Skip to content
Agentmart
Submit a tool

american-inkblot-illustrations

Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art…

Skill by MylesMCook

IndexedMIT
Write a review

Chalk Labs

Need help deploying american-inkblot-illustrations?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mylesmcook-american-inkblot-illustrations

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art, editorial explainer, workflow/methodology visual, concept metaphor, shot list, or sparse handwritten-label image prompt. Produces 16:9 clean white-background hand-drawn Inkblot-character illustrations with sparse red/orange/blue American English notes. Do NOT use for polished brand key visuals, PPT decks, complex architecture diagrams, children's cartoons, logos, memes, Chinese annotation workflows, or generic image prompts.

Use cases: documents, design, writing, marketing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/american-inkblot-illustrations

What's inside

Skill name
american-inkblot-illustrations
Description
Use when creating, planning, prompting, generating, or editing quirky US English article illustrations: blog, newsletter, essay, Notion, document body art, editorial explainer, workflow/methodology visual, concept metaphor, shot list, or sparse handwritten-label image prompt. Produces 16:9 clean white-background hand-drawn Inkblot-character illustrations with sparse red/orange/blue American English notes. Do NOT use for polished brand key visuals, PPT decks, complex architecture diagrams, children's cartoons, logos, memes, Chinese annotation workflows, or generic image prompts.
License
MIT
Instructions
64 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (15)

  • LICENSE.txt
  • NOTICE.md
  • SKILL.md
  • label-bank.md · assets/
  • evals.json · evals/
  • ai-workflow-article.md · evals/files/
  • community-trust-article.md · evals/files/
  • startup-metrics-article.md · evals/files/
  • triggers.json · evals/
  • composition-patterns.md · references/
  • inkblot-mascot.md · references/
  • prompt-template.md · references/
  • qa-checklist.md · references/
  • style-dna.md · references/
  • check_skill.py · scripts/

SKILL.md (first lines)

# American Inkblot Illustrations

Use this skill to plan, prompt, generate, or edit body illustrations for US English articles. The job is not “make a picture.” The job is to find one cognitive move in the article and turn it into a sparse, memorable, weird-but-clear 16:9 hand-drawn explainer.

Default visual character: **Inkblot**, a small solid-black deadpan worker with white dot eyes and thin legs. Inkblot must do the conceptual work in the drawing, not stand beside it as decoration.

## Route: load only what the task needs

| Situation | Load |
|---|---|
| Style fidelity matters, or any image prompt/generation/edit is requested | `references/style-dna.md` |
| Inkblot’s shape, role, action, or “too cute / too decorative” issue matters | `references/inkblot-mascot.md` |
| Creating a shot list, choosing a structure type, or inventing a metaphor | `references/composition-patterns.md` |
| Calling an image tool or writing a final image prompt | `references/prompt-template.md` |
| Reviewing generated images or planning edits/regenerations | `references/qa-checklist.md` |
| Need short US English label ideas | `assets/label-bank.md` |

Do not preload all references. Read the narrow file named above when the branch applies.

## Workflow

1. **Digest the source.** Read the user’s article, Markdown, Notion export, screenshot text, pasted draft, or concept. If the user gave a URL and the runtime can browse, fetch it; otherwise ask for the text only if there is no usable content.
2. **Pick cognitive anchors, not paragraphs.** Good anchors are decisions, bottlenecks, before/after contrasts, system loops, evidence chains, trust gaps, handoffs, tradeoffs, and stuck-to-running state changes. Skip generic intros and paragraphs that are already visually obvious.
3. **Decide the mode.**
   - Planning only: output a shot list.
   - Generate/create/make/draw: generate each image separately when an image tool exists; otherwise deliver final prompts.
   - Edit/fix/remove title/reduce text: write or run the narrow edit instruction, then QA.
4. **Create the shot list.** Default to 4-8 shots for a normal article, 1-3 for a short piece, and no more than 9 for a long piece. Each shot gets one structure type and one core idea.
5. **Generate or prompt one image at a time.** Read `references/prompt-template.md`. Never pack multiple final illustrations into one collage unless the user explicitly requested a comic strip.
6. **QA before delivery.** Read `references/qa-checklist.md` after generation/editing. Regenerate or edit if the image is too dense, too cute, too PPT-like, too text-heavy, too patriotic by default, or if Inkblot is decorative.
7. **Save when working in a workspace.** Put finished images under `assets/<article-slug>-illustrations/` as `01-topic-name.png`, `02-topic-name.png`, etc. Do not overwrite existing assets unless asked.

## Shot list format

Use a compact table:

| Placement | Theme | Core idea | Structure | Inkblot action | Elements | Labels |
|---|---|---|---|---|---|---|

Labels must be American English, usually 1-3 words each. Use 3-5 labels per image unless the user asks for no text.

## Generation defaults

Use these defaults unless the user overrides them:

- 16:9 horizontal article body illustration.
- Pure white background; no paper texture, beige, shadows, gradients, or noise.
- Black hand-drawn line art with slightly wobbly thin lines.
- Sparse red/orange/blue handwritten English notes.
- Main subject covers roughly 40%-60% of the canvas; keep at least 35% empty white space.
- One core action, structure, state, or metaphor per image.
- Inkblot is the active subject of the conceptual action.
- Weird, clever, clean, and editorial; not cute, not childish, not brand-polished.

## Gotchas

- **“American” means US English and everyday US editorial grounding, not flags/eagles/Uncle Sam.** Use civic or patriotic symbols only when the article is actually about those topics.
- **Inkblot is abstract, not racialized.** Do not call it “Little Black” in US-facing output; do not add human ethnicity, race-coded features, gender, or costumes.
- **Text in generated images is fragile.** Fewer labels beat more labels. If text fails, remove labels, regenerate, or keep labels outside the image.
- **This is not a PPT infographic skill.** Remove titles, grids, tidy corporate boxes, and dense arrows.
- **Do not copy examples from the source project.** Reuse the style DNA, not old object layouts or compositions.
- **If no image-generation tool exists, still do the useful work:** output shot lists and ready-to-run prompts.

From MylesMCook/mcook-skills, MIT.

More from MylesMCook/mcook-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 7, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MylesMCook

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get american-inkblot-illustrations running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying american-inkblot-illustrations?

CallGet help
Cite this page

american-inkblot-illustrations skill. Agent Mart. https://agentmart.dev/skills/mylesmcook-american-inkblot-illustrations (last updated 2026-10-24)