sales-inbox-zero
Inbox Zero platform help — open-source AI email assistant that auto-labels your inbox, drafts replies in your voice, blocks cold emails, bulk unsubscribes, and exposes a REST API + CLI for automation rules ($18-42/mo, self-hostable, 10K+ GitHub stars). Use when setting up Inbox Zero for Gmail or Outlook, AI drafts don't sound like you after weeks of use, automation rules aren't firing or mislabeling emails, self-hosting setup fails with Docker or Google PubSub errors, comparing Inbox Zero to Fyxer or Superhuman or SaneBox or Shortwave for inbox management, managing email rules via the CLI or REST API from an AI coding agent, or choosing between Starter/Plus/Professional plans. Do NOT use for choosing a dedicated meeting note-taker (use /sales-note-taker). Do NOT use for AI executive assistant comparison (use /sales-alfred).
What this skill does
# Inbox Zero Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
Ask the user:
1. **What are you trying to do with Inbox Zero?**
- A) Set up Inbox Zero for the first time (hosted or self-hosted)
- B) Fix inbox organization / mislabeled emails
- C) Improve AI draft quality (sounds robotic, wrong tone)
- D) Build automation rules (plain-English or API/CLI)
- E) Bulk unsubscribe or archive
- F) Compare Inbox Zero to alternatives
- G) Self-hosting or Docker deployment issues
- H) Something else — describe it
2. **Which email provider?**
- A) Gmail / Google Workspace
- B) Outlook / Microsoft 365
- C) Other (IMAP — limited support)
3. **Which plan are you on (or considering)?**
- A) Free trial (haven't decided yet)
- B) Starter ($18/mo) — single account, basic automation
- C) Plus ($28/mo) — 2 accounts, Slack, attachments
- D) Professional ($42/mo) — team analytics, priority support
- E) Self-hosted (free, BYO infrastructure)
**If the user's request already provides most of this context, skip directly to the relevant step.** Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask only the most critical 1-2 clarifying questions at the end.
## Step 2 — Route or answer directly
If the request maps to another skill, route:
- Choosing a meeting note-taker → "Run: `/sales-note-taker {user's original question}`"
- AI executive assistant comparison (alfred_ etc.) → "Run: `/sales-alfred {user's original question}`"
- CRM integration strategy → "Run: `/sales-integration {user's original question}`"
- General email deliverability → "Run: `/sales-deliverability {user's original question}`"
Otherwise, answer directly from the platform reference below.
## Step 3 — Inbox Zero platform reference
**Read `references/platform-guide.md`** for the full platform reference — capabilities, pricing, data model, API endpoints, CLI usage, self-hosting, and integration recipes.
Answer the user's question using only the relevant section. Don't dump the full reference.
## Step 4 — Actionable guidance
You no longer need the platform guide — focus on the user's specific situation.
**For improving draft quality:**
1. Send more emails manually — Inbox Zero learns from your sent history
2. Add context to your knowledge base (Plus+ only) — company info, style guides
3. Always review drafts before sending — the AI never auto-sends
4. Calendar integration improves drafts by factoring in your schedule
**For fixing automation rules:**
1. Write rules in plain English — be specific about conditions and actions
2. Test rules on a few emails before enabling broadly
3. Check the rule execution log to see which rules fired
4. If rules conflict, reorder by priority — first matching rule wins
**For self-hosting decisions:**
1. Self-hosting is free but requires Docker, Node.js v24+, PostgreSQL, and Google/Microsoft OAuth setup
2. You need Google PubSub for real-time Gmail push notifications — this is the most common setup failure
3. The hosted version ($18+/mo) skips all infrastructure complexity
4. Self-hosted gets the same features but you manage updates and uptime
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there.
## Gotchas
*Best-effort from research — review these, especially items about plan-gated features and integration gotchas that may be outdated.*
- **Gmail and Outlook only (hosted).** Despite being open-source, the hosted version only supports Gmail and Outlook. IMAP/SMTP support is the #1 requested feature but not yet shipped. Self-hosted users can attempt IMAP but it's experimental.
- **No Zapier, no Make, no MCP server.** The only programmatic interfaces are the REST API and CLI. If you need iPaaS connectivity, you'll need to build a custom webhook bridge.
- **Slack integration requires Plus ($28/mo).** Starter plan has no messaging integrations.
- **Attachment auto-filing requires Plus ($28/mo).** Google Drive and OneDrive filing is plan-gated.
- **Self-hosting requires Google PubSub.** The most common deployment failure is missing `GOOGLE_PUBSUB_TOPIC_NAME` — without it, real-time email processing won't work for Gmail.
- **API is rules + analytics only.** You cannot read/send/archive emails via the API — it manages automation rules and retrieves inbox stats.
- **Self-improving**: If you discover something not covered here, append it to `references/learnings.md` with today's date.
## Related skills
- `/sales-fyxer` — Fyxer AI email assistant (inbox organization, voice-trained drafts, meeting notes, $22.50-50/mo). Install:
`npx skills add sales-skills/sales --skill sales-fyxer -a claude-code`
- `/sales-superhuman` — Superhuman AI email client (keyboard workflow, Split Inbox, MCP server, $25-40/mo). Install:
`npx skills add sales-skills/sales --skill sales-superhuman -a claude-code`
- `/sales-shortwave` — Shortwave AI-native Gmail client (AI filters, Ghostwriter, MCP consumer, $24-100/mo). Install:
`npx skills add sales-skills/sales --skill sales-shortwave -a claude-code`
- `/sales-sanebox` — SaneBox server-side email filtering (smart folders, any email provider, $7-36/mo). Install:
`npx skills add sales-skills/sales --skill sales-sanebox -a claude-code`
- `/sales-clean-email` — Clean Email inbox cleanup (bulk actions, Auto Clean rules, Unsubscriber, $29.99/yr). Install:
`npx skills add sales-skills/sales --skill sales-clean-email -a claude-code`
- `/sales-unboxd` — Unboxd AI email secretary (action item extraction, daily briefings, $7.50-41.67/mo). Install:
`npx skills add sales-skills/sales --skill sales-unboxd -a claude-code`
- `/sales-unrollme` — Unroll.me free newsletter unsubscribe and digest (data-funded, not available in EU). Install:
`npx skills add sales-skills/sales --skill sales-unrollme -a claude-code`
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install:
`npx skills add sales-skills/sales --skill sales-do -a claude-code`
## Examples
### Example 1: Automation rules keep mislabeling client emails
**User says**: "I wrote a rule to label client emails as 'Priority' but it's also catching newsletters — how do I fix this?"
**Skill does**:
1. Reads the platform guide for rule syntax and execution logic
2. Explains that rules match in order — first match wins
3. Suggests adding an exclusion condition (e.g., "except from addresses containing 'newsletter' or 'noreply'")
4. Recommends testing the rule via CLI (`rules list --json`) to inspect current config
5. Notes that rules can be refined over time as the AI learns from corrections
**Result**: Targeted fix for rule mislabeling with CLI debugging approach
### Example 2: Managing rules via CLI from Claude Code
**User says**: "How do I use the Inbox Zero CLI to list and create automation rules from my AI coding agent?"
**Skill does**:
1. Reads the platform guide for CLI reference
2. Shows installation: `npm install -g @inbox-zero/api`
3. Shows auth: `export INBOX_ZERO_API_KEY=iz_...`
4. Shows `rules list --json` to inspect current rules
5. Shows `rules create` with a JSON rule definition from stdin
6. Notes `stats by-period --json` for inbox analytics
**Result**: Working CLI setup with code examples for AI agent integration
### Example 3: Comparing Inbox Zero to Superhuman
**User says**: "Should I use Inbox Zero or Superhuman? I'm a solopreneur on a budget."
**Skill does**:
1. Compares: Inbox Zero is open-source with API/CLI access at $18/mo (or free self-hosted); Superhuman is premium speed-focused at $25-40/mo
2. Notes Inbox Zero has bulk unsubscribe, cold email blocking, and plain-English rules; Superhuman has keyboard speed, Split Inbox, and MCP server
3. Notes Inbox Zero is self-hostable for $0; Superhuman is SaaS-only
4. Recommends Inbox Zero for budget-conscious users who want automation + open-source flexibility; SupRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.