sales-note-taker
Sales meeting note-taker and conversation-intelligence strategy — platform selection across 150+ tools (Fathom, Fireflies, Gong, Otter, Avoma, Grain, tl;dv, Read.ai, MeetGeek, Granola, Krisp, Circleback, Plaud, and the full long tail in references/platforms.md) plus backend API integration for auto-downloading transcripts into CRM, data warehouse, or Slack. Use when choosing an AI note-taker (pricing, features, compliance), deciding between webhook and polling, wiring transcripts into HubSpot or Salesforce, building a call-intelligence data pipeline, normalizing transcript formats, choosing a batch transcription service, a hardware AI voice recorder for in-person meetings, a bot-free / local-first / GDPR-hosted recorder, a real-time playbook-adherence tool, a meeting translation (RSI) platform, or a voice-note-to-text app, or debugging note-taker API rate limits and auth flows. Do NOT use for reviewing a single call for coaching (use /sales-call-review) or building a coaching program (use /sales-coaching).
What this skill does
# Sales Note-Taker & Conversation-Intelligence Strategy
Help the user (a) pick the right AI meeting note-taker for their sales team, and/or (b) wire its API into downstream systems (CRM, warehouse, Slack, internal tools). This skill is tool-agnostic — it references specific platforms for selection and integration patterns but focuses on cross-vendor strategy.
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated knowledge.
Ask the user:
1. **What's your primary goal?**
- A) Pick a note-taker for my team (selection/comparison)
- B) Integrate an existing note-taker's API (transcripts → somewhere)
- C) Both — evaluating a platform AND planning the integration
- D) Debugging a specific API/webhook issue
2. **What's your use case?**
- A) Sales org — discovery/demo calls, pipeline intelligence, coaching
- B) Customer success — onboarding, QBRs, renewal health
- C) Cross-functional — sales + CS + internal meetings
- D) Specific workflow — e.g., auto-log transcripts to HubSpot, push action items to Slack, pipe everything to Snowflake
3. **If integrating, where are transcripts going?**
- A) CRM (HubSpot, Salesforce, Attio, Pipedrive)
- B) Data warehouse (Snowflake, BigQuery, Redshift, Databricks)
- C) Internal app / database
- D) Slack / notifications only
- E) Multiple destinations (fan-out)
4. **Scale?**
- A) <50 meetings/week (single team)
- B) 50-500/week (mid-market sales org)
- C) 500+/week (enterprise, multi-team)
Skip-ahead rule: if the user's prompt already has enough context, skip to Step 2.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Reviewing a specific call for coaching or scoring | `/sales-call-review {user's question}` |
| Building a coaching program or training cadence | `/sales-coaching {user's question}` |
| General CRM-to-tool integration patterns (Zapier, webhooks, iPaaS) | `/sales-integration {user's question}` |
| Salesloft Conversations config | `/sales-salesloft {user's question}` |
| ZoomInfo Chorus config | `/sales-zoominfo {user's question}` |
| Seismic Meeting Intelligence config | `/sales-seismic {user's question}` |
| Meeting scheduling (not note-taking) | `/sales-meeting-scheduler {user's question}` |
Otherwise, answer directly below.
## Step 3 — Platform reference
**Start with `references/platforms.md`** for the quick comparison table across all platforms.
Then read the detailed file matching the user's segment:
| Segment | File | When to read |
|---|---|---|
| SMB / budget | `references/platforms-smb.md` | Budget < $50/user/mo, small teams, free-tier shoppers |
| Mid-market / sales | `references/platforms-midmarket.md` | Sales-focused teams, methodology scorecards, coaching, CRM enrichment |
| Enterprise / revenue | `references/platforms-enterprise.md` | $1K+/user/yr budget, revenue intelligence, bolt-on CI |
| Field / in-person | `references/platforms-field.md` | In-person sales, field reps, mobile recording |
For comparison questions spanning segments (e.g., "Fathom vs Gong"), read both relevant files.
Answer using only the relevant section(s) — don't dump the full reference.
## Step 4 — Actionable guidance
You no longer need the platform reference — focus on the user's specific situation.
### Selection framework (if goal = selection)
Rank these in order for the user's context:
1. **Budget per seat** — Tactiq (free tier + $8-$12/mo) < Fathom (free tier + $16-$20/mo) < MeetGeek (free tier + $9.99-$17) < Fireflies ($10-$19) < Otter ($17-$30) < tl;dv (free tier + $18-$98/mo) < Avoma ($19-$79) < Claap ($24-$48/user/mo) < Gong ($1,200-$1,600/user/yr). Free tier only exists on Fathom, Fireflies, Otter, Read.ai, MeetGeek, tl;dv, Claap (very limited), Tactiq (very limited — 10 transcripts/mo).
2. **CRM depth** — Gong and Avoma have the deepest native CRM field-mapping and deal intelligence; Fathom Business, Fireflies Business, Fellow Business ($15/seat, HubSpot/Salesforce) are solid; Otter is thinnest.
3. **Coaching/QA features** — Gong > Avoma > tl;dv Business (MEDDIC/BANT/SPIN playbooks, aggregated insights) > Salesloft Conversations / Chorus > Fathom/Fireflies (basic scorecards only).
4. **API completeness** — Gong (richest, webhooks + REST) > Fireflies (GraphQL + webhooks) > Avoma (REST + webhooks) > Fathom (REST + webhooks) > Wave (REST + webhooks + MCP + semantic search, 60/min + 1K/day) > MeetGeek (REST + webhooks + MCP, all plans) > Jamie (REST + webhooks + MCP, Pro+) > Grain (REST, Business+) > Sembly (webhooks-first) > Read.ai (REST beta + MCP + webhooks) > tl;dv (REST v1alpha1 + webhooks + MCP, Pro+) > Granola (REST read-only + MCP beta, Business+, 5 req/sec, no webhooks) > Jamy (REST partial, 2 endpoints + webhooks). Otter is Enterprise-only API (beta).
5. **Compliance** — Gong, Avoma, Fireflies Business, Fathom Business all have SOC 2 + GDPR. For HIPAA/regulated industries, short-list drops to Gong, Avoma, Fireflies Enterprise.
**Quick picks:**
- Solo rep / tiny team on a budget → Fathom free tier
- SMB sales team, HubSpot/Salesforce-centric → Fathom Business or Fireflies Business
- Mid-market sales org wanting methodology + coaching → Avoma
- Enterprise revenue intelligence, high budget → Gong
- Enterprise CI + forecasting in one platform, Clari Core user → Clari Copilot ($60-110/user/mo)
- Non-sales general meeting transcription → Otter or Fellow
- Mid-market team wanting CRM auto-enrichment + deal scoring without Gong prices, especially in the lemlist ecosystem → Claap
- Mid-size team wanting customizable templates + analytics + affordable CRM sync → MeetGeek
- GTM team wanting shareable call clips + MCP AI workflows → Grain
- Real-time AI coaching during calls + cross-session intelligence + Apple Watch → Hedy
- Privacy-first EU team, in-person meetings, or bot-free non-negotiable → Jamie
- Noisy environments where call quality is the primary pain + AI notes as a bonus → Krisp
- Pure noise cancellation only (no notes/transcription), contact center, or SDK embedding → IRIS Clarity
- Real-time live transcription during calls + Sales Copilot with cue cards and objection handling → Colibri
- Real-time AI coaching overlay with knowledge base RAG and pre-call briefs → Cluely
- Multilingual team needing real-time translation in 100+ languages + cross-language search → Jamy
- In-person meetings, phone calls, cross-device recording, semantic search across history → Wave
- Free unlimited recordings + sales coaching with playbook monitoring (MEDDIC/BANT/SPIN) → tl;dv
- Zero-setup Chrome extension, bot-free, Google Meet-first, no API needed → Tactiq
- Bot-free AI notepad for VCs/product teams, privacy-sensitive contexts, HubSpot CRM → Granola
- Open-source wearable for all-day in-person capture, developer extensibility, lowest price ($89) → Omi
- Bot-free video recording with screen capture, Chrome-first teams, CRM auto-sync on Business plan → Bluedot
- Multilingual global team needing 58-language transcription + cross-meeting AI intelligence (Notta Brain) → Notta
- All-in-one AI assistant that handles email + meetings + calendar + custom workflows in a single tool → Lindy
- Individual professional recording in-person meetings on iPhone, Notion-centric workflow, ultra-low budget ($60/yr) → Speakwise
- Open-source self-hosted meeting recorder, 100% local processing, HIPAA/GDPR by architecture, developer extensibility → Meetily
- Open-source bot-free AI notepad with markdown output, 10 STT providers, plugin SDK, local-first with optional cloud → Char
- Open-source AI dictation with context-aware formatting, Whisper local STT, push-to-talk, free MIT license → Amical
- Open-source cross-platform STT with Whisper + Parakeet dual-engine, push-to-talk, 20k+ stars, free → Handy
- Polished hardware wearable for in-person meetings + phone calls (VCS), 112 languages, SOC 2/HIPAA, 1.5M+ users → Plaud
- EU privacy-first with open-source/EU-only AI models, post-quantum encryption, DicteBOX on-prRelated 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.