# Clean Up Promotional Emails > Claude in Chrome can scan your inbox, identify promotional and marketing emails, and flag them for your review. You decide what to delete in bulk rather than clicking through one by one. Use for tasks like “Clean up promotional emails” and close variants. TEMPLATE — customize before installing. - **Type:** Skill - **Install:** `agentstack add skill-iankiku-agent-skill-factory-clean-up-promotional-emails` - **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/clean-up-promotional-emails ## Install ```sh agentstack add skill-iankiku-agent-skill-factory-clean-up-promotional-emails ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Clean up promotional emails — 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 can scan your inbox, identify promotional and marketing emails, and flag them for your review. You decide what to delete in bulk rather than clicking through one by one. 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 Find emails I likely don't need so I can review and bulk delete. Flag these: - Promotional emails from retailers/brands - Newsletters I haven't opened in 3+ months - Automated notifications (delivered shipping updates, expired calendar reminders) - Marketing emails from SaaS products Don't flag: - Emails from actual people (not automated) - Anything with attachments - Anything from [my company domain] Output: Show me the list organized by sender so I can review before deleting. ``` ## Required context and inputs - Logged into your Gmail account before starting the Claude in Chrome session - 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 - Gmail - 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 [Clean up promotional emails](https://claude.com/resources/use-cases/clean-up-promotional-emails) (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-clean-up-promotional-emails - 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%.