sales-dume
Dume.ai platform help — chat-first AI executive assistant connecting Gmail, Calendar, Slack, Jira, Notion, GitHub and 50+ tools for email triage, no-code workflow automation, custom AI agents, and daily task management. Use when email triage or smart draft responses aren't working right, a no-code workflow isn't triggering, setting up webhook-based automations on the PRO plan, a tool integration keeps disconnecting or failing to sync, connecting an external MCP server for real-time data, building custom AI agents for specialized tasks, WhatsApp messages not sending or receiving, the morning briefing pulling the wrong calendar or email data, evaluating Dume.ai vs alfred_ vs Lindy vs Saner.AI as an AI executive assistant, or choosing the right Dume plan. Do NOT use for AI calendar auto-scheduling with project management (use /sales-motion), choosing a dedicated AI meeting note-taker (use /sales-note-taker), or general tool integration architecture (use /sales-integration).
What this skill does
# Dume.ai Platform Help ## Step 1 — Gather context If `references/learnings.md` exists, read it first for accumulated platform knowledge. Ask the user: 1. **What's your Dume.ai challenge?** - A) Setting up Dume for the first time (integrations, agents) - B) Email triage, drafting, or morning briefing issues - C) Building or debugging a no-code workflow - D) MCP server integration - E) WhatsApp or Chrome extension issues - F) Custom AI agent creation - G) Evaluating Dume.ai vs alternatives - H) Something else 2. **Which plan are you on?** - A) Free (1,200 credits/year, 20 msgs/day, 1 integration) - B) GO ($8-9/mo — 30K credits/year, unlimited messages) - C) PRO ($15-18/mo — webhooks, premium models) - D) MAX ($33-40/mo — unlimited agents, custom builds) 3. **What are you trying to accomplish?** (describe your specific goal) **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 calendar auto-scheduling with project management | `/sales-motion [question]` | | Choosing a dedicated AI meeting note-taker | `/sales-note-taker [question]` | | General tool integration patterns | `/sales-integration [question]` | | Everything else | Answer directly using Step 3 | When routing, provide the exact command. ## Step 3 — Dume.ai platform reference **Read `references/platform-guide.md`** for the full platform reference — capabilities, pricing, integrations, MCP setup, workflow builder, and workarounds for common issues. Answer the user's question using only the relevant section. Don't dump the full reference. ## Step 4 — Actionable guidance - For setup: start with one integration (Gmail or Calendar), verify it connects, then add more - For workflows: use the visual Workflow Studio — start with a pre-built template, then customize - For MCP: PRO+ plan required; use Composio.dev for managed MCP or bring your own HTTP-streamable/SSE server - For plan selection: Free is too limited for daily use (20 msgs/day, 1 integration); GO is the sweet spot; PRO only if you need webhooks or premium AI models; MAX for heavy agent/workflow usage - For WhatsApp: ensure v3.8+ — WhatsApp was added October 2025 If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there. ## Gotchas - **No public REST API.** Dume.ai has no documented API endpoints. The developer surface is limited to webhook triggers (PRO+) and consuming external MCP servers. You cannot programmatically read or write Dume data from external tools. - **Integration connectivity is flaky.** Multiple AppSumo reviewers report that saving to Excel, uploading to OneDrive, and sending to inbox all failed. If an integration breaks, disconnect and reconnect it in Settings. Test immediately after connecting. - **Email parsing misses in long threads.** AI responses "miss the mark" in longer conversation threads or edge-case scenarios. Keep prompts specific and reference the exact email/thread you need help with. - **Free plan is effectively a trial.** 20 messages/day and 1 integration make it impractical for any real workflow. Budget for GO ($8/mo) minimum. - **Webhook triggers require PRO plan.** Workflow trigger nodes using webhooks, schedules, or integration events are gated to PRO ($15-18/mo) and above. - **MCP integration consumes external servers, doesn't expose one.** Dume connects TO MCP servers for data — it does not act as an MCP server itself. You cannot use Claude Code or ChatGPT to control Dume via MCP. - **Still actively evolving.** Major releases every 2-4 weeks (v4.2 as of March 2026). Expect feature changes, new integrations, and occasional bugs with newer capabilities. ## Related skills - `/sales-alfred` — alfred_ platform help (AI exec assistant — simpler, single-tier $24.99/mo, strong email triage) - `/sales-saner` — Saner.AI platform help (ADHD-friendly AI assistant — notes + tasks + daily planning) - `/sales-simular` — Simular (Sai) platform help (autonomous desktop agent — controls apps via GUI) - `/sales-inbox-zero` — Inbox Zero open-source AI email assistant (auto-labeling, rules API/CLI, self-hostable, $18/mo or free) - `/sales-lindy` — Lindy platform help (no-code AI agent builder — 4,000+ integrations) - `/sales-superhuman` — Superhuman platform help (fastest AI email client — keyboard-driven) - `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. ## Examples ### Example 1: Setting up email triage and morning briefing **User says**: "I connected my Gmail but the morning briefing isn't showing my emails or calendar events." **Skill does**: 1. Reads platform-guide.md for email triage and briefing setup details 2. Checks if user is on GO+ plan (Free only allows 1 integration) 3. Walks through verifying Gmail OAuth permissions and calendar access 4. Explains that morning briefing requires both Gmail and Calendar connected — briefing fires at 8:00 AM 5. If connection fails: disconnect both, reconnect in Settings, test with a specific email query first **Result**: Working morning briefing with email summaries and calendar preview ### Example 2: Building a webhook-triggered workflow **User says**: "I want to trigger a Dume workflow when a new lead comes in from my website form." **Skill does**: 1. Confirms user is on PRO+ plan (webhook triggers are plan-gated) 2. Explains the Workflow Studio: create a new workflow, add a Trigger Node set to "Webhook" 3. Shows how to copy the generated webhook URL and configure it in the form tool 4. Adds processing nodes (e.g., create Jira task, send Slack notification, draft welcome email) 5. Notes: test the webhook with a manual POST before going live **Result**: End-to-end form submission → Dume workflow with task creation and notification ### Example 3: Evaluating Dume.ai vs alfred_ vs Lindy **User says**: "I'm a solopreneur. Should I use Dume, alfred_, or Lindy for managing my email and tasks?" **Skill does**: 1. Compares approaches: Dume is a workflow-first assistant (50+ tools, custom agents, workflow builder), alfred_ is an email-first assistant (autonomous triage + drafts, single focus), Lindy is an agent-first builder (modular AI agents, 4,000+ integrations) 2. Notes Dume's strengths: broadest integration set, MCP support, visual workflow builder, WhatsApp 3. Notes tradeoffs: Dume has no API (locked ecosystem), alfred_ is simpler but narrower, Lindy has more integrations but is agent-builder not assistant 4. Pricing: Dume GO $8/mo vs alfred_ $24.99/mo vs Lindy $49/mo 5. Recommends Dume if primary pain is multi-tool workflow automation; alfred_ if primary pain is email overload; Lindy if primary pain is building custom AI agents **Result**: Clear decision framework based on primary pain point ## Troubleshooting ### Integration keeps disconnecting **Cause**: OAuth token expiration or browser extension interference during reconnection **Solution**: Disconnect the integration in Settings, clear browser cache, reconnect in an incognito window with no extensions. Grant all requested OAuth permissions. If it still fails after 3 attempts, contact [email protected]. ### Workflow not triggering **Cause**: Trigger node misconfigured, or using webhook trigger on Free/GO plan (requires PRO) **Solution**: Verify your plan supports the trigger type. For webhook triggers, test with a manual cURL POST to the webhook URL. For schedule triggers, check timezone settings. For integration triggers, verify the source integration is connected and active. ### Chat gives error messages **Cause**: Credit exhaustion, model unavailability, or rate limiting **Solution**: Check remaining credits in Settings. If credits are depleted, upgrade plan or wait for monthly reset. Try switching to a different AI model (Settings > AI Model). If errors persist across models, this is likely a service-side issue — wai
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.