sales-gmelius
Gmelius platform help — Gmail-native AI email collaboration with Meli AI assistant, shared inboxes, Kanban boards, automation rules, sequences, and team analytics ($19-$40/user/mo). Use when Gmelius is slow or lagging in Gmail with high email volume, shared inbox emails are not being assigned or automations are not triggering, comparing Gmelius to Hiver or Front for Gmail team collaboration, setting up Meli AI assistant for email drafting and sorting, building integrations with the Gmelius REST API or Zapier, or choosing between Meli/Growth/Pro plans. Do NOT use for comparing help desk platforms broadly (use /sales-helpdesk-selection). Do NOT use for non-Gmail shared inbox needs (use /sales-helpdesk-selection).
What this skill does
# Gmelius Platform Help
Helps with Gmelius — a Gmail-native platform where Meli AI and your team collaborate in real time to manage, prioritize, and reply to emails. Swiss-based, privacy-by-design.
## 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 Gmelius?**
- A) Set up shared inboxes for team email (support@, billing@)
- B) Configure Meli AI assistant for email drafting/sorting
- C) Build automation rules for routing and assignment
- D) Use Kanban boards for email project management
- E) Connect Gmelius to CRM or other tools via API/Zapier
- F) Fix performance or sync issues
- G) Compare Gmelius to Hiver or Front
- H) Something else — describe it
2. **Which plan are you on (or considering)?**
- A) Meli ($19/user/mo) — AI assistant, 5K conversations/mo, max 5 users
- B) Growth ($25/user/mo) — shared inboxes, automations, API, max 50 users
- C) Pro ($40/user/mo) — CRM integrations, webhooks, 100K conversations/mo
- D) Enterprise (custom) — unlimited, bespoke AI
- E) Free trial / not sure
3. **Team size?**
- A) Solo / 1-3 people
- B) 4-15 people
- C) 16-50 people
- D) 50+
**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... |
|---|---|
| Comparing help desk platforms broadly | `/sales-helpdesk-selection {question}` |
| Non-Gmail shared inbox (Outlook, standalone) | `/sales-helpdesk-selection {question}` |
| Connecting tools via Zapier/Make/API pipelines | `/sales-integration {question}` |
| Outbound email sequences strategy | `/sales-cadence {question}` |
| Customer feedback / CSAT strategy | `/sales-customer-feedback {question}` |
For Gmelius-specific questions, continue to Step 3.
## Step 3 — Gmelius platform reference
**Read `references/platform-guide.md`** for the full platform reference — capabilities, pricing, data model, API endpoints, integration recipes, and code examples.
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 **slow performance**: Reduce Chrome extensions, use a dedicated Chrome profile, refresh browser every 1-2 hours during peak. High-volume inboxes (500+ emails/day) are a known pain point.
- For **plan selection**: Meli ($19) for solo AI assistant. Growth ($25) for team shared inboxes and automations. Pro ($40) only if you need CRM integrations, webhooks, or 100K+ conversations.
- For **automation setup**: Start with simple rules (one condition → one action), then layer complexity. Test with broad conditions first, then narrow. All conditions must match for a rule to fire.
- For **API integration**: Growth plan minimum. OAuth 2.0 + PKCE auth. Start with board/conversation endpoints — lowest complexity.
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 pricing that may be outdated.*
- **Gmail-only.** No Outlook support (waitlisted). If any team member uses Outlook, Gmelius won't work — look at Front, Help Scout, or Freshdesk.
- **API requires Growth+ ($25/user/mo).** Meli plan has no API access. Webhooks require Pro ($40/user/mo).
- **Conversation bundling.** Emails with the same sender and subject bundle into one conversation — comments in the Gmelius pane won't be assigned to individual emails within the bundle.
- **Mobile app limitations.** Mobile experience is significantly more limited than desktop — no full automation management, limited Kanban functionality.
- **Meli plan caps at 5 users.** Growth caps at 50. If your team is larger, you need Pro or Enterprise.
- **Performance degrades at high volume.** G2 reviews report 10+ second email load times during peak periods. Browser-extension architecture means performance depends on Chrome resources.
## Related skills
- `/sales-hiver` — Hiver platform help (Gmail-native help desk, AI copilot, SLAs). Install:
`npx skills add sales-skills/sales --skill sales-hiver -a claude-code`
- `/sales-front` — Front platform help (AI-powered shared inbox, omnichannel, Autopilot/Copilot, REST API). Install:
`npx skills add sales-skills/sales --skill sales-front -a claude-code`
- `/sales-missive` — Missive platform help (collaborative team inbox, internal threads, co-drafting, multi-channel). Install:
`npx skills add sales-skills/sales --skill sales-missive -a claude-code`
- `/sales-helpdesk-selection` — Compare help desk platforms (Zendesk, Freshdesk, Intercom, Help Scout, and more). Install:
`npx skills add sales-skills/sales --skill sales-helpdesk-selection -a claude-code`
- `/sales-integration` — Connect tools via Zapier/Make/API pipelines
- `/sales-cadence` — Outbound email sequences strategy
- `/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: Setting up shared inbox with automations
**User says**: "We're a 12-person team on Google Workspace. We want to set up [email protected] as a shared inbox with auto-assignment and SLA tracking."
**Skill does**:
1. Reads platform guide for setup steps and plan requirements
2. Recommends Growth plan ($25/user/mo) — shared inboxes, automations, and SLAs included
3. Walks through: create shared inbox → invite agents → set up round-robin assignment → configure SLA rules with breach alerts
4. Notes collision detection prevents duplicate replies
5. Suggests starting with simple routing rules before building complex multi-step automations
**Result**: Step-by-step shared inbox setup with plan recommendation
### Example 2: Syncing Gmelius conversations to HubSpot via API
**User says**: "How do I automatically create HubSpot contacts when new conversations arrive in our Gmelius shared inbox?"
**Skill does**:
1. Reads platform guide for API endpoints and webhook events
2. Explains two paths: Zapier (Growth plan) or direct API + webhooks (Pro plan)
3. Provides Zapier recipe: Gmelius "New Conversation" trigger → HubSpot "Create Contact" action
4. For API path: set up webhook for conversation events → POST to HubSpot API
5. Notes that native HubSpot integration requires Pro plan ($40/user/mo)
**Result**: Working integration recipe with both Zapier and API approaches
### Example 3: Gmelius extremely slow loading emails
**User says**: "Gmelius takes 10+ seconds to load emails and our sidebar freezes during the morning rush."
**Skill does**:
1. Acknowledges this is a known issue — Gmelius runs as a Chrome extension, so performance depends on browser resources
2. Recommends: dedicated Chrome profile for email work, disable other extensions, clear browser cache
3. Suggests auto-assignment to distribute load so agents aren't all viewing the same queue
4. Notes periodic browser refreshes every 1-2 hours during peak help
5. If problem persists, recommends evaluating Hiver (also Gmail-native) or Front (standalone) for comparison
**Result**: Practical performance fixes with escalation path
## Troubleshooting
### Gmelius is extremely slow or laggy in Gmail
**Symptom**: Sidebar takes 10+ seconds to load, email interactions lag, browser becomes unresponsive with Gmelius active
**Cause**: Gmelius runs as a Gmail Chrome extension — performance depends on browser resources. High email volume (500+ emails/day) strains the extension.
**Solution**: 1) Use a dedicated Chrome profile with minimal extensions. 2) Clear browser cache weekly. 3) Refresh the Gmail tab every 1-2 hours during peak. 4) Check if other Chrome extensions conflict. 5) If persistent, contact Gmelius support — they may hRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".