本文へ移動
cccskills
無料GitHub で公開

cowork-home-inventory

Build an insurance-grade home inventory from a folder of photos and receipts -- identifies items, pulls values from receipts, estimates replacement costs, organizes by room, and outputs the documentation an insurance claim actually requires. Update mode keeps it current after new purchases.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Cowork Home Inventory

Build the document everyone wishes they had after the fire, flood, or break-in: a room-by-room inventory with values and proof. Input: a folder of photos (room shots, close-ups, serial-number shots) and receipts (PDF, email exports, images). Output: a structured inventory file plus a gap list of what still needs documenting.

Workflow

  1. Process the photos. Identify items in each image: what it is, brand/model when visible, condition, and the room (from filename, folder structure, or visual context). Read serial numbers and model plates from close-ups. Group multiple angles of the same item.
  2. Process the receipts. Extract item, vendor, date, and price from every receipt. Match receipts to photographed items where possible -- a matched receipt upgrades an item from "estimated" to "documented."
  3. Value the inventory. For receipt-matched items: purchase price and date. For unmatched items: estimated replacement cost (current retail for an equivalent, via web search for significant items), clearly labeled ESTIMATE. Never present an estimate as a documented value.
  4. Build the inventory. Output home-inventory.csv (or .xlsx via the xlsx skill) -- room, item, brand/model, serial, purchase date, purchase price, replacement estimate, documentation status, photo filename(s), receipt filename -- plus home-inventory-summary.md: totals by room and category, the high-value items list, and overall documented vs. estimated ratio.
  5. Gap list. What insurance will ask for that is missing: high-value items with no receipt (jewelry, electronics, instruments -- may need appraisals or serial-number photos), rooms with no coverage, items where only a wide shot exists. Rank by value at risk. Suggest the 20-minute photo walk that closes the worst gaps.

Rules

  • Documented and estimated values never blend: every line is labeled, and the summary reports both totals separately.
  • Never inflate. Replacement estimates use realistic current retail for equivalent items, not premium substitutes.
  • Serial numbers are gold: capture every legible one, and put items that should have one but don't on the gap list.
  • Do not catalog people, documents with financial account numbers, or anything in photos beyond the possessions themselves.
  • Note policy-relevant thresholds generically ("many policies sub-limit jewelry; confirm your rider") without interpreting the user's actual policy -- unless the policy document is in the folder, in which case cite its stated limits next to the relevant categories.
  • Keep the inventory file local and note in the summary that a copy belongs somewhere that survives the house (cloud drive, safe deposit).

Update Mode

Re-run on the same folder after adding new photos/receipts: append new items, update matched ones, preserve manual edits to the CSV, and report what changed. As a quarterly Cowork scheduled task, sweep the receipts/email-export folder and deliver the diff.

Quick Commands

  • "Inventory [folder]" -- full workflow
  • "What's undocumented?" -- step 5, the gap list
  • "Value check [item]" -- one replacement-cost lookup
  • "Update from new photos" -- update mode

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

日本語の概要は準備中です。原文の説明を表示しています。

OneWave-AI/claude-skills3392026年10月2日 更新

OneWave-AI のスキルをすべて見る

このスキルの問題を報告する