Wabi-Sabi — imperfection Agent Skill

Design intentional imperfection that reads as warmth — subtle asymmetry, hand-drawn elements, organic textures, intentional irregularities.

Context cost
3.8k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 15.1 kBtext throughout, nothing executable
Licence
Apache-2.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Design intentional imperfection that reads as warmth — subtle asymmetry, hand-drawn elements, organic textures, intentional irregularities. Use when adding human warmth to a digital design, distinguishing from competitors with uniform design systems, designing for personal or creative contexts. The skill is making imperfection look intentional and refined rather than sloppy or broken; the line between "designed warmth" and "looks unfinished" is narrow.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

design
Filed under

Design & Media

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md8.7 kB · preview
--- name: wabi-sabi-imperfection ---
6# Wabi-Sabi — imperfection
7
8Designing intentional imperfection is the half of wabi-sabi that adds warmth through irregularity, asymmetry, and visible craft. Done well, the imperfection reads as deliberate and refined — the work of someone who cared enough to break the grid in a chosen way. Done poorly, it reads as broken or unfinished.
9
10The challenge is calibration. Too little imperfection and the design reverts to standard digital uniformity; too much and it feels chaotic. The most successful applications use small, deliberate imperfections in otherwise-disciplined designs, so the imperfection reads as character rather than as failure.
11
12## What "intentional imperfection" looks like
13
14**Subtle asymmetry.** A layout that's mostly grid-aligned but lets one element sit slightly off. A button with off-center text. A logo positioned slightly above center. The asymmetry is small enough to feel intentional, large enough to be noticed.
15
16**Hand-drawn elements.** Illustrations or icons that show the artist's hand — visible brushstrokes, varied line weights, irregularities in the form. These contrast with vector-precise elements and add visual texture.
17
18**Organic textures.** Backgrounds that suggest paper, watercolor, fabric, or other natural materials — rather than flat colors or smooth gradients. The texture reads as material rather than as digital surface.
19
20**Variable typography.** A typeface that has subtle character variations (humanist serifs are often like this), or hand-set text with intentional kerning irregularities. Contrasts with mathematically-uniform display type.
21
22**Variable spacing and rhythm.** Layouts where vertical spacing isn't perfectly uniform — some sections breathe more than others, creating a more editorial feel.
23
24**Imperfect alignment used deliberately.** A pull-quote that breaks the column. A photo that bleeds past its frame. A subhead that hangs into the margin.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,217 words
Files2
LicenceApache-2.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈130
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
3,645
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
1.9%
of a 200k window
Ten skills this size would take about 19% of the window before you open a file.
050k100k150k200k context window

3.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 15.1 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md8.7 kB
  • references/imperfection-techniques.md6.4 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing. The Apache-2.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Wabi-Sabi — imperfection · 3.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/wabi-sabi-imperfection/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/wabi-sabi-imperfection" ] && { [ ! -e .claude/skills/wabi-sabi-imperfection ] || { mv .claude/skills/wabi-sabi-imperfection "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/wabi-sabi-imperfection" .claude/skills/ && echo "Installed .claude/skills/wabi-sabi-imperfection"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add hashgraph-online/wabi-sabi-imperfection

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/wabi-sabi-imperfection/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/wabi-sabi-imperfection/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/wabi-sabi-imperfection" ] && { [ ! -e ~/.claude/skills/wabi-sabi-imperfection ] || { mv ~/.claude/skills/wabi-sabi-imperfection "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/wabi-sabi-imperfection" ~/.claude/skills/ && echo "Installed ~/.claude/skills/wabi-sabi-imperfection" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/wabi-sabi-imperfection/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencehashgraph-online/wabi-sabi-imperfection

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers1
Claim this skill