Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Send Messages Eink Display

ASecurity

This skill sends content to a TRMNL e-ink display device using the webhook API.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgobashapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill send-messages-eink-display --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Send Messages Eink Display?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Send Messages Eink Display
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-send-messages-eink-display/badge)](https://www.skillsdirectory.com/skills/rondoflow-send-messages-eink-display)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: send-messages-eink-display
description: "This skill sends content to a TRMNL e-ink display device using the webhook API."
category: "Content & Writing"
author: community
version: "1.0.1"
icon: pencil
---

# TRMNL Display Skill

This skill sends content to a TRMNL e-ink display device using the webhook API.

## Webhook Configuration

- **Endpoint:** `https://trmnl.com/api/custom_plugins/0d9e7125-789d-46a6-9a51-070ac95364d8`
- **Method:** POST
- **Content-Type:** application/json

## How to Send a Message

Use curl to POST a JSON payload with `merge_variables`:

```bash
curl "https://trmnl.com/api/custom_plugins/0d9e7125-789d-46a6-9a51-070ac95364d8" \
  -H "Content-Type: application/json" \
  -d '{"merge_variables": {"title": "Your Title Here", "text": "Your message content here"}}' \
  -X POST
```

## Available Merge Variables

The TRMNL device is configured with a template that supports these variables:

| Variable | Description |
|----------|-------------|
| `title` | The main heading displayed prominently |
| `text` | The body content below the title (supports Markdown) |
| `image` | Fully qualified URL to an image (displayed on the right side) |

## Markdown Support

The `text` field supports Markdown formatting for richer content:

- **Bold:** `**text**`
- **Italic:** `*text*`
- **Lists:** Use `- item` or `1. item`
- **Line breaks:** Use `\n` in the JSON string
- **Headers:** `## Heading` (use sparingly, title is already prominent)

## Usage Examples

**Simple notification:**
```json
{"merge_variables": {"title": "Reminder", "text": "Stand up and stretch!"}}
```

**Status update with formatting:**
```json
{"merge_variables": {"title": "Build Status", "text": "**All tests passing**\n\nReady to deploy."}}
```

**List format:**
```json
{"merge_variables": {"title": "Today's Tasks", "text": "- Review PR #42\n- Update docs\n- Team standup at 10am"}}
```

**Weather-style info:**
```json
{"merge_variables": {"title": "San Francisco", "text": "**Sunny, 72°F**\n\nPerfect day for a walk"}}
```

**With image:**
```json
{"merge_variables": {"title": "Album of the Day", "text": "**Kind of Blue**\nMiles Davis", "image": "https://example.com/album-cover.jpg"}}

## Instructions for Claude

When the user asks to send something to their TRMNL device:

1. Parse the user's request to extract a title and message
2. If only a message is provided, generate an appropriate short title
3. Keep titles concise (under 30 characters recommended)
4. Keep text brief - e-ink displays work best with short, readable content
5. Use Markdown formatting to enhance readability (bold for emphasis, lists for multiple items)
6. If relevant, include an image URL (must be a fully qualified public URL)
7. Send the webhook using the curl command above
8. Confirm to the user what was sent

If the user provides arguments like `/trmnl Meeting in 5 minutes`, interpret the first few words as a potential title and the rest as the message, or use your judgment to create an appropriate title/text split.

## Response Handling

A successful response looks like:
```json
{"message":null,"merge_variables":{"title":"...","text":"..."}}
```

If you see an error message in the response, inform the user of the issue.

## Notes

- The device refreshes periodically, so content may not appear instantly
- E-ink displays are monochrome - no color support
- Keep content concise for best readability on the small screen
- Images must be fully qualified public URLs (e.g., `https://example.com/image.png`)
- Images are displayed on the right side in a two-column layout

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →