cognitedata

MUST be used whenever building a chat UI with Atlas agents in a Flows app. Do NOT manually write useAtlasChat integration code — this skill handles installation, component structure, and hook wiring. Triggers: useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI. For a full chat app, run skills in order: (1) integrate-atlas-chat, (2) create-client-tool (per tool), (3) setup-python-tools (if Python tools needed).

Call a deployed Cognite CDF Function and retrieve its response, with Zod-validated API responses and an optional React Query hook. Use this skill whenever you need to invoke any CDF Function (by numeric function ID or external ID), pass arbitrary input data, and get a typed, validated result back — regardless of what the function does, the function has an outpt, or what shape its input/output takes. Triggers: call cognite function, invoke CDF function, run CDF function, poll CDF function, CDF Functions API, cognite function result, function call nonce.

MUST be used whenever scaffolding a new Atlas agent project. Creates agent.yaml, README.md, and a starter eval/cases.yaml with the correct structure, tool definitions, and instructions. Do NOT manually write agent.yaml from scratch — this skill handles the full scaffold. Triggers: create agent, new agent, scaffold agent, agent project, agent template, cognite agents create.

Simplified Aura guidance for selecting primitives, keeping token usage consistent, and applying reliable layout/copy/state patterns in Flows and Fusion apps.

CDF Data Modeling query-vs-list expert skill. Use for graph-native reads with instances.query, traversal payload design, failure debugging, pagination/dedupe semantics, and regression-proof tests (including Node.js/TypeScript parity checks).

Reference skill for CDF Data Modeling API best practices. Covers concurrency limits (avoiding 429s), pagination patterns for instances.list and instances.query, batching write operations, search vs filter guidance, and the QueuedTaskRunner (Semaphore) utility for controlling concurrent requests. Triggers: DMS limits, 429 error, rate limit, pagination, cursor, nextCursor, batching, semaphore, QueuedTaskRunner, cdfTaskRunner, instances.search, instances.list, instances.query, instances.upsert, concurrency, deadlock.

MUST be used when migrating a legacy Dune app to the new Flows app hosting infrastructure. Orchestrates the full migration: audits current state, updates app.json to appsApi infra, delegates auth wiring to setup-flows-auth, creates or updates manifest.json network permissions, and updates deploy scripts to @cognite/cli. Use this whenever a user says 'migrate to Flows', 'migrate to new infra', 'move from dune to flows', 'migrate legacy app', or wants to move their existing app to the new Flows app hosting.

MUST be used whenever creating an AtlasTool (client-side tool) for an Atlas agent. Do NOT manually write AtlasTool definitions or wire them into useAtlasChat — this skill handles the TypeBox schema, execute function, and hook wiring. Prerequisite: integrate-atlas-chat (vendored src/atlas-agent + TypeBox/AJV deps). This includes tools that fetch data, render UI, call APIs, show charts, query local state, or perform any browser-side action. Triggers: AtlasTool, client tool, add tool, create tool, new tool, tool definition, agent tool.

CDF data model design patterns for containers, views, and CDM/IDM extensions in YAML. Use when creating or modifying data model YAML files, extending CogniteCore or IDM types, designing containers and views, adding indexes or direct relations, auditing data models, or deploying via Cognite Toolkit.

Search-first, production-safe query patterns for Cognite DMS (Data Modeling Service), including pagination, traversal, retries, and anti-pattern avoidance.

Expert guidance on CDF Functions. Use when the user is writing, reviewing, or troubleshooting a CDF Function, configuring Function YAML files for the Cognite Toolkit, working with handler signatures, secrets, schedules, local development, or function deployment.

Validate CDF resource identifiers against naming conventions — for a single file, resource type, or small set of identifiers. Use for quick spot-checks: "does this externalId look right?", "check naming in this file", "is this identifier valid?", "validate this resource name". For a full project sweep across all domains (data modeling, transformations, functions, workflows, DMS queries) use `cog-vd-audit` instead.

Expert guidance on CDF Transformations. Use when the user is writing, reviewing, or troubleshooting a CDF Transformation SQL query running on the Spark SQL backend, configuring Transformation YAML files for the Cognite Toolkit, working with transformation destinations (nodes, edges, instances, raw, etc.), or auditing an existing transformation for performance, memory, incremental-load, JOIN, DM/delete, or formatting issues.

Expert guidance on CDF Workflows. Use when the user is designing, writing, or troubleshooting a CDF Workflow, configuring Workflow YAML files for the Cognite Toolkit, working with task types (function, transformation, dynamic, subworkflow, cdf), triggers, dependencies, or error handling.

Full best-practices audit of a CDF (Cognite Data Fusion) project. Scans all Cognite Toolkit YAML, SQL, and Python files and produces a structured AUDIT_REPORT.md covering naming conventions, data modeling, transformations, functions, workflows, and DMS query patterns. Use this skill whenever the user says "audit this project", "run best practices audit", "check best practices", "full audit", "validate CDF project", "compliance check", "run the auditor", "cog-vd-audit", "audit everything", or asks to review a project against Cognite best practices or production readiness. Also trigger when the user shares a project directory and asks if it follows the right patterns, is ready for production, or is ready for go-live.

Stage changes, run pre-commit hooks, and optionally commit, push, create a PR, and monitor CI. Use when the user says "send it".

Create a Jira ticket in the CDF project at cognitedata.atlassian.net. Defaults to Task or Bug issue type, component velocity:tooling, and parent epic CDF-26605 (Toolkit: Maintenance H1 2026). Use when the user wants to create a Jira ticket, log a bug, file a task, or track work in Jira.

Fetch Jira via Atlassian MCP (server user-atlassian), branch, plan, code. Use when the user says "start it" or "start" with a Jira URL.