Predictingthepast

100TrustedShips scripts

Restoration, dating, and attribution analysis for Ancient Greek and Latin inscriptions.

What it does

Predictingthepast allows an assistant to perform specialized epigraphic analysis on classical texts. It provides tools to reconstruct damaged inscriptions, determine their probable geographic or chronological origins, and identify parallel texts from the historical record.

By executing internal scripts specifically designed for Greek and Latin character sets, the system processes fragments to produce machine-inferred restorations and embedding vectors. It operates entirely offline, relying on established epigraphic datasets to interpret text gaps while maintaining strict attribution of the source data.

When it earns its place

Reach for it when…

Apply this when examining fragmentary ancient inscriptions that require character-level restoration, or when seeking the likely time period and region associated with a specific epigraphic text.

Look elsewhere when…

This is not intended for the translation or linguistic analysis of long-form literary texts or classical manuscripts that lack the structural nature of stone or plaque inscriptions.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • restore this damaged Latin inscription fragment
  • determine the probable date for this Greek epigraphic text
  • find parallel inscriptions for this fragment
  • identify the origin of this stone inscription

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/predictingthepast ~/.claude/skills/predictingthepast

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/predictingthepast .claude/skills/predictingthepast

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server