# Compare Products Across Sites > Claude in Chrome reads the specs from multiple product pages you have open, normalizes the data, and creates a comparison table in Google Sheets. Use for tasks like “Compare products across sites” and close variants. TEMPLATE — customize before installing. - **Type:** Skill - **Install:** `agentstack add skill-iankiku-agent-skill-factory-compare-products-across-sites` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [iankiku](https://agentstack.voostack.com/s/iankiku) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [iankiku](https://github.com/iankiku) - **Source:** https://github.com/iankiku/agent-skill-factory/tree/main/templates/claude-in-chrome/compare-products-across-sites ## Install ```sh agentstack add skill-iankiku-agent-skill-factory-compare-products-across-sites ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Compare products across sites — skill template Turn this template into a working skill by resolving every `TODO`. The seed prompt below is the published Anthropic example this template was derived from; your skill should generalize it for repeated, hands-off use. ## Outcome Claude in Chrome reads the specs from multiple product pages you have open, normalizes the data, and creates a comparison table in Google Sheets. TODO: Restate the outcome for YOUR context in one sentence: who runs this, on what input, producing what artifact, how often. ## Seed prompt (verbatim from source, © Anthropic PBC) ```text I'm trying to decide between a few laptops and I have the product pages open in different tabs. Can you look at each one, pull out the specs, and put them in a Google Doc so I can compare them side by side? I care most about: processor, RAM, storage, screen size, battery life, and weight. Let me know which one wins on each category. ``` ## Required context and inputs - Claude in Chrome extension installed - Paid plan subscription required - Product pages open in separate browser tabs - Google Docs/Sheets login for output creation - TODO: exact file paths / folders / message formats this skill should expect - TODO: domain context the model cannot infer (naming conventions, thresholds, house style) ## Tools, connectors, APIs, and authentication - Claude in Chrome extension - TODO: confirm which connectors are enabled in the runtime that will execute this skill - Authentication: connectors authenticate via their own OAuth flows — this skill must NEVER ask for, store, or echo credentials, tokens, or API keys. If auth is missing, stop and tell the user which connector to enable. ## Permissions and sensitive actions - Reads: TODO (folders, channels, records this skill may read) - Writes: TODO (what it may create/modify, and where) - Held back for the primary agent / human: sending external communications, financial transactions, deleting or overwriting originals, submitting web forms, and ANY click that finalizes state on a third-party site (browser-use skill: show a review step first) ## Workflow 1. Describe the task 2. Give Claude context 3. What Claude creates 4. Follow up prompts 5. Tricks, tips, and troubleshooting TODO: adapt the steps above (from the source page) into imperative instructions for the executing agent, including what to do between steps. ## Decision points - TODO: list each point where the skill must choose between paths, with the rule to apply - Default rule: prefer the reversible option; when two readings of the input are plausible, surface both rather than picking silently. ## Validation criteria - Output matches the outcome statement above (spot-check against the seed prompt's asks) - Every factual claim is traceable to a provided input, connector record, or cited source - Nothing is submitted/saved on a website without showing the user a review step first - Site actions limited to the domains named in the workflow - TODO: add one domain-specific check a reviewer in your org would apply ## Failure modes and fallbacks - Connector unavailable or unauthenticated → pause, tell the user exactly which connector to enable and why; offer a degraded run from uploaded files - Page fails to load or selector drifts → retry once, then stop and report; never guess at form fields - Ambiguous or missing input → ask one targeted question; if unattended, state the assumption inline and proceed - Any step would take a sensitive/irreversible action → stop and hand back to the user (see Delegation) ## Delegation Apply the repo's delegation policy (`docs/delegation-policy.md` — bundle or restate it if you install this skill outside the repo). Defaults for this template: - Run single-agent unless a step fans out over independent items (files, records, vendors, channels). Only independent work parallelizes. - Each delegated task must ship with: the minimal context slice it needs, an explicit output contract, a validation check the primary agent runs on the result, and a fallback if it returns empty or fails. - Final review, synthesis, and every sensitive action listed above stay with the primary agent. - TODO: name the concrete subtasks (if any) that qualify for delegation here. ## Attribution Derived from [Compare products across sites](https://claude.com/resources/use-cases/compare-products-across-sites) (retrieved 2026-07-26). Seed prompt and workflow content © Anthropic PBC. Scaffold structure original to this repository. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [iankiku](https://github.com/iankiku) - **Source:** [iankiku/agent-skill-factory](https://github.com/iankiku/agent-skill-factory) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-iankiku-agent-skill-factory-compare-products-across-sites - Seller: https://agentstack.voostack.com/s/iankiku - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.