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.