Skip to content
SkillModel-led2,171 tokens in use

using-agent-skills

Map incoming work to the right agent skill and follow six operating behaviors that apply across all of them.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/using-agent-skills
npx skills add addyosmani/agent-skills --skill using-agent-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing using-agent-skills costs

55tokens idle
2,171tokens 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 →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • 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 →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Using Agent Skills is the meta-skill for the whole collection. It gives a discovery tree that sends each kind of task to the matching skill, from interview-me and spec-driven-development through implementation, testing, review and shipping.

It also sets six core operating behaviors: surface assumptions, manage confusion, push back when warranted, enforce simplicity, keep scope tight and verify with evidence. A lifecycle sequence and a quick reference table show how the skills combine.

What You Get

  • A skill discovery decision tree
  • Six non-negotiable operating behaviors
  • A lifecycle sequence and a quick reference of all skills
  • Four skill rules that start from checking for an applicable skill

Common Use Cases

  • Choosing a skill at the start of a session
  • Planning the sequence of skills for a feature
  • Setting shared behavior rules for an agent
  • Onboarding a team to the skill collection

What Makes It Unique

Unlike a skill for one task, this one covers the collection itself and states that skills are workflows with steps and verification. It names failure modes such as sycophancy and unsolicited renovation and points to a project-wide definition of done.

Under The Hood

The skill is a single SKILL.md of instructions that works as a router and as a set of standing rules. It runs no scripts and reaches nothing outside the repository. It names the other skills in the collection and links to a definition-of-done reference.

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