Agent skill

Iterating Esp32 Amoled UI

by niclasvestlund-YT in niclasvestlund-YT/vibepulse

A skill your agent uses when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review.

MITAuto-check passedDevelopment

Install Iterating Esp32 Amoled UI

skills CLI
$ npx skills add niclasvestlund-YT/vibepulse --skill iterating-esp32-amoled-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install niclasvestlund-YT/vibepulse iterating-esp32-amoled-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/niclasvestlund-YT/vibepulse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/iterating-esp32-amoled-ui .claude/skills/iterating-esp32-amoled-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
iterating-esp32-amoled-ui
GitHub stars
208
Token cost
~927 tokens
SKILL.md length
441 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review.

  • Works in 7 steps: Select board registries using… → Check git status and relevant diff.… → Start python3… → …
  • Making any Torget AMOLED app visual change
  • SKILL.md covers Required sequence, interaction performance, Invariants and Stop signals
  • Calls python3 and git

What it does

Iterating Esp32 Amoled UI is an agent skill from niclasvestlund-YT/vibepulse. Use when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Embedded systems and File uploads and storage. It works with ESP32. The repository describes itself as: ESP32-S3 AMOLED for Claude Code & Codex usage, live agent activity, and answerable NEEDS YOU alerts. Local-first macOS/Windows host; optional encrypted relays. The licence is MIT.

When your agent uses it

  • Making any Torget AMOLED app visual change
  • Exact-size mockup
  • Simulator capture
  • Physical review

Example prompts

  • “/iterating-esp32-amoled-ui”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Select board registries using docs/adding-a-display.md. For 2.16 read spec/hardware.md, spec/hardware-capabilities.yaml,
  2. Check git status and relevant diff. Scope concurrent Claude/Codex edits.
  3. Start python3 tools/vibepulse_studio/server.py. Studio stays 1:1 480 x 480;
  4. The shared LVGL raster is the visual authority. Test widest realistic copy, a
  5. Save accepted tokens. Run
  6. Implement one static shared LVGL batch and run ./test/run.sh.
  7. Build once after static acceptance. Flash only with explicit user authorization;

What it can do on your machine

Read from SKILL.md and the folder at commit 21b905d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Iterating Esp32 Amoled UI loads about 927 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 441 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~927

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from niclasvestlund-YT/vibepulse at commit 21b905d, republished under its MIT licence (© niclasvestlund-YT). 441 words, ~927 tokens.

Download SKILL.mdSave it as .claude/skills/iterating-esp32-amoled-ui/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
iterating-esp32-amoled-ui
description
Use when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review.

Iterating Torget AMOLED UI

Explore at panel size; implement in shared LVGL. Preview, install, acceptance are separate gates.

Required sequence

  1. Select board registries using docs/adding-a-display.md. For 2.16 read spec/hardware.md, spec/hardware-capabilities.yaml, spec/hardware-sources.yaml, spec/device-units.yaml, spec/hardware-opportunities.md, spec/ui-spec.md, design/vibepulse/studio-design.json, and the latest physical review under docs/superpowers/reviews/. If no physical review exists, do not claim approval.
  2. Check git status and relevant diff. Scope concurrent Claude/Codex edits.
  3. Start python3 tools/vibepulse_studio/server.py. Studio stays 1:1 480 x 480; show materially different states at native board size.
  4. The shared LVGL raster is the visual authority. Test widest realistic copy, a missing-data state, broad numbers, and source provenance across live, cached/stale, and no-data. Compare live/stale using the same active fixture. Keep one dominant metric; round secondary values; encode discovered spacing as validator tests.
  5. Save accepted tokens. Run python3 tools/vibepulse_studio/design.py --check and tools/preview-ui.sh vibepulse [board]; review native captures.
  6. Implement one static shared LVGL batch and run ./test/run.sh. Use two-stage review: specification fidelity, then code/test quality.
  7. Build once after static acceptance. Flash only with explicit user authorization; inspect static physical AMOLED before animation.

interaction performance

Static approval does not imply motion approval. Measure cross-app lag at the shared display pipeline first.

  1. Reproduce the gesture on the physical panel after its static gate.
  2. Log gesture begin/end, first redraw, flush count and time, free internal heap, largest internal block, and transport errors.
  3. Repeat 20 times under network/TLS stress.
  4. Change one variable at a time and compare with baseline.

never increase display-buffer height without a measured memory budget and network/TLS stress run. Prefer fewer frames when bandwidth is limited.

Show full SKILL.md (176 more words)Show less

Invariants

  • Lock provider accents to Claude #D97757 and Codex #6F78FF; never fabricate data.
  • Generate image assets at native final sizes; compose before alpha-aware scaling. Test transparent corners, palette/pixels, and compare files byte-for-byte with checked-in firmware assets. Do not scale or recolor at runtime.
  • Do not infer visual correctness from a green test. Inspect exact rasters at 1:1; assertions must independently prove visible claims, not compare two outputs from the same potentially broken renderer.
  • Never add persistent UI layers or canvas buffers without approval and a measured memory budget.
  • tiny, time pressure, a connected cable, prior approval, or Studio approval never authorizes skipping preview, review, or the physical flash gate.
  • Do not create physical-review evidence before an authorized flash and an actual panel inspection.

Stop signals

SignalRequired response
Concurrent editsRecheck scope and diff.
Preview differs from LVGLResolve before building.
Flash requested implicitlyStop and ask for explicit authorization.
Motion requested earlyComplete the static physical AMOLED review first.
Motion feels slow across appsInstrument the shared pipeline before changing UI code.

Round boards: lessons.

© niclasvestlund-YT, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/iterating-esp32-amoled-ui of niclasvestlund-YT/vibepulse.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 21b905d

Compare with similar skills

Iterating Esp32 Amoled UI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Iterating Esp32 Amoled UI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Iterating Esp32 Amoled UI this skillniclasvestlund-YT/vibepulse208—~927Automated safety check: PassMIT
Flash Esp32s3RomanLut/hx_espnow_rc129—~794Automated safety check: PassMIT
Guition Jc3636k718cMichalZaniewicz/esphome-guition-jc3636k718c-va167—~3kAutomated safety check: PassMIT
Implement Next Taskrvdbreemen/OTGW-firmware207—~2.1kAutomated safety check: PassGPL-3.0
Flash Devicesjtenniswood/esphome-media-player234—~1.1kAutomated safety check: PassCustom licence
Flash Displaysjtenniswood/espcontrol1.1k—~2.8kAutomated safety check: PassCustom licence

Similar skills

  • Flash Esp32s3

    RomanLut/hx_espnow_rc

    Build, flash, recover, and verify the ESP32-S3 Super Mini MAVLink/ESP-NOW USB receiver in examples/rxesp32s3mavlinkrcusb.

    129 GitHub stars~794 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Guition Jc3636k718c

    MichalZaniewicz/esphome-guition-jc3636k718c-va

    Reference for building/editing ESPHome configs on the Guition JC3636K718C round knob display (ESP32-S3, 1.8" 360x360 ST77916, CST816 touch, rotary knob, PCM5100A DAC, PDM mic, WS2812 LED ring).

    167 GitHub stars~3k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Implement Next Task

    rvdbreemen/OTGW-firmware

    Drive the autonomous 2.0.0 ESP32-S3-only async + FreeRTOS migration (epic TASK-865).

    207 GitHub stars~2.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Flash Devices

    jtenniswood/esphome-media-player

    Flash ESPHome firmware to physical EspControl devices. An agent skill from jtenniswood/esphome-media-player.

    234 GitHub stars~1.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Flash Displays

    jtenniswood/espcontrol

    Flash EspControl display firmware from this repository using ESPHome.

    1.1k GitHub stars~2.8k tokensUpdated today
    Backend & APIsAuto-check passed
  • Brings a RuView CSI sensing node online by building ESP32-S3 or ESP32-C6 firmware, flashing the board, provisioning WiFi and checking the serial output.

    97k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check: notes

More from niclasvestlund-YT/vibepulse

  • Vibepulse

    niclasvestlund-YT/vibepulse

    A skill your agent uses for VibePulse panel questions, permission behavior, setup, status, or doctor diagnostics for the optional local Codex bridge.

    208 GitHub stars~1.6k tokensUpdated 10 days ago
    Auto-check passed

Works with

Categories

Questions about Iterating Esp32 Amoled UI

What does Iterating Esp32 Amoled UI do?

A skill your agent uses when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review. Iterating Esp32 Amoled UI is an agent skill from niclasvestlund-YT/vibepulse. Use when making any Torget AMOLED app visual change, exact-size mockup, simulator capture, or physical review.

When should I use Iterating Esp32 Amoled UI?

Iterating Esp32 Amoled UI fits situations like: making any Torget AMOLED app visual change; exact-size mockup; simulator capture; physical review.

How do I install Iterating Esp32 Amoled UI in Claude Code?

Run `npx skills add niclasvestlund-YT/vibepulse --skill iterating-esp32-amoled-ui -a claude-code`. Or copy the skill folder (.claude/skills/iterating-esp32-amoled-ui in niclasvestlund-YT/vibepulse) into .claude/skills/iterating-esp32-amoled-ui in your project. Claude Code loads it when a task matches its description.

How do I install Iterating Esp32 Amoled UI in Codex?

Run `npx skills add niclasvestlund-YT/vibepulse --skill iterating-esp32-amoled-ui -a codex`. Or copy the skill folder (.claude/skills/iterating-esp32-amoled-ui in niclasvestlund-YT/vibepulse) into .agents/skills/iterating-esp32-amoled-ui in your project. Codex loads it when a task matches its description.

Can I use Iterating Esp32 Amoled UI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add niclasvestlund-YT/vibepulse --skill iterating-esp32-amoled-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iterating-esp32-amoled-ui, .gemini/skills/iterating-esp32-amoled-ui, .github/skills/iterating-esp32-amoled-ui and .opencode/skills/iterating-esp32-amoled-ui in your project.

What does Iterating Esp32 Amoled UI need to run?

Going by SKILL.md and its folder, Iterating Esp32 Amoled UI needs the command-line tools its instructions call (python3 and git). Our summary lists: Python 3.

Does Iterating Esp32 Amoled UI access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Iterating Esp32 Amoled UI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Iterating Esp32 Amoled UI use?

Iterating Esp32 Amoled UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Iterating Esp32 Amoled UI use?

About 927 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Iterating Esp32 Amoled UI?

Skills that share tags, products or a category with Iterating Esp32 Amoled UI: Flash Esp32s3 (RomanLut/hx_espnow_rc, 129 stars), Guition Jc3636k718c (MichalZaniewicz/esphome-guition-jc3636k718c-va, 167 stars), Implement Next Task (rvdbreemen/OTGW-firmware, 207 stars) and Flash Devices (jtenniswood/esphome-media-player, 234 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Iterating Esp32 Amoled UI?

niclasvestlund-YT (a GitHub user) maintains it in niclasvestlund-YT/vibepulse, which has 208 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 30, 2026.

Source: niclasvestlund-YT/vibepulse on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.