sales-fellow
Fellow platform help — AI meeting assistant with REST API for transcripts, agendas, action items, and meeting metadata. Use when Fellow AI notes missing action items or creating false ones, bot-free recording not notifying external participants, transcript export hard to find, CRM sync not pushing notes to HubSpot or Salesforce, Zapier triggers requiring manual kickoff, picking between Fellow Free vs Team vs Business vs Enterprise, enabling the Developer API in workspace settings, or building a Fellow transcript pipeline. Do NOT use for selecting between Fellow and competitors like Fathom/Fireflies/Gong (use /sales-note-taker) or reviewing specific call recordings (use /sales-call-review).
What this skill does
# Fellow Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated Fellow knowledge.
1. **What are you trying to do?**
- A) Configure Fellow workspace/plan or understand pricing tiers
- B) Build a backend integration (REST API, webhooks, Zapier)
- C) Troubleshoot AI notes, action items, or transcript issues
- D) Set up CRM sync (HubSpot/Salesforce) or project management integrations
- E) Troubleshoot bot-based or bot-free recording
- F) Evaluate Fellow vs alternatives — **route to `/sales-note-taker`**
2. **Which Fellow plan?**
- A) Free (5 AI notes + 5 AI recordings lifetime)
- B) Team ($7/user/mo annual) — 10 AI notes/recordings per user/month, API access
- C) Business ($15/user/mo annual) — unlimited AI, CRM sync, keyword tracking
- D) Enterprise ($25/user/mo annual) — analytics, redaction, provisioning
3. **If integrating, what's the destination?**
- A) CRM (HubSpot, Salesforce)
- B) Project management (Jira, Asana, Linear, Monday, Notion, Confluence)
- C) Data warehouse or internal system (via API)
- D) Slack / notifications
- E) Zapier / n8n automation
Skip-ahead rule: if the user's prompt already has enough context, skip to Step 2.
## Step 2 — Route or answer directly
| User situation | Route to |
|---|---|
| "Fellow vs Fathom vs Fireflies — which should we pick" | `/sales-note-taker {question}` |
| "Review this Fellow recording and score it" | `/sales-call-review {question}` |
| "Build a coaching program using Fellow recordings" | `/sales-coaching {question}` |
| "Generic Zapier/Make/n8n workflow patterns" | `/sales-integration {question}` |
| Anything Fellow-platform-specific (API, pricing, CRM sync, bot behavior, templates) | Stay here |
When routing, use the exact command: `/sales-{skill} {user's original question}`.
## Step 3 — Fellow platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing tiers, integrations, plan-gated features, recording modes, template system.
**Read `references/fellow-api-reference.md`** for API docs — authentication, endpoints, audit logging, security model.
Answer using only the relevant section. Don't dump the entire reference.
## Step 4 — Actionable guidance
Once you have the relevant reference content:
1. **For API questions** — note that API requires Team+ plan, admin must enable in Workspace Settings > Security, each user creates their own key in User Settings > Developer Tools. Keys are user-scoped (same access as in-app).
2. **For CRM sync** — requires Business+ plan. Fellow auto-suggests CRM fields from meeting context. Native HubSpot/Salesforce sync; other CRMs via Zapier.
3. **For recording mode questions** — Fellow supports both bot-based (structured meetings, video playback) and bot-free (external calls, ad-hoc, in-person). Bot-free requires desktop app install. Bot-free has NO automated disclosure for external participants.
4. **For template questions** — 500+ templates exist but discovery is poor. Recommend pinning 3-5 org-wide templates (Business+) rather than browsing the full library.
If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there with today's date.
## Gotchas
> *Best-effort from research — review these, especially items about plan-gated features and integration gotchas that may be outdated.*
- **Free plan is extremely limited.** 5 AI notes + 5 AI recordings for the lifetime of the account — not per month. Effectively a trial, not a usable free tier.
- **Bot-free recording has no automated participant disclosure.** Unlike bot-based mode (where the bot's presence signals recording), bot-free gives no notification to external participants — potential liability in two-party consent jurisdictions.
- **Zapier triggers often require manual kickoff.** The integration doesn't auto-trigger for all events — some Zaps need a manual push. Options are limited compared to native API.
- **CRM sync is Business+ only ($15/user/mo).** HubSpot and Salesforce native sync. AI-powered CRM field updates are Enterprise-only ($25/user/mo).
- **API keys are user-scoped.** Each key only accesses data the user can see in Fellow's UI. No workspace-wide admin key. For team-wide pipelines, each user must create their own key.
- **Transcript export is buried.** AI notes and agenda export are in the meeting view, but raw transcript export is in a separate menu. Not obvious on first use.
- **AI action items miss or hallucinate.** Multiple reviewers report the AI creates false action items from questions or discussion points, and misses actual commitments. Review AI-generated items before sharing.
## Related skills
- `/sales-note-taker` — Picking a note-taker (Fathom vs Fireflies vs Avoma vs Gong vs Otter vs Fellow vs Grain vs Sembly vs Read.ai) and cross-vendor integration patterns
- `/sales-call-review` — Review a specific Fellow recording and score against MEDDPICC/SPIN/Challenger
- `/sales-coaching` — Use Fellow recordings in coaching programs
- `/sales-integration` — Zapier/Make/n8n workflows to move Fellow data to other tools
- `/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 -y`
## Examples
### Example 1: CRM sync not working
**User says**: "I set up Fellow but meeting notes aren't pushing to our HubSpot — what's wrong?"
**Skill does**:
1. Confirms the user is on Business+ plan (CRM sync is plan-gated)
2. Checks if HubSpot integration is connected in Fellow workspace settings
3. Walks through the auto-suggest flow — Fellow identifies deal updates, contact notes, next steps and suggests CRM fields
4. Notes that AI-powered CRM field updates (auto-fill without review) require Enterprise tier
**Result**: Identifies the plan gate or configuration gap preventing sync.
### Example 2: Building a transcript pipeline via API
**User says**: "I want to pull all Fellow transcripts into our data warehouse automatically"
**Skill does**:
1. Confirms Team+ plan (API access required) and admin has enabled Developer API
2. Walks through key creation in User Settings > Developer Tools
3. Recommends Zapier triggers for agendas/AI notes/transcripts as the simplest path (Business+)
4. For custom builds, points to REST endpoints at developers.fellow.ai — JSON responses with transcript text, speaker timestamps, agendas, metadata
5. Flags user-scoped keys — for team-wide ingestion, each user needs their own key
**Result**: Clear path from plan check to working pipeline architecture.
### Example 3: Bot keeps joining external calls
**User says**: "Fellow's bot is joining calls with prospects and it's awkward — can I stop it?"
**Skill does**:
1. Explains bot-based vs bot-free recording modes
2. Recommends bot-free for external/prospect calls — records locally without a visible bot
3. Warns that bot-free requires desktop app install and has no automated disclosure
4. Suggests setting bot-based for internal meetings only, bot-free for external
**Result**: Recording mode configured per call type with compliance awareness.
## Troubleshooting
### AI action items are wrong or missing
**Symptom**: Fellow generates action items that weren't discussed, or misses actual commitments
**Cause**: The AI infers action items from conversation patterns — questions and hypotheticals can be misinterpreted as commitments
**Solution**: Review AI-generated items before sharing. Edit or delete false ones. For critical meetings, supplement with manual action items in the agenda. The Business+ plan's structured templates help anchor the AI to actual agenda items.
### Can't find transcript export
**Symptom**: AI notes and agenda export fine, but can't find the raw transcript
**Cause**: Transcript export is in a different menu than AI notes export
**Solution**: From the meeting view, look for a separate transcript tab/secRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.