sales-integration
Connects sales tools with webhooks, Zapier/Make, native integrations, and custom API pipelines — CRM sync, event triggers, data mapping, and error handling. Use when CRM data isn't syncing from Mailshake/Apollo/Salesloft, webhook events aren't firing or arriving malformed, Zapier/Make automations are failing or skipping records, data is duplicating or missing between tools, or an integration that was working suddenly breaks. Do NOT use for Qwilr-specific automations (use /sales-qwilr-automation), general CRM platform config (use /sales-apollo or /sales-salesloft), or marketing automation flows (use /email-sequence).
What this skill does
# Connect Sales Tools Help the user design and implement integrations between sales tools — from choosing the right integration method through trigger/action design, field mapping, and error handling. This skill covers webhooks, Zapier/Make, native integrations, and custom API pipelines. ## Step 1 — Gather context If `references/learnings.md` exists, read it first for accumulated knowledge. Ask the user: 1. **What are you connecting?** - Source tool (where the event happens): Mailshake, Apollo, Salesloft, Smartlead, Lemlist, Yesware, Groove.cm, Mixmax, Reply.io, Woodpecker, Hunter.io, Seismic, Tomba, Prospeo, Seamless.AI, SafetyMails, Closum, Omnisend, Mailchimp, SendGrid, Postmark, Customer.io, Mailgun, Klaviyo, ActiveCampaign, Outscraper, Enrich.so, Minelead, Lobstr.io, GetProspect, Skrapp, OpenWeb Ninja, Anymail Finder, ZeroBounce, Snov.io, LeadMagic, ZoomInfo, Clearbit, RB2B, 6sense, Brevo, Braze, Iterable, GetResponse, SendPulse, Clay, HubSpot, Salesforce, Qwilr, RudderStack, Boomi, Workato, Celigo, SnapLogic, Jitterbit, Tray, Informatica, TIBCO, other - Destination tool (where the action should happen): Salesforce, HubSpot, Slack, Pipedrive, other - Is this one-way or bidirectional? 2. **What should trigger the integration?** - A) Email reply received - B) New lead captured - C) Meeting booked - D) Deal stage changed - E) Contact created/updated - F) Sequence/cadence completed - G) Form submission - H) Custom event — describe it 3. **What should happen when triggered?** - A) Create a record (contact, task, deal, activity) - B) Update a record (field change, stage change, owner change) - C) Send a notification (Slack, email, SMS) - D) Enroll in a sequence/cadence - E) Multiple actions — describe 4. **What's your technical comfort level?** - A) No-code — Zapier, Make, native integrations only - B) Low-code — comfortable with basic API calls, can follow docs - C) Code — can build custom integrations with API + webhooks 5. **What's your current stack?** (list all sales/marketing/CRM tools in use) **If the user's request already provides most of this context, skip directly to the relevant step.** Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask only the most critical 1-2 clarifying questions at the end — don't gate your response behind gathering complete context. ## Step 2 — Integration architecture Choose the right integration method based on complexity and technical requirements. ### Decision matrix | Method | Best for | Technical skill | Cost | Reliability | |--------|----------|----------------|------|-------------| | **Native integration** | CRM sync, built-in connectors | None | Free (included) | High | | **Zapier / Make** | Multi-step workflows, no-code | Low | $20-100/mo | High | | **Webhooks + handler** | Real-time events, custom logic | Medium | Free-low | Medium-high | | **Custom API pipeline** | Complex transformations, high volume | High | Varies | Depends on implementation | ### Native integrations — always check first Before building anything custom, check if a native integration exists: For a complete lookup table of 240+ native integrations across all supported tools, see `references/integrations.md`. **Rule**: If a native integration covers your use case, use it. Native integrations handle auth, retry, and error handling automatically. Only go custom when native doesn't support your specific trigger or action. ## Step 3 — Common integration patterns ### Lead/reply → CRM record + notification **Trigger**: Reply received in Mailshake/Apollo/Salesloft **Actions**: 1. Create or update contact in CRM 2. Create activity/task on the contact record 3. Send Slack notification to rep **Implementation options**: - Zapier: Trigger = Mailshake "Reply Received" → Actions = Salesforce "Create Task" + Slack "Send Message" - Webhook: Mailshake push event (Reply) → your endpoint → Salesforce API + Slack API - Native: Mailshake-Salesforce integration (auto-syncs replies as activities) ### Meeting booked → CRM + sequence exit **Trigger**: Meeting booked (Calendly, Chili Piper, or CRM scheduler) **Actions**: 1. Update contact status/stage in CRM 2. Remove from active sequence/cadence 3. Create deal/opportunity 4. Notify AE ### CRM status change → sequence enrollment **Trigger**: Lead status changes to "MQL" in CRM **Actions**: 1. Enroll contact in outbound sequence (Apollo, Salesloft, Mailshake) 2. Assign to appropriate rep based on routing rules **Implementation options**: - **Zapier/Make (no-code)**: HubSpot "Lifecycle Stage Change" trigger → Apollo "Add Contact to Sequence" action. Easiest setup, handles auth automatically. - **CRM webhook + custom API (low-code)**: HubSpot workflow triggers webhook → your endpoint calls Apollo `POST /contacts/add_to_emailer_campaign`. More control over field mapping, error handling, and conditional logic. - **Native CRM workflow (if supported)**: Some CRM-to-engagement-tool integrations support enrollment triggers natively — check Settings > Integrations before building custom. **Error handling for sequence enrollment**: - **Duplicate contact**: Check if contact already exists in the engagement tool before creating — use "Find or Create" logic - **Already enrolled**: The API may reject enrollment if the contact is active in another sequence — handle gracefully (log, skip, or queue for later) - **Sequence capacity / enrollment limits**: Sequences may have max enrollment caps or daily add limits. Monitor the API response for limit errors and implement a retry queue for overflow. - **Re-qualification**: If a lead was previously disqualified and re-enters MQL, decide whether to re-enroll or skip (prevent spamming the same contact) ### Deal stage change → stakeholder notification **Trigger**: Deal moves to "Proposal Sent" or "Negotiation" in CRM **Actions**: 1. Notify relevant stakeholders in Slack 2. Create follow-up task for rep 3. Trigger proposal creation in Qwilr (see `/sales-qwilr-automation`) ### Multi-tool activity sync **Trigger**: Any activity logged in engagement tool (email sent, call made, meeting held) **Action**: Sync activity to CRM as a completed task/activity **Key considerations**: - Define sync direction (one-way vs bidirectional) - Map fields between tools (Salesloft "Call" → Salesforce "Task" with type "Call") - Handle duplicates (check if activity already exists before creating) ## Step 4 — Platform webhook reference For platform-specific webhook configs, API integrations, and native connector details, see `references/platforms.md`. ## Step 5 — Data sync best practices ### Define source of truth Before building any bidirectional sync, decide which tool is the source of truth for each field: | Data type | Typical source of truth | Why | |-----------|------------------------|-----| | Contact info (name, email, phone) | CRM (Salesforce/HubSpot) | CRM is the canonical record | | Activity data (emails, calls) | Engagement tool (Apollo/Salesloft/Mailshake) | Activity originates in the engagement tool | | Deal/opportunity | CRM | Revenue data lives in CRM | | Lead score | MAP or CRM | Scoring logic runs in MAP/CRM | | Sequence status | Engagement tool | Sequence state managed by engagement tool | ### Conflict resolution - **Last-write-wins**: Simple but dangerous — later update overwrites earlier one - **Source-of-truth wins**: Designated source always overwrites destination - **Field-level rules**: Different rules per field (e.g., CRM wins for phone, engagement tool wins for email status) - **Manual review**: Flag conflicts for human review (safest for critical fields) ### Deduplication - **Match keys**: Email address (primary), company domain + name (secondary) - **When to dedup**: Before creating records, during sync, and periodically as maintenance - **Tools**: Native CRM dedup (Salesforce Duplicate Rules, HubSpot dedup tool), or third-party (Dedupely, RingLe
Related 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.