keboola

The canonical way to get a past meeting or call into the Keboola CRM: import its recording (from Plaud), download the transcript, and log it as a `call` activity with a structured English write-up. Use this WHENEVER the user wants to log/record a call or meeting to the CRM or write one up — e.g. "log activities from meetings to CRM", "log my call with <customer>", "write up the Bonami renewal call and put it in the CRM", "import today's Plaud recording", "pull my latest recording into the CRM as a call activity", "turn my recorded meeting into a CRM activity", or naming a recording by date. It finds the recording in Plaud, downloads the transcript, resolves the CRM account + opportunity, pulls the real attendees from Google Calendar, creates any missing contacts, and writes notes in a fixed 7-section English template (When / Participants / Key facts / Action points / Next steps / Customer sentiment / Customer feedback & product requests). When the call surfaces product feedback or feature requests, it also op

Build ad-hoc data-exploration views and dashboards over CRM data using natural language. Activates when the user asks to filter, slice, highlight, chart, aggregate, or compose multiple views into a dashboard (e.g. "show opportunities owned by X with stage Demo and highlight Activity Center", "give me a pipeline-by-stage chart", "build a CRO dashboard with KPIs and charts"). Translates the request into typed JSON and calls `crm views` / `crm dashboards`.

Enrich account data using external sources — research companies via Perplexity AI, search business registries (ARES, BRIS, D&B), validate firmographic data, and update CRM accounts with verified information. Activates when users need to research a company, validate account data, or enrich firmographics.

Research an account using registry data and enrichment to prepare for sales engagement. Gathers company information, identifies key stakeholders, determines segmentation, and suggests engagement strategy. Activates when users want to research a company, prepare for a first call, or enrich account data.

Triage and manage CRM alerts — list alerts by severity, acknowledge alerts, view summary statistics, run a daily triage routine, and reference alert type definitions. Activates when users need to review, acknowledge, or triage CRM alerts.

Manage sales commissions — view plans, track personal and team earnings, calculate payouts, generate and approve statements, handle clawbacks, and forecast future commissions. Activates when users need to work with commissions, earnings, statements, or clawbacks.

Manage competitive intelligence — browse battlecards, view competitor details, create and update battlecards (admin), track usage, auto-surface relevant competitors, and prepare pre-call competitive briefs. Activates when users need competitive information, battlecard management, or pre-call competitor preparation.

Manage the full contract lifecycle — create contracts, view details, renew, amend, inspect the renewal history chain, and generate bookings reports. Activates when users need to work with contracts, renewals, amendments, or bookings.

Host an MCP server as a private, single-tenant Keboola data app — a dedicated remote MCP endpoint on your own Keboola compute (Keboola MCP is the built-in example, but it wraps any streamable-HTTP / FastMCP server) with client auth. Use when a user wants a private or self-hosted MCP endpoint, or would benefit from one but hasn't asked (see "When to use this"). Keywords: host/self-host MCP server as Keboola data app, private/remote MCP endpoint, deploy MCP to Keboola.

Use right after a Keboola semantic-context tool returns, when building an app, query, report, or transformation from a semantic model. Ground the SQL in the model's own physical mapping (dataset `tableId`/`fqn`, metric SQL) and confirm the real columns before writing any query — do not build SQL from the business-facing display names.

Use when building, modifying, deploying, or debugging Keboola Apps (Streamlit or Python/JS). Covers the full lifecycle — choosing app type, configuring keboola-config/, storage access (RO workspace, RW Query Service, input mapping), authentication, DuckDB caching for performance, default Keboola styling, dashboard patterns, optional Kai chat integration, and the three client paths (MCP-only, Claude Code with filesystem, kbagent CLI).

Use when accessing a Keboola-managed Git (Forgejo) repo for a python-js data app via the kbagent CLI — provisioning the repo, finding its repo_url, minting a git_clone_url / push credential with create_python_js_data_app_git_credential, pushing source to Keboola git, copying source between GitHub and Keboola git, working around the ~15MB / HTTP 413 push cap with build-at-deploy, or deploying a data app from its managed git repo. Triggers: kbagent, Keboola managed git, Forgejo, data app repo, repo_url, git_clone_url, create git credential, push to Keboola git, build-at-deploy, HTTP 413, deploy from git.

Use this skill to migrate an existing Microsoft Power BI semantic model into a Keboola semantic layer model. Accepts two input shapes: (1) TMDL folder extracted with the Microsoft Power BI Modeling MCP server in `--readonly` mode (canonical, captures DAX + Power Query M expressions verbatim); (2) per-table JSON produced by older `get_semantic_model` calls (missing M steps). Maps Power BI tables → Keboola semantic-dataset, measures → semantic-metric (DAX preserved verbatim, flagged for SQL translation), relationships → semantic-relationship. Produces JSON files ready to push to the Keboola metastore via `sl-toolkit` or the REST API. Use for: migrate PowerBI semantic model, convert Power BI to Keboola SL, translate TMDL, import PowerBI tables, powerbi-to-sl, pbi-migration, brownfield semantic layer. Trigger when the user has PowerBI artifacts (TMDL folder, `*_semantic_layer.json`, `.bim`, `.pbip`) and wants them as a Keboola semantic layer.

Semantic layer reference for Keboola. Auto-loads when the user mentions: semantic layer, semantic model, SL, metastore, semantic-metric, semantic-dataset, semantic-relationship, semantic-glossary, semantic-constraint, inspect model, validate model, threshold constraints, metric sql, model entities, add dataset, create metric, update metric, delete metric, remove constraint. Provides API reference, payload shapes, CRUD procedures, validation rules, and operational gotchas so Claude can work with the metastore directly.

Use this skill for managing and reviewing Keboola projects. Activates when syncing project configs (init, pull, push, diff), running project reviews, analyzing SQL transformations, auditing security, assessing performance, validating financial logic, or evaluating template readiness. Covers the full Keboola CLI workflow and 10-agent review team.

Expert knowledge for writing, optimizing, and migrating DuckDB transformations in Keboola. Covers SQL dialect, block orchestration, dynamic backends, Parquet format, case sensitivity, Snowflake-to-DuckDB migration, type casting patterns, and best practices. Use when the user is writing DuckDB SQL, migrating from Snowflake, debugging DuckDB transformations, or needs guidance on DuckDB-specific syntax and configuration in Keboola.

Set up Google Workspace for Claude Code via the official `gws` CLI — Drive, Calendar, Gmail, Docs, Sheets, Chat. Triggers on "set up Google Workspace", "set up gws", "configure GWS", "fix Google access". Idempotent — short-circuits if already configured. Branches on operator-provisioned OAuth app (~2 min) vs manual GCP project walkthrough (~20 min).

How to use Agnes as an analyst — discover tables, choose the right query path for local vs remote data, take filtered snapshots of large remote tables, and look up canonical business-metric definitions. Use whenever someone asks about querying Agnes data, the catalog, snapshots, `agnes query`, remote/BigQuery tables, or how to compute a business metric. Triggers on "query Agnes", "what tables are there", "agnes catalog", "snapshot a remote table", "how do I compute revenue/MRR".

How to configure and customize THIS Agnes instance — the init prompt, the analyst workspace, branding / instance.yaml, and connectors — across its environments. Use when an operator or admin asks where the instance's content/config lives, how to change the init prompt or landing page, how to rebrand, or how a config value resolves. Triggers on "change the init prompt", "edit branding", "where does the config live", "how do I customize this instance", "change /home content", "initial workspace template".

Agnes implementation playbooks + non-negotiables. Use when implementing a feature in this repo — adding a data-source connector, REST API endpoint, HTML dashboard page, repository method/repo, or schema migration. Routes to per-task reference playbooks verified against the codebase.

Set up Asana for Claude Code — Personal Access Token in OS keychain, REST API access. Triggers on phrases like "set up Asana", "configure Asana", "fix Asana access". Idempotent — short-circuits if already configured.

Set up Atlassian (Jira + Confluence) for Claude Code — API token in OS keychain, email + base URL in ~/.claude/agnes/secrets.env, hosted Remote MCP registered. Triggers on "set up Jira", "set up Atlassian", "configure Confluence", "fix Jira access". Idempotent — short-circuits if already configured.

This skill should be used when the user asks to "build a JS app with Kai", "create a JavaScript data app", "integrate Kai with Express", "stream Kai responses in JavaScript", "add Kai chat to a web app", "build a Keboola chat UI in JS", "create a JS data app", or mentions JavaScript/Express/Node.js with Kai, kai-assistant, or Keboola AI Assistant. Provides patterns, gotchas, and working code for building JavaScript apps that integrate with the Kai API.

This skill should be used when the user asks to "build a streamlit app with Kai", "create a Keboola data app", "integrate Kai with Streamlit", "stream Kai responses in Streamlit", "add Kai chat to Streamlit", "build a Keboola chat UI", "create a data app", or mentions Streamlit with Kai, KaiClient, or Keboola AI Assistant. Provides patterns, gotchas, and working code for building Streamlit apps that integrate with the KaiClient library.

This skill should be used when the user asks to "use kai", "run kai command", "chat with Keboola AI", "query Keboola", "list tables", "check kai history", "interact with Keboola assistant", "send message to kai", or mentions Kai CLI, Keboola AI Assistant, or wants to execute Kai commands. Provides comprehensive guidance for using the Kai CLI tool to interact with the Keboola AI Assistant.

Build customer cohorts and measure repeat purchases by joining the demo orders_demo and customers_demo tables. Triggers on cohort, retention, and repeat-purchase questions over the demo dataset.

Summarise revenue, order count, and average order value over the demo orders_demo table, optionally grouped by day/week/month. Triggers on revenue, AOV, and order-trend questions over the demo dataset.

Prepares release notes and tags for a new Keboola MCP Server version. Use when the user asks to prepare a release, create release notes, or tag a new version.

Create production-ready Osiris ETL components (extractors, writers, processors). Use when building new components, implementing capabilities (discover, streaming, bulkOperations), adding doctor/healthcheck methods, packaging for distribution, validating against 60-rule checklist, or ensuring E2B cloud compatibility. Supports third-party component development in isolated projects.

Use when working with Keboola Connection projects via kbagent CLI. Covers: exploring and searching configurations (extractors, writers, transformations), browsing job history, analyzing cross-project data lineage, calling MCP tools across multiple projects, managing development branches, debugging SQL in temporary workspaces, bulk-onboarding organizations, syncing project configs as local files (GitOps), git-branching with Keboola dev branch isolation, sharing buckets across projects, linking shared data, encrypting secrets for MCP tool call workflows, uploading/downloading Storage Files with tag management, and syncing storage metadata and job history. Triggers: kbagent, Keboola project, keboola configs, keboola jobs, keboola lineage, keboola transformations, keboola MCP tools, keboola workspace, SQL debugging, keboola branches, keboola organization, keboola sharing, bucket sharing, link bucket, keboola sync, keboola git, keboola gitops, sync pull, sync push, sync diff, branch-link, search configs, find in c

Use when adding a new library/package to the platform-libraries monorepo (a new libs/<name> directory) and wiring it into Docker, CI and the publish/release pipeline.