Skip to content
SkillModel-led5,398 tokens in use

dbs-learning

Turns a topic into a numbered series of study articles and reads the feedback you write at the end of each one to set the depth of the next.

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

75tokens idle
5,398tokens 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
  • Examples9/15
  • 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-learning is a Chinese-language agent skill for studying one topic over many sessions. It creates a topic folder with a study plan and numbered articles, each ending with a feedback section where you write what you understood, what you did not, and what you want expanded.

When you ask for the next article it reads that feedback first, summarizes your understanding in three to five points, and picks the depth and angle of the next piece to match. For a new topic inside a project it can check the project’s own materials to guess your starting level, then asks you to confirm before it writes anything.

What You Get

  • A topic folder with a study plan file named 00-学习计划.md, numbered articles such as 01.md and 02.md, and an assets folder
  • Every article built from the same sections: the problem it solves, body, summary, preview of the next article and a feedback area
  • A three-choice question about your knowledge baseline when the project already holds related material: build on the project, start from zero, or use files you name
  • An index file listing each topic, its progress, last update and next step
  • A next article that responds to your feedback: simpler with examples, a new angle, more cases, or a higher level

Common Use Cases

  • Studying a field such as economics in a sequence of articles that tracks what you did and did not follow
  • Turning one method from your own notes into a short course that grows with your questions
  • Resuming a topic after a break by saying continue and letting the agent read your last feedback

What Makes It Unique

The next lesson depends on what the learner wrote after the last one. The skill filters out the template prompts in the feedback area so only your own words count, and it maps feedback types to responses: confusion lowers abstraction, boredom changes the angle, application questions bring cases. It treats project files as weak evidence of what you know, ranks your own published writing above AI drafts and third-party text, and never reads credentials or private material unless you name it.

Under The Hood

It is a prose-only skill with no scripts. The agent reads the SKILL.md only. It writes files: it creates a topic folder, study plan, numbered articles and index in your project or in a Documents folder, and updates them each round. For a new topic in a project it reads a few top-level files such as README and AGENTS.md and related material, and skips environment files, keys and other sensitive items. It does not call web services or run commands.

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