Skip to content
SkillModel-led1,195 tokens in use

ask-emil

A router over the skills in the repository: describe your situation and it recommends one skill or a short sequence from idea to shipped.

58,388 stars on the repository MIT Licenseemilkowalski/skills · skills/ask-emil
npx skills@latest add emilkowalski/skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ask-emil costs

22tokens idle
1,195tokens 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 →
Good
  • Frontmatter8/15
  • Structure19/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources10/15

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 →
Good
  • Development activity80
  • Maintenance40
  • Community52
  • Maturity28
  • Momentum40

Ask Emil reads the skill you are about to use before recommending it, then points to one skill or one short sequence for the situation you describe. Its guide groups the repository into a main flow from idea to ship, upkeep skills for an existing codebase, references that sit underneath, standalone skills and a list of common situations. It is set to run only when you invoke it.

What You Get

  • One recommended skill or short sequence with the reason
  • A map of the main flow: prototype, build, break, review and learn
  • An upkeep list for auditing, finding opportunities and removing motion
  • Common situations matched to skills

Common Use Cases

  • Choosing between animate, choreograph and gestures for a new piece of UI
  • Deciding what to run before shipping a feature
  • Finding the right audit skill for an app that feels off

What Makes It Unique

It carries no design rules of its own. Its value is the map: which skill leads the build, which checks follow, and which upkeep skills suit an existing app. It reads each target skill before describing it, so a recommendation reflects what that skill says today.

Under The Hood

One SKILL.md with no scripts or network access, set so the model only loads it when you invoke it by name. The model reads the SKILL.md of the skill it is about to recommend, matches your situation to the flow and replies with a recommendation.

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