Skip to content
SkillModel-led2,323 tokens in use

dbs-restore

Pulls the latest saved diagnosis from local storage and shows where you stopped, so a new chat can continue without retelling everything.

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

49tokens idle
2,323tokens in use
4,194tokens, 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 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 →
Good
  • Frontmatter8/15
  • Structure22/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • Resources7/15

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-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.

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