Skip to content
SkillModel-led84 tokens in use

big-pics-little-words

Asks the agent to explain whatever you are discussing as an HTML page with big pictures and few words, without leaving out the key details.

4,275 stars on the repository MIT Licenseplannotator/effective-html · skills/big-pics-little-words
npx skills add plannotator/effective-html --skill big-pics-little-words
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing big-pics-little-words costs

27tokens idle
84tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Needs attention
  • Frontmatter8/15
  • Structure0/25
  • Examples0/15
  • Output5/15
  • Size13/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity60
  • Maintenance24
  • Community48
  • Maturity24
  • Momentum40

big-pics-little-words is a short prompt-style skill for turning the current conversation into a visual explainer. The agent builds an HTML page that shows the subject with large visuals and terse, jargon-free text, written as if the viewer is new to the topic.

It leaves the design to the agent’s taste, asks for real pictures or icons only where they help, and is set to run only when you invoke it by name.

What You Get

  • An HTML page that explains the current subject visually
  • Large visuals with short captions that keep the key details
  • Real-world pictures or icons used selectively where they clarify
  • Everyday-language prose with jargon removed

Common Use Cases

  • Understanding a complicated architecture the agent just described in text
  • Explaining a bug or a design decision to a teammate who was not in the conversation
  • Turning a long planning discussion into a page you can skim in a minute
  • Giving a newcomer an orientation to a codebase or a topic

What Makes It Unique

It is deliberately minimal, with no template, house style or checklist to follow. The skill sets one preference, show more and say less, and leaves layout, imagery and visual direction to the agent. It is a sibling of the one-pager skill, which aims the same idea at sharing with teammates.

Under The Hood

The skill is a single short instruction file with no scripts, and its frontmatter keeps the model from invoking it automatically. The agent writes an HTML file to your workspace. The instructions ask for real-world pictures where they help, so the agent may fetch or reference images from the web, and you should check what ends up on the page.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers