predictingthepast

Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validated workflow and good use of a reference file for output format. It loses points on conciseness and progressive disclosure because the HTTP-serving snippets and full citation/dataset-acknowledgement blocks inflate the main file and would fit better as separate referenced files.

Suggestions

Move the Linux/macOS and Windows HTTP-server snippets plus the serving instructions into a reference file (e.g. references/serving_html.md) and link to it, keeping only a one-line pointer in SKILL.md.

Relocate the full citation and dataset-acknowledgement text to a reference file (e.g. references/citation.md) and summarize the requirement inline, reducing the main file's token load.

Trim the duplicated dataset-acknowledgement 'IMPORTANT' reminder (it appears twice in the References section) to a single concise instruction.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence, but the lengthy HTTP-server snippets (Linux/macOS and Windows variants) and the full dataset-acknowledgement/citation block pad the file with content that could live in a referenced file. It avoids explaining concepts Claude already knows, so it stays above 1.	2 / 3
Actionability	Provides copy-paste-ready bash commands for preprocessing, inference, and visualization, a complete flag reference, and concrete markup examples with real input strings — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step flow is explicitly sequenced (prerequisites -> preprocess -> pre-flight checks -> inference -> present results) with validation checkpoints (pre-flight confirmations, min-length/constraint warnings, restore-time estimates) and feedback loops for error recovery.	3 / 3
Progressive Disclosure	The output-format detail is correctly pushed to references/output_format.md (one level, clearly signaled), but the large HTTP-server and citation/dataset-acknowledgement sections remain inline in SKILL.md rather than being split into their own referenced files, leaving structure uneven.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, third-person, and provides explicit both 'what' and 'when' guidance with a strong set of natural trigger terms and named tools. It is concise without padding and clearly occupies a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'restoration, attribution, dating, contextualization, and embedding' — each tied to a named tool (Aeneas/Ithaca), matching the top anchor.	3 / 3
Completeness	Explicitly states what it does and includes an explicit 'Use when asked to...' trigger clause covering both natural phrases and tool-name mentions.	3 / 3
Trigger Term Quality	Includes natural user phrasings ('restore', 'attribute', 'date', 'find parallels', 'where was it written', 'embed', 'analyze') plus tool names Aeneas/Ithaca, giving broad coverage of terms a user would say.	3 / 3
Distinctiveness Conflict Risk	Highly niche — ancient-text/epigraphic restoration via specific named models (Aeneas/Ithaca) — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google-deepmind/science-skills
Path: skills/predictingthepast/SKILL.md
Commit: 0b42509

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.