Skip to content
SkillModel-led706 tokens in use

using-superpowers

The bootstrap skill that makes your agent check for a relevant skill before any response, including clarifying questions.

322,762 stars on the repository MIT Licenseobra/superpowers · skills/using-superpowers
/plugin install superpowers@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing using-superpowers costs

29tokens idle
706tokens in use
3,783tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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
  • Frontmatter12/15
  • Structure17/25
  • Examples3/15
  • Output5/15
  • Size15/15
  • Resources12/15

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 activity56
  • Maintenance68
  • Community64
  • Maturity36
  • Momentum40

Using Superpowers is loaded at the start of a conversation and sets the rule that if there is even a 1% chance a skill applies, the agent must invoke it before acting. It lists the thoughts that signal rationalization, sets skill priority so process skills such as brainstorming and systematic debugging come first, and points to per-harness tool references.

What You Get

  • A mandatory skill-check rule that runs before any response
  • A priority order: process skills first, implementation skills second
  • A table of rationalizations with the reality behind each
  • Reference files for six agent harnesses
  • A precedence rule that puts your own instructions first

Common Use Cases

  • Starting any session so relevant skills fire on their own
  • Routing a build request to brainstorming and a bug report to systematic debugging
  • Running the same skill set across several coding harnesses

What Makes It Unique

Most skills wait to be called. This one is the entry point that makes the rest trigger: it removes the agent’s option to skip a skill that might apply, including before clarifying questions, and tells subagents to ignore it.

Under The Hood

Instructions only, with per-harness reference files for tool names. The skill itself runs nothing and reaches no outside services. Plugins for several harnesses inject it at session start so it is in context from the first turn.

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