sales-unboxd
Unboxd platform help — AI email secretary that reads every email and extracts action items with deadlines into daily briefings, supports Gmail/Outlook/IMAP ($7.50-41.67/mo). Use when action items keep getting lost in email threads, spending too much time reading and triaging emails, daily briefing is missing important messages, credits are running out before the month ends, emails getting categorized into the wrong bucket, comparing Unboxd to Fyxer or Superhuman or SaneBox or Shortwave for inbox triage, or setting up Unboxd with multiple email accounts. Do NOT use for AI reply drafting or voice-trained email writing (use /sales-fyxer or /sales-superhuman). Do NOT use for choosing a meeting note-taker (use /sales-note-taker).
What this skill does
# Unboxd Platform Help
Helps with Unboxd — an AI email secretary that reads every email for you and extracts action items, highlights, and FYIs into structured daily briefings. Supports Gmail, Outlook, and IMAP.
## 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 Unboxd?**
- A) Set up Unboxd for the first time
- B) Fix categorization (emails in wrong bucket)
- C) Manage credits / hitting daily limits
- D) Configure multiple email accounts
- E) Compare Unboxd to alternatives
- F) Something else — describe it
2. **Which email provider(s)?**
- A) Gmail / Google Workspace
- B) Outlook / Microsoft 365
- C) IMAP (other provider)
- D) Multiple providers
3. **Which plan are you on (or considering)?**
- A) Plus ($7.50/mo) — 2 accounts, 20 emails/day
- B) Pro ($12.50/mo) �� 4 accounts, 50 emails/day
- C) Ultra ($41.67/mo) — 8 accounts, 200 emails/day
- D) Not sure / evaluating
**If the user's request already provides most of this context, skip directly to the relevant step.**
## Step 2 — Route or answer directly
| If the question is about... | Route to... |
|---|---|
| AI-drafted email replies in your voice | `/sales-fyxer {question}` or `/sales-superhuman {question}` |
| Meeting note-taking or call recording | `/sales-note-taker {question}` |
| AI executive assistant (calendar + tasks + email) | `/sales-alfred {question}` |
| General AI email assistant comparison | `/sales-do AI email assistant selection` |
For Unboxd-specific questions, continue to Step 3.
## Step 3 — Unboxd platform reference
**Read `references/platform-guide.md`** for the full platform reference — capabilities, pricing, categorization logic, provider setup, and comparison data.
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 **categorization issues**: Manually correct miscategorized emails — Unboxd learns from corrections over time
- For **credit management**: Check daily usage patterns, consider upgrading if consistently hitting limits
- For **missing action items**: Verify the sender isn't in your block list, check if the email was processed (credit used)
- For **multiple accounts**: Each plan tier limits connected accounts — Plus (2), Pro (4), Ultra (8)
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 credit limits that may be outdated.*
- **Credit-based pricing with daily caps.** Plus plan processes only 20 emails/day (600/mo). High-volume inboxes will hit limits fast — important emails arriving after the daily cap won't be processed until the next day.
- **No API, no webhooks, no Zapier/Make.** Entirely closed ecosystem. You cannot export action items programmatically or integrate with task managers automatically.
- **No AI reply drafting.** Unboxd reads and categorizes — it does NOT write replies. If you need AI-drafted responses, pair it with Superhuman or Fyxer, or use a different tool entirely.
- **IMAP polling vs webhook.** Gmail and Outlook use real-time webhooks for email retrieval. IMAP uses periodic polling — expect delays for non-Gmail/Outlook providers.
- **Small startup (~1,000 users).** Limited community support, no G2/Capterra reviews. Evaluate stability risk for mission-critical email workflows.
- **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 platform help — AI email assistant with voice-trained reply drafting and meeting notes
- `/sales-superhuman` — Superhuman platform help — fastest AI email client with keyboard workflow and MCP server
- `/sales-sanebox` — SaneBox server-side email filtering (smart folders, any email provider, $7/mo). Install:
`npx skills add sales-skills/sales --skill sales-sanebox -a claude-code`
- `/sales-inbox-zero` — Inbox Zero open-source AI email assistant (auto-labeling, rules API/CLI, self-hostable, $18/mo or free). Install:
`npx skills add sales-skills/sales --skill sales-inbox-zero -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-alfred` — alfred_ platform help — AI executive assistant for email triage, tasks, and calendar
- `/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: Credits running out before month end
**User says**: "I'm on the Plus plan and I keep running out of Unboxd credits by the 15th. What should I do?"
**Skill does**:
1. Reads platform guide for credit system details
2. Explains Plus plan: 600 credits/mo, 20/day cap — if inbox receives 30+ emails/day, many go unprocessed
3. Suggests: upgrade to Pro (1,500 credits/mo, 50/day) or set up email filters to reduce noise before it reaches Unboxd
4. Notes that keyword/address blocking in Unboxd can prevent low-value emails from consuming credits
**Result**: Clear upgrade recommendation with workaround for staying on current plan
### Example 2: Comparing Unboxd vs Fyxer for a busy founder
**User says**: "I get 100+ emails a day and waste 2 hours reading them. Should I use Unboxd or Fyxer?"
**Skill does**:
1. Reads platform guide comparison section
2. Explains core difference: Unboxd extracts action items so you skip reading; Fyxer organizes inbox and drafts replies
3. Unboxd is better if: you mainly need to know what requires action, you want daily briefings, you use IMAP providers
4. Fyxer is better if: you need AI-drafted replies, you want meeting notes, you need HubSpot integration
5. Notes pricing: Unboxd Pro $12.50/mo (50 emails/day) vs Fyxer Starter $22.50/mo (unlimited emails)
6. For 100+ emails/day, user would need Unboxd Ultra ($41.67/mo) — at that price, Fyxer may be better value
**Result**: Nuanced comparison factoring in email volume and pricing
### Example 3: Setting up Unboxd with multiple email accounts
**User says**: "I want to connect my Gmail, Outlook, and Fastmail to Unboxd. How does that work?"
**Skill does**:
1. Reads platform guide for multi-account setup
2. Confirms Unboxd supports all three: Gmail via webhook, Outlook via webhook, Fastmail via IMAP
3. Notes IMAP (Fastmail) will poll periodically rather than real-time — expect delays
4. Checks plan: 3 accounts requires at least Pro ($12.50/mo, up to 4 accounts)
5. Explains daily credit limit is shared across all accounts — 50 emails/day total on Pro
**Result**: Setup guidance with provider-specific notes and plan requirement
## Troubleshooting
### Emails categorized into the wrong bucket
**Symptom**: Important client emails showing up in FYI instead of Action Items, or newsletters appearing as Highlights
**Cause**: Unboxd's AI categorization learns over time — early usage has lower accuracy, especially for ambiguous emails
**Solution**: Manually correct miscategorized emails consistently. Use keyword blocking to prevent known low-value senders from being processed. Check that the sender isn't in your block list if important emails aren't showing up at all. Give it 1-2 weeks of corrections before judging accuracy.
### Daily credit limit reached — important emails not processed
**Symptom**: Emails arriving after the daily cap go unprocessed until next day
**Cause**: Credit-based system processes emails in order received. On Plus plan (20/day), a busy morning can exhaust credits before afternoon emails arrive.
**Solution**: Upgrade plan (Pro = 50/day, Ultra = 200/dRelated 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.