calibre-metadata-apply

A skill for updating metadata of existing Calibre books.

Requirements

• calibredb must be available on PATH in the runtime environment
• subagent-spawn-command-builder installed (for spawn payload generation)
• pdffonts is optional/recommended for PDF evidence checks
• Reachable Calibre Content server URL
• http://HOST:PORT/#LIBRARY_ID
• If authentication is enabled, prefer /home/altair/.openclaw/.env:
• CALIBRE_USERNAME=
• CALIBRE_PASSWORD=
• Pass --password-env CALIBRE_PASSWORD (username auto-loads from env)
• You can still override explicitly with --username .
• Optional auth cache: --save-auth (default file: ~/.config/calibre-metadata-apply/auth.json)

Supported fields

Direct fields (set_metadata --field)

• title
• title_sort
• authors (string with & or array)
• author_sort
• series
• series_index
• tags (string or array)
• publisher
• pubdate (YYYY-MM-DD)
• languages
• comments

Helper fields

• comments_html (OC marker block upsert)
• analysis (auto-generates analysis HTML for comments)
• analysis_tags (adds tags)
• tags_merge (default true)
• tags_remove (remove specific tags after merge)

Required execution flow

A. Target confirmation (mandatory)

• Run read-only lookup to narrow candidates
• Show id,title,authors,series,series_index
• Get user confirmation for final target IDs
• Build JSONL using only confirmed IDs

B. Proposal synthesis (when metadata is missing)

• Collect evidence from file extraction + web sources
• Show one merged proposal table with:
• candidate, source, confidence (high|medium|low)
• title_sort_candidate, author_sort_candidate
• Get user decision:
• approve all
• approve only:
• reject:
• edit: =
• Apply only approved/finalized fields
• If confidence is low or sources conflict, keep fields empty

C. Apply

• Run dry-run first (mandatory)
• Run --apply only after explicit user approval
• Re-read and report final values

Analysis worker policy

• Use subagent-spawn-command-builder to generate sessions_spawn payload for heavy candidate generation
• task is required.
• Profile should include model/thinking/timeout/cleanup for this workflow.
• Use lightweight subagent model for analysis (avoid main heavy model)
• Keep final decisions + dry-run/apply in main

Data flow disclosure

• Local execution:
• Build calibredb set_metadata commands from JSONL.
• Read/write local state files (state/runs.json) and optional auth/config files under ~/.config/calibre-metadata-apply/.
• Subagent execution (optional for heavy candidate generation):
• Uses sessions_spawn via subagent-spawn-command-builder.
• Text/metadata sent to subagent can reach model endpoints configured by runtime profile.
• Remote write:
• calibredb set_metadata updates metadata on the target Calibre Content server.

• Do not use --save-plain-password unless explicitly instructed by the user.
• Prefer env-based password (--password-env CALIBRE_PASSWORD) over inline --password.
• If user does not want external model/subagent processing, keep flow local and skip subagent orchestration.

Long-run turn-split policy (library-wide)

For library-wide heavy processing, always use turn-split execution.

Unknown-document recovery flow (M3)

Batch sizing rule:

• Keep each unknown-document batch small enough to show full row-by-row results in chat (no representative sampling).
• If unresolved items remain, stop and wait for explicit user instruction to start the next batch.

User intervention checkpoints (fixed)

• Light pass (metadata-only)
• Always run this stage by default (no extra user instruction required)
• Analyze existing metadata only (no file content read)
• Present a table to user:
• current file/title
• recommended title/metadata
• confidence/evidence summary
• Stop and wait for user instruction before any deeper stage
• On user request: page-1 pass
• Read only the first page and refine proposals
• Report delta from light pass
• If still uncertain: deep pass
• Read first 5 pages + last 5 pages
• Add web evidence search
• Produce finalized proposal with confidence + rationale
• Approval gate
• Show detailed findings and request explicit approval before apply

Pending and unsupported handling

• Use pending-review tag for unresolved/hold items.
• If document is unresolved in current flow, do not force metadata guesses.
• Tag with pending-review and keep for follow-up investigation.

Diff report format (for unknown batch runs)

Return full results (not samples):

• execution summary (target/changed/pending/skipped/error)
• full changed list with id + key before/after fields
• full pending list with id + reason
• full error list with id + error summary
• confidence must be expressed as high|medium|low

Runtime artifact policy

• Keep run-state and temporary artifacts only while a run is active.
• On successful completion, remove per-run state/artifacts.
• On failure, keep minimal artifacts only for retry/debug, then clean up after resolution.

Internal orchestration (recommended)

• Use lightweight subagent for all analysis stages
• Keep apply decisions in main session
• Persist run state for each stage in state/runs.json

Turn 1 (start)

• Main defines scope
• Main generates spawn payload via subagent-spawn-command-builder (profile example: calibre-meta), then calls sessions_spawn
• Save run_id/session_key/task via scripts/run_state.mjs upsert
• Immediately tell the user this is a subagent job and state the execution model used for analysis
• Reply with "analysis started" and keep normal chat responsive

Turn 2 (completion)

• Receive subagent completion notice
• Save result JSON
• Complete state handling via scripts/handle_completion.mjs --run-id ... --result-json ...
• Return summarized proposal (apply only when needed)

• state/runs.json

PDF extraction policy

• Try ebook-convert first
• If empty/failed, fallback to pdftotext
• If both fail, switch to web-evidence-first mode

Sort reading policy

• Use user-configured reading_script for Japanese/non-Latin sort fields
• katakana / hiragana / latin
• Ask once on first use, then persist and reuse
• Default policy is full reading (no truncation)
• Config path: ~/.config/calibre-metadata-apply/config.json
• key: reading_script

Usage

Dry-run:

cat changes.jsonl | node skills/calibre-metadata-apply/scripts/calibredb_apply.mjs \
  --with-library "http://127.0.0.1:8080/#MyLibrary" \
  --password-env CALIBRE_PASSWORD \
  --lang ja

Apply:

cat changes.jsonl | node skills/calibre-metadata-apply/scripts/calibredb_apply.mjs \
  --with-library "http://127.0.0.1:8080/#MyLibrary" \
  --password-env CALIBRE_PASSWORD \
  --apply

Do not

• Do not run direct --apply using ambiguous title matches only
• Do not include unconfirmed IDs in apply payload
• Do not auto-fill low-confidence candidates without explicit confirmation