sales-tray
Tray.ai platform help — enterprise iPaaS with 700+ connectors, Intelligent iPaaS, Enterprise Core governance, Merlin Agent Builder for AI agents, Tray Embedded for SaaS vendors, GraphQL API, Connector Development Kit. Use when Tray bill keeps climbing and task consumption is unpredictable, workflows fail with unclear errors and debugging feels opaque, evaluating Tray vs Workato vs MuleSoft vs Boomi, embedding integrations into a SaaS product via Tray Embedded, building Merlin AI agents, or configuring the GraphQL Embedded API and solution instances. Do NOT use for simple Zapier/Make automations (use /sales-integration), Workato-specific questions (use /sales-workato), or MuleSoft-specific questions (use /sales-mulesoft).
What this skill does
# Tray.ai Platform Help
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated platform knowledge.
Ask the user:
1. **What do you need help with?**
- A) Workflow building — connectors, triggers, steps, data mapping
- B) Merlin Agent Builder — AI agents, knowledge, tools, MCP
- C) Tray Embedded — embedding integrations in your SaaS product (Solutions, Solution Instances, Configuration Wizard)
- D) API Management — rate limiting, throttling, governance
- E) Connector Development Kit (CDK) — building custom connectors
- F) GraphQL API — Embedded API, Master/User tokens, mutations
- G) Deployment / environments / governance — Enterprise Core, SSO, audit logging
- H) Monitoring / troubleshooting — workflow errors, debugging, rate limits
- I) Pricing / licensing — task consumption, editions, cost optimization
- J) Evaluating Tray vs other iPaaS platforms
- K) Something else — describe it
2. **What edition are you on?**
- A) Pro
- B) Team
- C) Enterprise
- D) Tray Embedded (separate SKU)
- E) Not sure / evaluating
3. **What's your role?**
- A) Integration engineer (builds workflows)
- B) SaaS product team (embedding Tray in your app)
- C) Admin / architect (governance, security, deployment)
- D) AI/automation builder (Merlin agents)
- E) Evaluating Tray
**Skip-ahead rule**: if the user's prompt already provides enough context, skip to Step 2. Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask 1-2 critical clarifying questions.
## Step 2 — Route or answer directly
| Problem domain | Route to |
|---|---|
| Connecting Tray to Salesforce/HubSpot/CRM | `/sales-integration {question}` |
| CRM comparison — Salesforce vs HubSpot vs others | `/sales-crm-selection {question}` |
| Salesforce-specific config (Flows, Apex, SOQL) | `/sales-salesforce {question}` |
| Simple no-code Zapier/Make automations | `/sales-integration {question}` |
| Workato-specific questions | `/sales-workato {question}` |
| MuleSoft-specific questions | `/sales-mulesoft {question}` |
| Boomi-specific questions | `/sales-boomi {question}` |
| SnapLogic-specific questions | `/sales-snaplogic {question}` |
| Celigo-specific questions | `/sales-celigo {question}` |
| Jitterbit-specific questions | `/sales-jitterbit {question}` |
| CRM data quality / deduplication | `/sales-data-hygiene {question}` |
| Workflow design and task optimization | Answer directly — read platform guide |
| Tray Embedded integration | Answer directly — read platform guide |
| Merlin Agent Builder | Answer directly — read platform guide |
| GraphQL API / solution instances | Answer directly — read API reference |
| Pricing and cost optimization | Answer directly — read platform guide |
When routing, provide the exact command.
## Step 3 — Tray platform reference
**Read `references/platform-guide.md`** for the full platform reference — modules, pricing, connectors, Merlin agents, Tray Embedded, rate limits, governance.
Answer the user's question using only the relevant section. Don't dump the full reference.
If the question involves the GraphQL Embedded API (solution instances, user tokens, authentications), also **read `references/tray-api-reference.md`** for endpoints, authentication, and mutation details.
## Step 4 — Actionable guidance
You no longer need the platform guide — focus on the user's specific situation.
**Connector selection shortcut**: Check Tray's connector library first (700+ pre-built). If no connector exists, use the HTTP Client connector for any REST API, or build a custom connector with the Connector Development Kit (`falafel` Node.js framework).
**Cost optimization shortcut**: Task-based billing — each workflow step counts. Audit high-volume workflows, remove redundant steps, use branching to skip unnecessary actions. Enterprise contracts typically start at $36K/year; model task consumption before signing and negotiate usage caps.
**Debugging shortcut**: Use the workflow Debug panel to step through execution and inspect input/output at each step. For the Embedded API, inspect GraphQL responses for `errors` array — Tray returns HTTP 200 with an `errors` field even on failure. Check connection auth status; expired auths silently fail.
**Tray Embedded shortcut**: Solution instances are per-end-user copies of a Solution. Use Master Token for org-wide operations (Get Users, create Solution Instance). Use User Token (created via `createUserToken` mutation) for per-end-user operations (Get Solution Instances, update config). All API calls must be server-side — CORS blocks browser calls.
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 pricing details and feature availability which change frequently.*
- **No public pricing page.** Tray is sales-led — no self-service signup, no published tier pricing. Public third-party sources conflict by an order of magnitude (Pro quoted at both $99/mo and $595/mo). Enterprise contracts typically start at $36K/year. Always get a written quote before committing.
- **Task-based billing escalates unpredictably in production.** The most common user complaint across G2/Capterra reviews: task consumption in production exceeds estimates. Model expected task volume carefully and ask Tray sales for consumption alerts and soft caps before signing.
- **GraphQL backend-only — CORS blocks client-side calls.** "The Tray GraphQL API is a backend API only and calls must be invoked server-side." You cannot call the Embedded API from a browser. All integration UI in your SaaS product must route through your backend.
- **Two token types with different scopes.** Master Token = entire org workspace (used for `Get Users`, admin mutations). User Token = single end user (used for `Get Solution Instances`, `updateSolutionInstance`). Some endpoints (e.g., `Get Authentications`) accept both. Use the wrong token and you'll get empty results or auth errors.
- **Rate limits: 30 req/sec, 1800 req/min, burst 50/sec.** Call connector endpoint has separate concurrency limit of 1000 active requests. Docs don't specify which HTTP response code is returned when exceeded — monitor for rate-limit errors and implement exponential backoff.
- **Documentation gaps are a consistent complaint.** G2 and Capterra reviewers repeatedly note thin docs, missing real-world examples, and steep learning curve for advanced features. Budget training time and pair new builders with experienced ones.
- **Regional base URLs differ.** US: `tray.io/graphql`. EU: `eu1.tray.io/graphql`. APAC: `ap1.tray.io/graphql`. Whitelabel OAuth redirects use `{org}.integration-authentication.com/oauth2/token`. Using the wrong region returns empty results without an obvious error.
- **Tray.io → Tray.ai rebrand.** The product rebranded to Tray.ai in 2024 with heavy AI/Merlin pivot. `tray.io` now 301-redirects to `tray.ai`, but API surface and developer docs still use `tray.io` domains. Both work in documentation links.
## Related skills
- `/sales-workato` — Workato platform help — enterprise iPaaS, 1200+ connectors, recipe automation, MCP Gateway (top competitor)
- `/sales-mulesoft` — MuleSoft platform help — Anypoint Platform, API-led connectivity, 450+ connectors (direct competitor)
- `/sales-boomi` — Boomi platform help — enterprise iPaaS, 1000+ connectors, Data Hub MDM (direct competitor)
- `/sales-celigo` — Celigo platform help — mid-market iPaaS, 1000+ connectors, NetSuite depth (direct competitor)
- `/sales-snaplogic` — SnapLogic platform help — enterprise iPaaS, 1000+ Snaps, AgentCreator (direct competitor)
- `/sales-jitterbit` — Jitterbit platform help — Harmony iPaaS, 400+ connectors, API Manager (direct competitor)
- `/sales-informatica` — Informatica IDMC platform help — enterprise iPaaS + data management, CDI/CAI, MDM, Data Catalog (direct competitor,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.