Step 2 implemented

prompts/README.md

@@ -0,0 +1,13 @@
+# Prompt Artifacts
+
+This directory stores transcription prompts as individual Markdown artifacts.
+
+## Conventions
+- Keep one prompt per file.
+- Use stable, descriptive snake_case file names.
+- Prefer incremental edits to a single prompt per change for clean history.
+- Keep prompts human-readable and policy-focused.
+- Do not store secrets in prompt files.
+
+## Current Prompt
+- `transcribe_document.md`: baseline verbatim transcription policy for historical documents.

prompts/transcribe_document.md

@@ -0,0 +1,72 @@
+# Historical Document Verbatim Transcription Prompt
+
+## Purpose
+Transcribe the provided historical document image as a faithful **verbatim** transcript.
+Do not summarize. Do not paraphrase. Do not modernize style.
+
+## Output Contract
+- Return only the transcription text.
+- Preserve original wording, punctuation, and meaningful structure.
+- Keep line/section flow readable while preserving intent and document organization.
+- Never invent missing content.
+
+## Rules for Ambiguous or Damaged Text
+
+### Misspellings and original errors
+- Preserve original spelling.
+- Add `[sic]` immediately after an evident original error.
+
+### Missing words or clear omissions
+- If a single missing word is obvious from context, insert it in square brackets.
+- Example form: `[to]`
+
+### Uncertain readings
+- If best-effort interpretation is uncertain, use bracketed guess with question mark.
+- Example form: `[Boston?]`
+
+### Completely illegible text
+- Use a clear bracketed label.
+- Preferred forms: `[illegible]`, `[torn]`, `[ink blot]`, `[remainder of page torn]`
+
+### Crossed-out text
+- Preserve it using: `[deleted: ...]`
+
+### Squeezed-in or above-line insertions
+- Preserve it using: `[inserted: ...]`
+
+### Superscripts and abbreviations
+- Bring superscript letters down to baseline text.
+- Expand only when clearly intended; if expanded, place added letters in brackets.
+
+### Non-text visual elements
+- Describe briefly in square brackets.
+- Example forms: `[wax notary seal attached here]`, `[sketch of a fort layout]`
+
+### Marginalia and side notes
+- Signal location before the note text.
+- Example form: `[written in left margin: ...]`
+
+### Line-break hyphenation
+- Rejoin words split across line breaks when they are clearly one word.
+- Remove only line-break hyphens used for wrapping.
+
+### Ambiguous capitalization
+- Prefer modern capitalization only when uncertainty is high.
+- Preserve clearly intentional archaic capitalization.
+
+### Hierarchical outlines and numbering
+- Preserve original numbering characters exactly (including roman numerals and unusual suffixes).
+- Preserve indentation levels.
+- Do not silently correct sequence mistakes; if clearly erroneous, preserve and use `[sic]` where appropriate.
+
+## Confidence and Integrity Policy
+- When uncertain, mark uncertainty explicitly rather than guessing silently.
+- If text cannot be read, use a bracketed illegibility label instead of fabrication.
+- Do not add commentary outside the transcription.
+
+## Final Self-Check
+Before finalizing, ensure:
+1. The transcript is verbatim and not summarized.
+2. Uncertain/illegible areas are explicitly marked.
+3. Crossed-out and inserted text are preserved with required tags.
+4. Structure/ordering is preserved as faithfully as possible.