sales-jamie
Jamie platform help — bot-free AI meeting note-taker, REST API with personal and workspace keys, webhook automations, CRM sync to HubSpot/Salesforce/Attio, MCP server for Claude/ChatGPT/Cursor. Use when setting up Jamie for a sales team, connecting Jamie webhooks to Make.com or a custom endpoint, pulling meeting transcripts and summaries via Jamie API, syncing Jamie action items to Asana or CRM, troubleshooting Jamie not recording or missing speakers, comparing Jamie pricing tiers, or configuring Jamie speaker recognition. Do NOT use for choosing between note-takers (use /sales-note-taker) or reviewing a specific call for coaching (use /sales-call-review).
What this skill does
# Jamie Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
1. **What do you need help with?**
- A) Initial setup — installing the app, connecting calendar, first recording
- B) API integration — pulling transcripts/summaries programmatically
- C) Webhook setup — automating workflows when meetings complete
- D) CRM sync — connecting HubSpot, Salesforce, or Attio
- E) Notes sync — Notion, Google Docs, or OneNote
- F) Speaker recognition or custom terminology
- G) Pricing / plan selection
- H) Troubleshooting — recording not working, missing content, sync issues
2. **Which plan are you on?**
- A) Free (10 meetings/mo, 30 min limit)
- B) Plus (20 meetings/mo, 2 hr limit)
- C) Pro (unlimited meetings, 3 hr limit)
- D) Team (Pro features + centralized billing)
- E) Enterprise (SSO, admin controls, EU residency)
- F) Not sure / evaluating
Skip-ahead rule: if the user's prompt already contains enough context, skip to Step 2.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Choosing between note-takers (Jamie vs Fireflies vs Fathom etc.) | `/sales-note-taker {user's question}` |
| Reviewing a specific sales call for coaching | `/sales-call-review {user's question}` |
| Building a coaching program | `/sales-coaching {user's question}` |
| General CRM/tool integration patterns (Zapier, iPaaS) | `/sales-integration {user's question}` |
| HubSpot platform config (beyond Jamie sync) | `/sales-hubspot {user's question}` |
| Salesforce platform config (beyond Jamie sync) | `/sales-salesforce {user's question}` |
Otherwise, answer directly below.
## Step 3 — Jamie platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing, API endpoints, webhook setup, integrations, data model.
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.
- **API vs webhooks**: Use webhooks (`meeting.completed`) for real-time pipelines; use REST API for batch queries and search. Combine both for production: webhook for push + nightly reconcile poll.
- **Personal vs workspace keys**: Personal keys see only your meetings + shared ones. Workspace keys (admin-created) see all workspace meetings — use for team-wide dashboards or CRM sync.
- **Plan gating**: API/webhooks require Pro+. CRM sync (HubSpot/Salesforce/Attio) requires Pro+. Free and Plus are personal-use only.
- **MCP**: Community-built `vicampuzano-jamie-mcp` connects Jamie to Claude/ChatGPT/Cursor — requires Pro+ and `JAMIE_API_KEY` env var.
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 integration gotchas that may be outdated.*
- **Processing delays.** Summaries can take 5-10 minutes even for short meetings. Users report summaries getting stuck in "processing" — if this happens, check for app updates or restart Jamie.
- **Lost/failed recordings.** Multiple users report entire meetings lost, especially during app upgrades. Never update Jamie mid-meeting. For high-stakes calls, keep a backup recorder.
- **Speaker identification is inconsistent.** Mislabeling, duplicating, and phantom speaker tags are common. In large meetings (7-8+ people), entire participants may be left out. Manually correct speakers in early meetings to train speaker memory.
- **No video recording.** Audio only. If you need to review slide shares or demos, pair with a screen recorder or choose a video-capable note-taker.
- **No Android app.** Desktop (Mac/Windows) and iOS only.
- **Free tier is very limited.** 10 meetings/month with a 30-minute cap. Most competitors offer more generous free tiers (Fathom: unlimited free recordings).
- **No native Zapier integration.** Automation goes through Make.com or custom webhooks.
- **CRM sync is Pro+ only.** Free and Plus plans can't push notes to HubSpot/Salesforce/Attio.
- **Webhook endpoint URL can't be updated.** Delete and recreate if the URL changes. Events are also immutable after creation.
- **Audio deleted after transcription.** You can't re-listen to or re-process a meeting.
## Related skills
- `/sales-note-taker` — Compare note-takers, plan API integration architecture, normalize transcript formats across vendors
- `/sales-call-review` — Review a specific call for coaching
- `/sales-coaching` — Build coaching programs that consume call data
- `/sales-integration` — General CRM/tool integration patterns (Zapier, Make, webhooks, iPaaS)
- `/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: Setting up Jamie webhooks with Make.com
**User says**: "I want Jamie to automatically create a Notion page for every meeting."
**Skill does**:
1. Confirms user is on Plus+ plan (webhooks require it)
2. Walks through: Jamie Settings → Integrations → Webhooks → Create Webhook → paste Make.com webhook URL
3. Notes to select `meeting.completed` event and API Key auth with `x-make-apikey` header
4. Shows Make.com scenario: webhook trigger → parse JSON → create Notion page with summary + action items
**Result**: Automated Notion pages for every completed meeting.
### Example 2: Building a transcript pipeline via Jamie API
**User says**: "I need to pull all meeting transcripts from Jamie into our data warehouse nightly."
**Skill does**:
1. Recommends workspace API key (admin-created, sees all workspace meetings)
2. Shows: `GET /v1/workspace/meetings` with date filters → paginate → for each meeting fetch transcript (Markdown format)
3. Flags 100 req/min rate limit — add throttling for large workspaces
4. Suggests hybrid: webhook for real-time + nightly batch to catch gaps
**Result**: Production-ready architecture for transcript ingestion.
### Example 3: Jamie not picking up speakers correctly
**User says**: "Jamie keeps labeling my colleague as 'Speaker 2' instead of their name."
**Skill does**:
1. Explains speaker memory: Jamie learns speakers over time from repeated meetings
2. Walks through: manually label speakers in the first few meetings → Jamie's speaker memory learns the voice
3. Notes custom words feature for proper nouns and company-specific terminology
4. Flags: bot-free recording relies on device microphone quality — if remote participants are quiet, diarization suffers
**Result**: Clear steps to improve speaker identification accuracy.
## Troubleshooting
### Meeting summary stuck in processing or lost entirely
**Symptom**: Meeting ends but summary never appears, stays in "processing" indefinitely, or disappears
**Cause**: App update during recording, network interruption, or processing pipeline failure. Users report ~80% reliability — critical meetings can be missed.
**Solution**: Never update Jamie during an active meeting. If stuck: restart the Jamie app, check for pending updates, and verify internet connectivity. For high-stakes meetings, run a backup recorder (screen recording or a second tool). If a summary is lost, there's no recovery — Jamie deletes audio after transcription.
### Speaker mislabeled or missing in large meetings
**Symptom**: Speakers labeled as "Speaker 2" instead of names, phantom speaker tags appear, or participants entirely missing from transcript (common in 7-8+ person meetings)
**Cause**: Bot-free recording relies on device microphone quality. Remote participants with poor audio, crosstalk, or similar voices cause diarization failures. Speaker memory needs multiple meetings to learn voices.
**Solution**: Manually correct speaker labels in the first 3-5 meetings with each person to train speaker memory. Use custom worRelated 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.