sourcelibrary-v2

Run OCR and translation quality evaluations across scripts and languages. Produces research-grade reports with MCR, cross-model agreement, embedding-space hallucination detection, and corpus readiness scores.

Run a Glass Bead Game session — a parlor game played against the Source Library corpus. Players connect verified passages from different books, times, and traditions into a growing string of 'beads,' with Claude as librarian, verifier, and scribe. Trigger when the user says 'glass bead game,' 'let's play beads,' or asks to start/resume/publish a game session. Claude runs the search-verify-display loop; humans do the noticing, choosing, and judging.

Stage-2 verification of first-translation flips using INDEPENDENT Claude subagents (subscription, not API key) with full evidence capture. Use to verify proposed badge changes (demotes/promotes) before writing any public claim — the binding step that catches AI-fabricated priors. Each subagent reports its actual search queries + sources, persisted to the first_translation_attempts provenance log.

Triage and respond to the user-feedback queue — pull open feedback, detect items already fixed but never marked, route translation-requests and metadata-corrections, mark items resolved, and (on approval) email submitters. Use when asked to check/triage/answer/clear feedback, "what are people saying?", or "respond to feedback."

Sweep Claude's private per-machine memory for team-relevant operational knowledge and propose moving it into the shared repo (or the private ops repo) as draft PRs. Use to promote lessons that accreted privately, or run on a schedule. Never auto-merges; never leaks.

One-shot audience & usage report — signups, DAU/MAU, time on-site, traffic, top content, search behavior, referrers, countries, and user journeys. Use when asked "what's our usage?", "how many signups?", "time on site?", "traffic?", or any audience/engagement metrics question.

Use this skill whenever choosing or evaluating a background image for the 'quote' section of a Source Library collection page — the wide banner where a sourced quotation is overlaid on an image drawn from the collection's plates or illustrations. Trigger for any request to pick, rank, or judge a background image behind quote text, select a plate for the quote banner, or decide whether a candidate image works as a text background. The goal is a beautiful, legible, on-theme backdrop that the quotation reads cleanly over.

Populate a collection page with editorial content — expanded description, highlighted books, gallery images, sourced quotes. Also audits existing collections for staleness, broken links, and missing content. Use when a collection exists but needs its content built out, or when auditing collection quality.

Use this skill whenever writing the 'Featured work' description that appears on a Source Library collection page — the short editorial blurb beneath a highlighted book's title, author, and bibliographic stats. Trigger for any request to write, rewrite, or edit a featured-work blurb, curator's pick description, or highlighted-book caption for a collection. The output is about the BOOK itself (what it is, why it matters, what is distinctive about it), never about Source Library, translation, OCR, or digitisation.

Autonomous curator for Source Library. Discover, evaluate, and import historical texts from digital archives. Assigns books to collections. Outputs batch import scripts for efficient acquisition.

Autonomous curator for Source Library - discover, evaluate, and import historical texts in alchemy, Hermetica, Kabbalah, Rosicrucianism, and early modern knowledge. Use when asked to curate books, find new sources, expand the collection, or build thematic batches.

Batch process books through the complete pipeline - generate cropped images for split pages, OCR all pages, then translate with context. Use when asked to process, OCR, translate, or batch process one or more books.

Load context for pipeline, cron, Lambda, OCR, and translation work. Use when starting any pipeline monitoring, debugging, or processing task.

Quick canon + pipeline health check. Use when asked "how's it going?", "status?", "how's the db?", or any quick health check. Lighter than /progress — focuses on mission metrics, not job debugging.

Check pipeline processing progress — all phases including OCR, translation, image extraction, enrichment, and more. Shows real page-level verification, not just job counters. Use when asked "how's it going?", "progress?", "status?", "now?", or any progress check.

Extract and catalog illustrations from historical books using AI vision. Generates rich metadata (subjects, figures, symbols, style, technique) and museum-style descriptions. Use when asked to extract images, run image detection, or process book illustrations.

Quality auditor for Source Library. Prioritizes verifying original language texts (not modern translations), auditing metadata accuracy against title pages, USTC alignment, and translation quality. Use for systematic quality control or to identify modern translations that should be replaced with originals.

Record a lesson learned after fixing a bug or discovering a pattern. Updates domain memory files and checks for contradictions. Use after resolving non-trivial issues.

Load context for data fixes, page count corrections, and quality issues. Use when fixing specific books, debugging data problems, or running maintenance scripts.

Load context for UI, frontend, navigation, and analytics work. Use when starting any visual, interaction, or engagement task.

Search and cite primary sources from Source Library. Use when asked what historical authors wrote, to find quotes from old texts, investigate alchemical or philosophical works, or cite translated Latin/German sources.

Create a DOI-ready scholarly edition of a translated book. Use when asked to publish, create an edition, mint a DOI, or prepare a book for scholarly publication. Generates front matter, creates versioned editions, builds EPUBs, and mints DOIs via Zenodo.

Bibliographic research agent for analyzing books and manuscripts. Builds comprehensive "book biographies" showing production context, textual transmission, related editions, and scholarly networks. Use when asked to research a book's history, find related editions, analyze manuscript transmission, or build bibliographic context.