Skip to content
SkillModel-led7,571 tokens in use

dbs-standard-answer

Researches a complex question in two parts, first the theories, authors and field knowledge, then historical cases, and ends with a conditional standard answer.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-standard-answer
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-standard-answer costs

142tokens idle
7,571tokens 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
  • Structure22/25
  • Examples12/15
  • Output0/15
  • Size13/15
  • 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-standard-answer starts with a direct answer to your question, then does two linked pieces of research. Part one reviews the claim for absolutes and causal leaps, maps relevant fields, authors and theories, verifies the main theory’s source and applies it to your situation. Part two turns the problem into a structural fingerprint and compares historical cases with the same structure: nearest successes, cross-field repeats, failures and counterexamples.

The result is graded as mature consensus, conditional answer or no unified answer, and is written as when X holds, the repeated approach is Y because Z, and it fails when W. Short questions get a short merged answer, and video, course or slide versions are added after the research when requested.

What You Get

  • A direct answer followed by a claim review (keep, narrow, rebuild or drop)
  • A table of fields, authors, theories and mechanisms with verification status
  • Four to six historical cases with success, failure and counterexample roles, and a similarity matrix
  • A conditional standard answer with its cause, its failure boundary and a list of open facts
  • Optional short-video prototypes, slide or course versions built on the research

Common Use Cases

  • Asking whether a classic solution exists for a recurring business or career problem
  • Finding credible theory behind a method before turning it into a course or video
  • Comparing how similar founders or organisations handled the same bind

What Makes It Unique

It joins theory research and historical case comparison in one flow, and the mechanisms found in part one decide which cases enter part two. It grades its own conclusion, separates verified facts from interpretation and inference, and states where the answer breaks. Quotes found through secondary sources are labelled as such, and unverifiable anecdotes are not written as fact.

Under The Hood

The skill is one long instruction file with no scripts. It works from your material and the model’s own knowledge by default. It may search the web only when an external fact would change the conclusion or you ask for sources, and it stops after two failed attempts to verify a fact. It does not write files unless you ask for a deliverable, and it prefers original works, papers and official archives over encyclopedias when it does check.

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