Skip to content
SkillModel-led1,896 tokens in use

dbs-chatroom-austrian

A fixed three-seat chatroom where simulated Hayek and Mises answer your question from Austrian economics and Claude judges the exchange.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-chatroom-austrian
npx -y skills add dontbesilent2025/dbskill -g --all
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing dbs-chatroom-austrian costs

69tokens idle
1,896tokens 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 →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • 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 →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

dbs-chatroom-austrian opens a discussion with two fixed voices. Hayek looks at who holds the knowledge a decision needs and whether order can grow without design. Mises reasons from the fact that people act and traces causes to their root. Claude plays judge and flags anyone forcing a theory onto the facts.

Each round has two answers of up to 200 words and a judge note of up to 200 words, then asks whether to continue. The first round starts with a notice that the lines are simulated from public work and are not the people’s own words.

What You Get

  • A reply from simulated Hayek of up to 200 words
  • A reply from simulated Mises of up to 200 words
  • A judge note from Claude on whether theory was forced, what was missed and what to take away
  • A simulation notice at the start of the first round
  • Follow-up rounds with context from earlier ones

Common Use Cases

  • Looking at a market, pricing or regulation question through Austrian economics
  • Seeing where a knowledge-based argument and a principle-based argument disagree
  • Testing whether a policy plan relies on central coordination
  • Getting a quick sanity check on an economics claim

What Makes It Unique

The roster is fixed at two named economists plus a judge, so you get a school-specific debate and no panel selection step. The two are set up with a deliberate contrast, one willing to compromise and one holding to principle, and the judge is told to call out forced theory and role-play for show.

Under The Hood

The agent reads SKILL.md. When the host supports sub-agents it starts the two economist voices as parallel sub-agents with the prompts written in the Skill, otherwise it writes them one after the other. It has no scripts, runs no shell commands, makes no web requests and writes no files.

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