dbs-restore reads the most recent archive written by dbs-save and shows it as a short status: the original complaint, the conclusions reached, the directions you rejected, the hypotheses still to test and the next step you confirmed. It does not diagnose and does not route you anywhere until you answer.
It can also open a numbered archive, switch to another project by name, or list the three most recently active projects when the current one has nothing saved. The skill only reads the archive configuration, it never changes it.
What You Get
- A status summary with project, time, original complaint, source skill and state (in progress, concluded or abandoned)
- Lists of conclusions reached, directions you rejected and hypotheses still to verify
- The next step you confirmed last time, or a note that it is still undecided
- A list of your three most recent projects when the current project has no archive
Common Use Cases
- Continuing a business diagnosis in a new chat a week later
- Checking what you concluded and what you ruled out before acting on it
- Switching to another project’s archive with a project name or a number from the list
What Makes It Unique
It is a narrow tool that only restores state. It does not summarize the whole file, does not pick the next skill for you and asks one open question at the end. The newest archive is chosen from the timestamp in the file name, so cloud sync that rewrites modification times cannot reorder your history. It shares one archive contract with dbs-save and dbs-report.
Under The Hood
The skill is prose instructions plus one shared reference file that defines the archive location, file names and format. It reads the local configuration file and lists files under the archive root, then reads one markdown archive from disk. It makes no network calls, runs no scripts and writes no files. If the saved next step is confirmed it passes the archive content as context to the next skill.