Skip to content
SkillMixed7,738 tokens in use

dbs

The entry point of the dbskill toolbox: it reads your problem, picks the right Skill or a sequence of them, and works through the task in the same conversation.

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

110tokens idle
7,738tokens in use
10,566tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/check-update.sh, scripts/list-official-skills.py, scripts/numbered-prompts.py.

Touches

shelldetectednetworkdetectedwrites filesdetected

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
  • Size11/15
  • Resources8/15

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 →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 26
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/check-update.sh, line 24
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    scripts/check-update.sh, line 27

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 is the dispatcher of dontbesilent’s Chinese business and content toolbox. You describe a problem, some material or a decision you are stuck on, and it works out the end result you need, picks one Skill or an ordered set, tells you why, and starts the work in the same turn.

It also runs a beginner walkthrough, opens numbered prompts published in the author’s GitHub repository, and lists every numbered prompt on request. The Skill text is written in Chinese and replies in the language you use.

What You Get

  • A short statement of what dbs understood, which Skills it will use and why, before any analysis starts
  • One Skill, a sequence, parallel runs or side-by-side comparisons, chosen from what the task needs
  • A beginner walkthrough when you type /dbs with a request for an introduction
  • Numbered hidden prompts run from /dbs followed by a three-digit code, and a list of all published codes
  • An update reminder at the end of a reply when a newer dbskill version exists

Common Use Cases

  • You have a business problem such as low renewals and do not know which method to start with
  • You have a draft and want it checked, rewritten and formatted by several Skills in order
  • You want to see what dbskill can do before choosing a command
  • You received a three-digit code in a video and want to run it

What Makes It Unique

Most skills do one job. dbs does no business analysis of its own: it is a router that reads each candidate Skill’s handoff field (what state it takes over and what it delivers), plans backward from the deliverable, and avoids using more Skills than needed. It lists choices when the direction is yours to decide, and it keeps a short task state across turns so you never repeat the command.

Under The Hood

Each time it starts, dbs runs a shell script that fetches a small version file from the author’s GitHub raw URL at most once a day and writes a timestamp to a folder in your home directory (.dbs). It also runs a Python script that lists the installed dbskill Skills from the local files. For numbered prompts, another Python script downloads the catalog and the prompt file from the author’s public GitHub repository, checks a hash, and the agent then follows that prompt. These are network fetches and local commands, not code from a hidden source. The agent reads the chosen Skills’ SKILL.md files and follows them.

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