '{"action":"push","data":{"title":"KPIs","source":"openclaw","sections":[{"id":"s1","header":"Today","items":[{"id":"m1","type":"metric","title":"Revenue","subtitle":"$12,450","detail":"+12%","metricColor":"#00FF00"},{"id":"m2","type":"progress","title":"Goal","progress":0.73}]}]}}' | nc -U "$MOLTENVIEW_SOCKET"

Actions

ActionPurposeData Required
pushDisplay new viewYes
updateUpdate existing viewYes
clearClear current viewNo
statusCheck connectionNo

Status Check

echo '{"action":"status"}' | nc -U "$MOLTENVIEW_SOCKET"
# Returns: {"status":"ok"}

Notes

Comments

Loading comments...