vibepulse: Skill for Claude Code

.claude/skills/iterating-esp32-amoled-ui/SKILL.md

iterating-esp32-amoled-ui is a skill for Claude Code, Codex from niclasvestlund-YT/vibepulse. It costs 33 tokens per session (787 once invoked), scanned A, original, MIT.

A workflow for changing and reviewing the visual interface of a 480×480 Torget AMOLED device, including simulator previews and physical-device checks. It uses LVGL, a library for drawing interfaces on embedded devices.

In plain words
What is it for?
Use it to make AMOLED screen changes, create exact-size mockups, capture simulator images, and review live, cached, missing-data, and wide-number states on the device.
Why use it?
It keeps visual changes tied to the device’s real screen size and hardware limits. It also separates previewing, installing, and accepting a change so unapproved designs are not treated as finished.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions Codex.

This is niclasvestlund-YT/vibepulse's own configuration. It tells Claude Code and Codex how to work on vibepulse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibepulse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to niclasvestlund-YT/vibepulse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/niclasvestlund-YT/vibepulse/main/.claude/skills/iterating-esp32-amoled-ui/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/niclasvestlund-YT/vibepulse

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for iterating-esp32-amoled-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui/github.svg)](https://agentmods.dev/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui)
Your own site
<a href="https://agentmods.dev/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui"><img src="https://agentmods.dev/badge/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for iterating-esp32-amoled-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui"><img src="https://agentmods.dev/badge/skills/niclasvestlund-yt/vibepulse/iterating-esp32-amoled-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 57
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00787
Opus 5 $0.00016 $0.00394
Sonnet 5 $0.00007 $0.00157
Haiku 4.5 $0.00003 $0.00079

Measured 12d ago against content hash 76847ad0492c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

iterating-esp32-amoled-ui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/iterating-esp32-amoled-ui/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterating Torget AMOLED UI

Explore at panel size; move an approved batch into shared LVGL. Preview, install, acceptance are separate gates.

Required sequence

  1. 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. Work at 1:1 480 x 480; show materially different states when coherent.
  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 with the same active fixture so provenance alone changes. 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; review the exact 480 x 480 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 deliberate frames when bandwidth is limited.

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 73 lines · 33 tokens per session scan A 76847ad0492c

Subscribe to this mod's changes

iterating-esp32-amoled-ui is a skill published in the GitHub repository niclasvestlund-YT/vibepulse (193 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 787 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cad-viewer

Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing .step, .stp, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, URDF, SRDF, or SDF generation skills.

earthtojake/text-to-cad · 79 tokens

solidworks-vibecad

A planning guide for turning natural-language mechanical design requests into structured, parameterized SolidWorks plans that can be reviewed before execution.

wzyn20051216/solidworks-automation-skill · 96 tokens

add-interfaces

Enrich an existing PartCAD part with connection interfaces and ports (mating metadata) so it can be mated to other parts automatically. Use for /pc:add-interfaces or when the user asks to add interfaces, ports, connectors, or mating information to a part, or to make parts snap/connect/assemble together.

partcad/partcad · 69 tokens

gen-assembly

Generate a PartCAD assembly (an ASSY that composes parts with placement and/or mates) from a description, generating or reusing the component parts and validating the result with the PartCAD CLI. Use for /pc:gen-assembly or when the user asks to generate or create an assembly, mechanism, or multi-part product.

partcad/partcad · 71 tokens

render

Render a PartCAD object or a CAD file to a 2D image - PNG, JPEG, SVG or DXF - from one or many viewing angles (front, back, left, right, top, bottom, iso, or an arbitrary direction), with pc render for an object a package declares or pc adhoc render for a file that belongs to no package. Use for /pc:render or when the…

partcad/partcad · 168 tokens

gen-part

Generate a PartCAD part from a natural-language description (and optional reference images/requirements) by authoring a CAD script and validating it with the PartCAD CLI. Use for /pc:gen-part or when the user asks to generate, create, or model a single mechanical part.

partcad/partcad · 60 tokens