菜单
Load context for data fixes, page count corrections, and quality issues. Use when fixing specific books, debugging data problems, or running maintenance scripts.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
| name | maintenance |
| description | Load context for data fixes, page count corrections, and quality issues. Use when fixing specific books, debugging data problems, or running maintenance scripts. |
Read these files before proceeding with maintenance work:
memory/data-quality.md — Known issues by date rangememory/lessons-learned.md — Postmortem patterns.claude/docs/thumbnails.md — Cover selection and thumbnail fixesBooks imported before Dec 30, 2025 may have wrong page counts. See docs/ia-page-count-bug-report.md.
npx tsx scripts/maintenance/fix-ia-page-counts.ts --book-id=XXX --correct-count=YYYPOST https://sourcelibrary.org/api/books/{id}/reimportpipeline_auto.status to metadata_enriched, clear retry_count and errorjobs with status: 'processing', updated_at: { $lt: 2h ago }, set to cancelledCoverImagePicker or fixStaleThumbnail() in pipeline cronPOST /api/books/restore/[id]pipeline_auto.status: 'empty_shell' — don't delete, may have metadataAfter reading the memory files above, flag anything that contradicts what you observe in the codebase:
.claude/docs/image-archiving.md.claude/docs/import-apis.md