Visual Token Editorial Agent Skill

Create or revise deterministic editorial visual-poetry posters in which exact crops from one source photograph become inline semantic…

Context cost
6.3k tokensestimated from the bundle, loaded when it triggers
Bundle
8 files · 51.4 kB2 scripts among them — read before you run
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Create or revise deterministic editorial visual-poetry posters in which exact crops from one source photograph become inline semantic tokens inside a poetic sentence, while the lower photograph remains pixel-identical outside the corresponding solid masks. Use for 图像词元、语义图像拼贴、图片嵌入文字、visual token editorial, editorial visual poetry, or the established photo-plus-inline-crops style.

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.md5.7 kB · preview
--- name: visual-token-editorial ---
6# Visual Token Editorial
7
8Create one static portrait composition from one source photograph. Treat it as reproducible editorial typography, not generative image editing.
9
10## Workflow
11
121. Before generating, resolve three choices: whether the source should be compositionally cropped, whether copy is user-provided or auto-generated, and the copy language. Do not repeat choices the user already supplied. If any remain unresolved, ask them together in one concise message and wait.
132. Read [visual-system.md](references/visual-system.md) and inspect the source. When a tall or awkward source would produce an excessively tall poster or weak focal structure, recommend a specific landscape crop and explain what it preserves. Crop only after the user agrees.
143. If cropping is approved, preserve the original and create one deterministic cropped working image without generative fill, retouching, or rescaling distortion. Choose the landscape ratio from the image rather than forcing one universal ratio. Generate or place the final copy only after this working image is fixed.
154. Determine the copy mode. If the user supplies copy, preserve its wording, punctuation, and language; only add line breaks and inline token positions. If no copy is supplied, automatically write restrained poetic copy in English, or in another language selected by the user.
165. Select 4–7 source details that correspond to concrete words or images in the copy. Preview every crop alone at its final display size and keep it only if the named object or attribute remains immediately recognizable. Let semantic fit, image density, and the harmony of the resulting holes determine the exact count.
176. Keep the copy to no more than four lines. Do not treat every comma as an automatic line break; group related clauses into visually balanced lines. Start token display height near 1.6 times the font size, then use compact leading near 2.15 times the font size with enough clearance for the tallest token.
187. Create composition.yaml from [composition-schema.md](references/composition-schema.md). It uses JSON-compatible YAML and needs no PyYAML.
198. Run scripts/validate_composition.py composition.yaml; fix errors and consciously review crop-size or loose-leading warnings.
209. Run scripts/render_composition.py composition.yaml --output final.png --qa qa_report.md.
2110. Inspect the result. If a mask harms the lower image, revise the bbox; never repaint the missing region.
2211. Deliver final.png, composition.yaml, and qa_report.md.
23
24## Invariants
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md843 words
Files8
Licencenot declared
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.

≈110
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,190
on trigger
The instruction body and 7 supporting files, read only when the skill fires.
3.1%
of a 200k window
Ten skills this size would take about 32% of the window before you open a file.
050k100k150k200k context window

6.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

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

8 files, 51.4 kB on disk. Mostly text — the instructions the model reads — with 2 scripts in it that your client would run only if the instructions tell it to. 3 files of its source are not in the download — listed after these, with why.

  • SKILL.md5.7 kB
  • README.md5.9 kB
  • README.zh-CN.md5.6 kB
  • agents/openai.yaml0.2 kB
  • references/composition-schema.md2.5 kB
  • references/visual-system.md5.3 kB
  • scripts/render_composition.py11.6 kB
  • scripts/validate_composition.py14.6 kB

Not in the download

Not carried is a type a skill download does not hold. Take them from its source.

  • .gitignorenot carried
  • examples/late-light-open-city.pngnot carried
  • examples/signals-at-blue-hour.pngnot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 2 scripts beside the text, so the download is 8 files — not the whole of its source: 3 files are left out. They are listed under the files, with why.

Install

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

# Visual Token Editorial · 6.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/visual-token-editorial/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/visual-token-editorial" ] && { [ ! -e .claude/skills/visual-token-editorial ] || { mv .claude/skills/visual-token-editorial "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/visual-token-editorial" .claude/skills/ && echo "Installed .claude/skills/visual-token-editorial"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add sanendy/visual-token-editorial

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/visual-token-editorial/ 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/visual-token-editorial/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/visual-token-editorial" ] && { [ ! -e ~/.claude/skills/visual-token-editorial ] || { mv ~/.claude/skills/visual-token-editorial "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/visual-token-editorial" ~/.claude/skills/ && echo "Installed ~/.claude/skills/visual-token-editorial" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/visual-token-editorial/ 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. Not in this download: 3 files of its source (the full list, and why). Take them from its source.

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
Referencesanendy/visual-token-editorial

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.

Who wrote it

SA
Sanendy

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill