Skip to content
SkillModel-led2,106 tokens in use

idea-refine

Turn a vague idea into a one-pager through divergent expansion, stress-testing and a Not Doing list.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing idea-refine costs

76tokens idle
2,106tokens in use
8,949tokens, 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. Scripts: scripts/idea-refine.sh.

Touches

shelldetectedwrites filesdetected

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
  • Structure23/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources11/15

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
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 34
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 34

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

Idea Refine acts as an ideation partner that moves an idea through three phases. Phase one restates the idea as a How Might We problem, asks three to five sharpening questions and generates five to eight variations. Phase two clusters the favorites, tests each on user value, feasibility and differentiation, and names hidden assumptions.

Phase three writes a markdown one-pager with the problem statement, recommended direction, key assumptions, MVP scope and a Not Doing list, saved to docs/ideas after the user confirms.

What You Get

  • A three-phase ideation process
  • Supporting files with frameworks, an evaluation rubric and example sessions
  • A markdown one-pager template
  • A setup script that creates the docs/ideas folder

Common Use Cases

  • Shaping a vague product idea
  • Stress-testing assumptions before building
  • Exploring alternatives before choosing a direction
  • Writing an MVP scope

What Makes It Unique

The skill limits itself to five to eight considered variations, refuses to skip the question of who the idea is for and treats the Not Doing list as the most valuable output. It hands off to interview-me when the user is unsure what they want and to spec-driven-development once a direction is chosen.

Under The Hood

The skill loads a SKILL.md and, on demand, three supporting markdown files with frameworks, evaluation criteria and examples. In a codebase the agent may read files with Glob, Grep and Read to ground its variations. An optional shell script creates docs/ideas, and the agent writes the one-pager there after the user confirms.

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