Skip to content
SkillModel-led6,157 tokens in use

dbs-theory-grounding

Checks whether a claim in your slides, course or method holds, then anchors it to one credible theory and re-explains your case with it, limits included.

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

151tokens idle
6,157tokens 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
  • Examples9/15
  • Output0/15
  • Size11/15
  • 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-theory-grounding takes an experience-based claim with its case and first reviews the claim itself for absolutes, causal leaps, shifting definitions and over-generalising. It then defines the mechanism a theory must explain, scores two to four candidates, keeps one main theory and maps the case line by line through that theory.

It works offline by default and labels every source status, such as based on existing knowledge or verified in the original. The deliverable ends with limits, a counterexample and a slide-ready version with a short title, attribution, one-line explanation and speaker notes.

What You Get

  • A verdict on the original claim and a corrected standard
  • One main theory card with problem solved, mechanism, source and verification status
  • A table mapping each case sentence to the theory concept and the revised judgement
  • Applicable and non-applicable settings, a counterexample and unverified items
  • A slide-ready block with title, attribution, theory wording, one-line explanation and speaker notes

Common Use Cases

  • Adding a credible theory source to a course slide or keynote
  • Testing whether a favourite saying can be called a theory
  • Checking that a quoted famous name is not being forced onto a weak case

What Makes It Unique

It stays within one anchoring pass and leaves full historical studies to other skills. It keeps only one main theory per case and removes a second one that adds only common sense. The research table stays hidden unless asked, so documents for clients or teachers start from the verdict. Quotes are never presented as word-for-word unless checked against the original.

Under The Hood

The skill is one instruction file with no scripts or references. It starts from the material you provide and the model’s own knowledge and does not go online by default. It may use web search only when you ask for sources, exact quotes, page numbers or latest research, or when an outside fact would change the conclusion, and it stops after two failed checks. It writes its output in the chat and saves 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