Skip to content
SkillModel-led2,806 tokens in use

dbs-jtbd

Applies Jobs to Be Done to a customer, product or AI request: the progress the person wants, why now, how they choose, and what holds them back.

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

117tokens idle
2,806tokens 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-jtbd is a Chinese-language agent skill that explains why people hire a product, service, piece of content or even an AI. It looks for the situation, the progress the person is stuck on, the result they want, the current alternative and the standards they use to choose.

It also rewrites a request meant for an AI into a prompt that starts with a task statement, with situation, materials, limits, deliverable and three pass criteria. When you only want a copy or an answer, it does the analysis silently and delivers the result with one or two sentences on the job it serves.

What You Get

  • A JTBD judgment with surface request, task statement, three job layers, why now, choice criteria, switching friction, takeaways and next step
  • A rewritten AI prompt that opens with the task statement and adds situation, materials, boundaries, deliverable and three pass criteria
  • A direct answer or copy with a short note on which job it serves, when you do not want the framework
  • A list of open points limited to facts that would change the advice

Common Use Cases

  • Working out why customers leave an existing tool for a new one, and what makes them hesitate
  • Rewriting a loose request to an AI so it states the situation and what counts as good
  • Planning sales copy around the customer’s moment of trouble and the old approach that stopped working

What Makes It Unique

It deals with progress in a particular moment, not with user profiles or feature lists. The skill asks at most one concrete question, only when a missing fact would change the advice, and labels what is fact, inference and open. It avoids invented interviews or behavior data, and it skips the framework for ordinary acceptance-criteria questions. It treats AI as something a person hires, so the same method sharpens prompts.

Under The Hood

It is a prose-only skill with no scripts and no reference files. The agent reads the SKILL.md and a small agent metadata file, and works from the situation you describe in the conversation. It does not run commands, call web services or write 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