Community recipe

Turn bookshelf photos into an owned-book inventory

A household cannot easily tell which books it owns when titles are scattered across shelves and boxes.

Read original recipe

Proposed inputs

Name
Shelf images
Owner
Book owner
Minimum scope
One shelf without people, documents or address details.
Quality check
Number the images and check focus.
Name
Existing inventory copy
Owner
Book owner
Minimum scope
Title, edition and known copy count.
Quality check
Keep item identity distinct from repeated photographs.

Access and setup — proposed or unknown

Proposed minimum: Image copies and a separate inventory draft.
Compatibility unknowns: Unknown: image resolution limits, multilingual recognition and installed runtime.
External actions requiring approval: Uploading identifying photos, replacing records, sharing lists or ordering books.

Detailed steps and output format

At a glance

Suggested result: An inventory draft with uncertain identities, editions and physical-copy counts separated.Suggested; untested.
Tool: OpenClawSource-named; check current access.
Suggested inputs: Shelf images; Existing inventory copyProposed; access notes below.
Human review: Approve the selected photos and destination inventory. Review uncertain matches and physical-copy consolidation before replacing records. Ask separately before sharing personal…
Read full note
Approve the selected photos and destination inventory. Review uncertain matches and physical-copy consolidation before replacing records. Ask separately before sharing personal details or placing holds or orders.
Suggested boundaries; source approvals below.
Setup notes: Image copies and a separate inventory draft.Guide notes; proposed setup untested.
Cost: Workflow cost not established. Check current tool pricing, setup and human review costs before trying it.No measured cost or time added.
Content depth: Source-linked example · suggestions untestedDepth does not establish successful execution.

Check source evidence and limits ↓

Function and scope

Personal, Administration · Single task

Editorial classification; no execution or compatibility test is implied.

No tool mapping reviewed for this task.

Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.

The problem

A household cannot easily tell which books it owns when titles are scattered across shelves and boxes.

Suggested task · untested

Prepare an owner-checked inventory from selected images.

What you could produce

An inventory draft with uncertain identities, editions and physical-copy counts separated.

Where these suggestions come from

Core problem: Our suggestion; no result reported by the source
Agent job: Our suggestion; no result reported by the source
Expected output: Our suggestion; no result reported by the source
Relevant job roles: Our suggestion; no result reported by the source
Benefit type: Our suggestion; no result reported by the source

Suggestions and their limits

Describes the proposed purpose and review output; measured benefit and successful delivery are not established.

Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.

Before you try it · suggestions untested

Original decision guidance and synthetic first check. Source facts are reused by reference; nothing here was executed.

Read the attributed source evidence and original caveats below ↓

Why use this

A shelf photograph may contain enough information to locate a book, but looking through many photos is awkward. A partially hidden spine can also look deceptively similar to another edition.
A checked inventory could make later selection easier and expose gaps in the record. Suggestions should be grounded in confirmed holdings, while the owner decides whether a title suits the reader.

Why an agent / simpler alternative

Useful judgment: Connect partial visual clues while preserving unresolved matches.
Simpler alternative: Use barcode scanning for books with accessible ISBNs.
Unsuitable when: Insurance valuation or exhaustive ownership proof is required.

Expected deliverable and review checks

Proposed artifact: Image-linked inventory with an uncertainty queue.
Critical checks: Similar editions remain separate until checked.
Repeated photos do not increase physical-copy counts.
Missing output evidence: No accuracy benchmark or inspected completed inventory.

First check — proposed, unexecuted

Status: proposed_unexecuted
Synthetic fixture: Mock covers showing two editions, one duplicate photo and one unreadable spine.
Acceptance checks: Editions remain separate.
Duplicate photo is not treated as another copy; unreadable entry stays unknown.
Stop conditions: Identity would require guessing or unrelated personal content appears.

Tasks: Audio & video Planning & operations Home & errands

Useful for: Personal and household

Editorial relevance from the title and source-supported actions; not evidence of the operator’s occupation.

OpenClawIndependent testing: No

Failure handling, costs and limits

Failure signals and proposed responses

Signal
One visible word becomes a confident title.
Why it matters
A plausible invention pollutes future searches.
Proposed response
Retain the image location and ask for a clearer view.
Signal
Two editions collapse into one entry.
Why it matters
The record loses a meaningful distinction.
Proposed response
Preserve separate candidates until the owner checks identifiers.

Effort and cost — unknown

Setup work: Choose shelf labels and edition/copy conventions.
Ongoing review: Confirm uncertain rows and record additions or removals.
Unknowns: Unknown: image-processing cost and manual verification effort.

Limits

No guaranteed complete catalogue, valuation or child-reading suitability; source reuse permission is unresolved.

Full source evidence

Community recipe · Tool workflows

Original task title: Turn bookshelf photos into an owned-book inventory

Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.

Original source

https://github.com/ChatPRD/tradclaw/blob/main/skills/book-inventory/SKILL.md ↗

Attributed to: Claire Vo / ChatPRD

Supporting source context

Project documentation supporting the linked recipe’s scope, permissions and limits. These references do not establish an independent test or add counted jobs.

Community recipe

Original action type: tool_action
What the source reports: Extracts visible book identities from photos, writes a household inventory, labels unreadable or uncertain entries, consolidates duplicates, and uses the resulting owned collection for requested reading suggestions.
Source outcome limits: An inventory candidate and optional reading shortlist. Preserve unknowns, editions and multiple physical copies for owner review; no acquisition, loan or child-suitability guarantee.
Evidence attribution caveat: This community recipe describes a procedure; it does not prove successful execution or independently reproduced results.
Source approval description: Workspace rules require approval before outside messages and default to asking before sharing family information. The skill gives no separate confirmation gate for inventory edits.
Named tools: OpenClaw; bookshelf/cover images; resources/books/inventory.md.
Model or version: Unknown
Publication date: Unknown
Source last checked: 2026-10-14
Demonstrated in Canada: Unknown
Canadian availability: Unknown
Proposed Canadian adaptation: Keep title spelling, language, edition and local shelf location reviewable. A guardian decides suitability when books are for children; Canadian library availability is not part of this recipe.
Recommended approval boundaries: Approve the selected photos and destination inventory. Review uncertain matches and physical-copy consolidation before replacing records. Ask separately before sharing personal details or placing holds or orders.