snowflake-labs
- 305 skills
- 0 followers
- 54 repo stars
- 2 days ago last updated
- ▌ Sandbox · snowflake-labs bundleRoutes tasks to deploy common sandboxes or create isolated ones during subagent workflows when setting up test environments.
- ▌ Validate Etl Resolve Scripts · snowflake-labs bundleResolves the SSC-EWI-SSIS0004 blocks SnowConvert left in a validate-flow SSIS unit before deploy, converting variable-only Script Tasks to Snowflake Scripting and failing the rest by name instead of leaving silent no-ops. Use when the validateEtlResolveScripts task is dispatched for a unit whose parts carry SSC-EWI-SSIS0004.
- ▌
- ▌ Dbt Orchestrator · snowflake-labs bundleOrchestrates the full dbt Jinja repointing workflow. Invoked automatically by main.json when `scai code add` detects a dbt project (dbt_project.yml). Resolves the source SQL dialect, runs `scai code convert --dbt`, validates and fixes YAML configs for Snowflake compatibility, fixes dialect-specific macro files, and refines converted SQL models until the project compiles clean.
- ▌ Dbt Consolidation · snowflake-labsCollect one dbt consolidation choice before SSIS and Informatica dbt conversions. Consolidate SSIS projects and models by package, consolidate every SSIS package into one dbt project, consolidate Informatica projects and models by folder, consolidate every Informatica folder into one dbt project, or retain the per-Data-Flow/per-mapping layout. Supplies `--consolidate-dbt-projects` or, when only one platform is on dbt, `--consolidate-as-single-dbt-project` for `scai code convert`. Load from `convert` or `code-conversion-only` only when ETL will emit dbt.
- ▌ Convert Etl Aifirst · snowflake-labs bundleRouting for ETL platforms SnowConvert does not natively convert. Decides between the native ETL replatform path and the AI-First convert action, states what each exit code means, when the Code Unit Registry may record conversion as completed, and how lineage is written into the Code Unit Registry. Instruction-only: the runtime lives in the etl-aifirst action.
- ▌ Data Lineage · snowflake-labs bundleBuilds the Data Lineage graph from the Code Unit Registry with `scai assessment data-lineage`. When Power BI `.pbit` files are staged, enriches those reports into the registry first so the Reports lane is populated. Use for the assessment Data Lineage step.
- ▌ Fix Dbt Macros · snowflake-labs bundleFix macro files in a dbt project for Snowflake incompatibilities after `scai code convert --dbt` has repointed the project's model SQL and ref()/source() calls from its original source dialect (Redshift, BigQuery, Databricks, PostgreSQL, Teradata, Oracle, SqlServer, or any other dialect scai's dbt repointing supports) to Snowflake. Scoped strictly to files under macro-paths (default `macros/`) — does not touch model SQL or dbt_project.yml/profiles.yml. Use when the user says "fix dbt macros", "macros aren't Snowflake compatible", "fix macro files after dbt repointing", or after scai's dbt repointing conversion leaves macro-level source-dialect syntax unconverted. Normally spawned by `migration/dbt/SKILL.md` Step 4 in task mode, but also runnable standalone. Do NOT use for fixing model SQL or validating dbt config files — those are Steps 5 and 3 of the dbt repointing orchestrator. Distinct from `migrate-objects/actions/etl-stabilization/dbt-fixer`, which fixes SnowConvert-generated dbt projects during ETL stab
- ▌ Conversion Issues · snowflake-labsBuilds the AIM conversion-issues artifact and Jira ZIP from registry SSC-EWI markers, then fills Problem Description and Recommended Fix.
- ▌ Business Use Cases · snowflake-labs bundleFinds the business use cases in a converted workload and plans one migration wave per use case, over the registry with the `scai assessment waves` tools. Use during an assessment, or when someone asks for a wave or a use case around an application, a process, a report or an object.
- ▌ Dcp Setup · snowflake-labsReach an on-premise or private source through a Data Connectivity Proxy tunnel. scai data worker setup --dcp provisions the Snowflake side; this skill covers the agent the customer runs, and the lifecycle around it. Triggers: data connectivity proxy, DCP, on-premise source, private source, source unreachable from Snowflake, dcp agent, rotate bootstrap token.
- ▌
- ▌
- ▌ Budget Guardrail · snowflake-labsCap the spend of DMV's SPCS infrastructure — one custom Snowflake Budget over the project's warehouse and compute pool, with a custom action that turns off auto-resume and suspends both when spend reaches a threshold. Runs before the first data_infrastructure(mode="up") whenever the orchestrator or a worker is on SPCS.
- ▌
- ▌ Informatica Pmcmd Connection · snowflake-labsRegister Informatica PowerCenter pmcmd credentials as a scai connection so scai test etl-validate can launch workflows without re-exporting environment variables. Triggers: informatica, pmcmd, powercenter, etl connection, pmcmd credentials, add informatica connection.
- ▌ Validate Etl Repair · snowflake-labsRepair one converted ETL unit from a deploy or validation failure without entering stabilization.
- ▌ Validate Etl Seed · snowflake-labsSeed the ETL test YAML and arrange both source and Snowflake data for the isolated validate flow.
- ▌
- ▌ Cortex Code 4 · snowflake-labs bundleRoutes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise. Use when user asks about Snowflake databases, data warehouses, SQL queries on Snowflake, Cortex AI features, Snowpark, dynamic tables, data governance in Snowflake, Snowflake security, or mentions "Cortex" explicitly. Do NOT use for general programming, local file operations, non-Snowflake databases, web development, or infrastructure tasks unrelated to Snowflake.
- ▌ Skill Optimiser 2 · snowflake-labs bundleOptimize, audit, create, and improve Cortex Code skills following official best practices from the Anthropic skill-building guide. Use when: creating a new skill, reviewing an existing skill, optimizing skill description or triggers, improving SKILL.md structure, auditing skill quality, fixing undertriggering or overtriggering, restructuring skill for progressive disclosure. Do NOT use for: general code review, non-skill markdown editing, MCP server development. Triggers: optimize skill, audit skill, review skill, create skill, improve skill, fix skill triggers, skill best practices, skill quality check.
- ▌
- ▌ Cortex Code 2 · snowflake-labs bundleRoutes Snowflake-related operations to Cortex Code agent for specialized Snowflake expertise. Use when querying databases, checking data quality, or asking about Snowflake features.
- ▌ Cortex Code 3 · snowflake-labs bundleRoutes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise. Use when user asks about Snowflake databases, data warehouses, SQL queries on Snowflake, Cortex AI features, Snowpark, dynamic tables, data governance in Snowflake, Snowflake security, or mentions "Cortex" explicitly. Do NOT use for general programming, local file operations, non-Snowflake databases, web development, or infrastructure tasks unrelated to Snowflake.
- ▌ Rbac 2 · snowflake-labs bundleUse when designing or refactoring Snowflake RBAC: choosing a role hierarchy, creating database/schema access roles, setting up functional roles, deciding between primary and secondary roles, or referencing roles in masking and row access policies. Routes to focused sub-flows for each layer of the hierarchy. Triggers: rbac, role hierarchy, access roles, functional roles, schema access role, database access role, warehouse access role, secondary roles, policy roles, role design, grant, managed access schema, future grants
- ▌ Mlops 2 · snowflake-labs bundleUse when a developer or data engineer wants to assess MLOps maturity, design a promotion strategy (Code/Model/Hybrid), or implement MLOps capabilities (CI/CD, monitoring, retraining, governance) on Snowflake for traditional ML or LLM/GenAI workloads. Triggers: mlops, mlops maturity, mlops assessment, mlops strategy, mlops pattern, mlops framework, model promotion, ml ci/cd, ml monitoring, llmops, rag pipeline ops, fine-tuning ops.
- ▌ Spec Driven 2 · snowflake-labs bundleUse when implementing a feature, fixing a bug, refactoring code, creating a spec, writing a specification, planning implementation, or following a structured development workflow. Creates specifications BEFORE implementation using EARS notation, ensuring alignment, traceability, and regression prevention. Triggers: spec-driven, specification, SDLC, EARS, implement feature, fix bug, refactor, create spec, plan implementation, design first, spec workflow, structured development.
- ▌ Dcr V1 To V2 2 · snowflake-labs bundleUse when migrating a Snowflake Data Clean Room from V1 (SAMOOHA Provider/Consumer API) to V2 (Collaboration API). Discovers V1 setup via introspection queries, maps constructs to Collaboration API equivalents, converts JinjaSQL templates, and generates provider/consumer setup plus cleanup scripts. Output is local files only — no live DDL/DML. Triggers: DCR migration, V1 to V2, clean room upgrade, clean room migration, migrate DCR, upgrade clean room, SAMOOHA to Collaboration API.
- ▌ Xo 2 · snowflake-labs bundle**[REQUIRED]** XO operator workflow system — the single entry point. Triage classifies the request, routes to the right stage reference, and composes multi-stage pathways. Recording (save) and Recall run underneath. Triggers: work item, WI, task, implement, investigate, plan, review, execute, what should I do, where do I start, savepoint, resume.
- ▌ Snowpipe Bcdr 2 · snowflake-labs bundleUse when designing or operating Snowpipe disaster recovery on Azure ADLS Gen2 — choosing between dual-pipe, RA-GRS, active-active, or Failover Group patterns, and running failover/failback/catchup. Triggers: snowpipe BCDR, snowpipe disaster recovery, snowpipe failover, dual pipe, active-active pipe, RA-GRS snowpipe, GZRS snowpipe, snowpipe catchup, pipe failback, snowpipe high availability, failover group snowpipe, snowpipe RPO RTO.
- ▌ Snowpro Study 2 · snowflake-labs bundleGenerate SnowPro certification study materials including study plans, domain deep-dives, flashcards, and practice exam questions for any SnowPro exam. Dynamically discovers current certifications and exam versions from Snowflake. Use when asked to study, prep for, or generate content for SnowPro certifications.
- ▌ Snowflake Docs 2 · snowflake-labs bundleUse for **ALL** Snowflake documentation lookups: feature questions, SQL syntax, best practices, how-to guides, configuration, and troubleshooting. This is the required entry point for any question about Snowflake products or features. Triggers: Snowflake docs, how do I, SQL syntax, CREATE, ALTER, DROP, warehouse, stage, Cortex, Snowpipe, dynamic table, stored procedure, UDF, MCP, Snowpark, Streamlit, Native App, data sharing, replication, security, roles, grants, what is, how does, Snowflake feature.
- ▌ Swap Databases 2 · snowflake-labs bundleSwap the names of two Snowflake databases safely with object sync and grant mirroring. Also handles read-only databases by redirecting dependent objects from one DB to another without renaming. Also handles zerocopy swap of an imported datashare database with a catalog-linked database (CLD). Use when: swapping databases, renaming databases bidirectionally, blue-green database cutover, migrating database names, database name swap, redirecting dependencies, read-only database migration, shared database replacement, migrate shared views, redirect abstracted views, sfshares migration, zerocopy swap, datashare to CLD, imported database swap CLD. Triggers: swap databases, rename database, swap DB names, database cutover, blue-green swap, exchange databases, redirect dependencies, read-only database, replace shared database, migrate references, migrate sfshares, abstracted views, migrate views, zerocopy, datashare, catalog linked database, CLD, SYSTEM$ZEROCOPY_SWAP.
- ▌ Spark Migration 2 · snowflake-labs bundleMigrate Spark scripts and notebooks to Snowflake. Routes to one of two bundled conversion paths and orchestrates the post-conversion pipeline. **Default path: Snowpark Connect (SCOS)**, which preserves the PySpark API surface. The SMA / Snowpark API path is invoked only when the user explicitly asks for it. Also **deploys** the output as a **Notebook** (`deploy-notebook`) or **Code Bundle** (`deploy-code-bundle`). Triggers: convert spark, migrate pyspark, migrate spark, migrate to snowpark, convert to snowpark, snowpark connect, scos, scos migration, migrate to snowpark connect, migrate to scos, snowpark api, sma cli, sma conversion, run sma, snowflake.snowpark rewrite, already migrated, already ran sma, sma dashboard, fix ewis, stage conversion, dvp orchestrator, resume dvp, assess pyspark, assess spark, assess databricks, spark assessment, databricks assessment, spark workload assessment, migration readiness, migration readiness report, spark readiness, spark compatibility, spark compatibility report, pyspa
- ▌ Quickstart Guide 2 · snowflake-labs bundleUse when a user pastes a Snowflake Quickstart URL or asks to learn/walk through a Quickstart. Fetches the source content from GitHub, parses it into stages, checks the learner's environment, and delivers a guided build experience with two modes (learner or builder). Triggers: quickstarts.snowflake.com, snowflake.com/en/developers/guides/, walk me through this quickstart, teach me this quickstart, learn this guide, I want to do this quickstart. Do NOT use for general SQL help or non-Quickstart tutorials.
- ▌ Check Agent Access 2 · snowflake-labs bundleAudits all (or selected) Cortex Agents in a Snowflake account. For each agent the skill reads the live specification, extracts every dependency (semantic views, Cortex Search services, UDFs, warehouses, tables), then checks whether a user-supplied role holds the required privilege on each object — including inherited grants via role hierarchy. Results are presented as a gap table grouped by agent, followed by an optional one-click remediation script. Triggers: check agent access, audit agent privileges, who can use my agents, role access to agents, missing agent grants, grant agent usage, agent USAGE check, PUBLIC can't call agent, fix agent permissions, check role permissions for Cortex Agent. Do NOT use for: general RBAC design (use `rbac`), warehouse credit audits, or auditing non-agent Snowflake objects.
- ▌
- ▌
- ▌ Review Skill Sflabs 2 · snowflake-labs bundleUse when a contributor has built a Cortex Code skill locally and wants a pre-PR readiness check before opening a pull request against Snowflake-Labs/cortex-code-skills. Verdict: promote, adapt, or skip — with concrete fixes. Triggers: "review a skill", "is this skill ready for labs", "check this skill before PR", "audit skill for promotion", "does this skill belong in labs".
- ▌ Solutions Installer 2 · snowflake-labs bundleUse for ALL requests to install, set up, deploy, or tear down a pre-built Snowflake industry solution. This skill reads a solution's manifest.json for metadata, then executes its setup SQL scripts against the user's Snowflake account. Triggers: install solution, coco solutions install, set up solution, deploy solution, teardown solution, uninstall solution, sf-solutions, solution accelerator, demo environment. Do NOT use for: adding pages to the solutions catalog website (use snowflake-solutions-catalog instead), building custom solutions from scratch, or general SQL authoring.
- ▌
- ▌
- ▌
- ▌ Manage Zerocopy Sapbdc 2 · snowflake-labs bundleManage the end-to-end lifecycle of the Snowflake and SAP BDC Zero-Copy Integration and connector. Use when: consuming SAP data products in Snowflake, publishing Snowflake databases to SAP BDC with minimal CSN (v1.0, SDK-compatible), analyzing shared SAP data, or troubleshooting SAP BDC connector issues. This version uses MINIMAL CSN generation only (no options, no reviews, no validation loops). Triggers: SAP BDC, SAP connector, minimal CSN, SDK CSN, zerocopy connector, SAP data product, SAP BDC Connect, SAP publish, SAP share, SAP troubleshoot.
- ▌ Ontology Stack Builder 2 · snowflake-labs bundleUse for ALL requests that mention: ontology, knowledge graph, semantic layer from schema, ontology-on-snowflake, abstract views, ontology metadata tables, KG_NODE, KG_EDGE, build ontology stack, generate ontology from tables, ontology layer generation, map tables to ontology, generate cortex agent config. Triggers: build ontology, create ontology stack, schema-to-ontology, OWL import, knowledge graph on snowflake, create semantic models from schema. Do NOT use for: simple semantic view creation (use semantic-view skill), standalone Cortex Agent creation (use cortex-agent skill).
- ▌ Semantic View Patterns 2 · snowflake-labs bundleUse when learning Snowflake Semantic View patterns, teaching SV concepts, applying patterns to existing SVs, or building new SVs with best practices. Triggers: semantic view patterns, sv patterns, walk me through, time intelligence, range join, ASOF join, semi-additive, window metrics, derived metrics, role playing dimensions, accumulating snapshot, sv diagnostics, fan trap, USING clause, NON ADDITIVE BY.
- ▌ Setup Openflow Privatelink 2 · snowflake-labs bundleUse when configuring private connectivity from Snowflake OpenFlow (running on SPCS) to AWS-hosted or on-premises data sources via AWS PrivateLink. Covers NLB + VPC Endpoint Service on AWS, then SYSTEM$PROVISION_PRIVATELINK_ENDPOINT, network rules, and External Access Integration on Snowflake. AWS only (Public Preview also exists on Azure but is out of scope here). Triggers: OpenFlow PrivateLink, SPCS private connectivity, NLB for OpenFlow, EAI for OpenFlow, SYSTEM$PROVISION_PRIVATELINK_ENDPOINT, OpenFlow RDS, OpenFlow MySQL, OpenFlow PostgreSQL, private ingestion OpenFlow, SPCS egress.
- ▌ Snowpark API 2 · snowflake-labs bundleSnowpark Python API conversion path via the SMA CLI. Bundled sub-skill of `spark-migration`, invoked by the parent ONLY when the user explicitly asks for an SMA / Snowpark API rewrite (`snowflake.snowpark`, snake_case `with_column` / `group_by` / `session.create_dataframe`). Owns: SMA CLI detection, conversion, EWI dashboard, notebook migration, EWI fixer, stage conversion, DVP orchestration, and the API-side final summary. Use when: user explicitly asked for SMA / SMA CLI / Snowpark API / `snowflake.snowpark` rewrite, OR user wants to operate on an already-converted SMA output (open dashboard, fix EWIs, run stage conversion, resume DVP). Triggers: snowpark api, sma cli, sma conversion, run sma, snowflake.snowpark rewrite, snake_case snowpark, fix ewis, ewi fixer, sma dashboard, stage conversion, resume dvp, dvp orchestrator, already migrated sma.
- ▌ Deploy Notebook 2 · snowflake-labs bundleDeploy a migrated Snowpark/SCOS project to Snowflake as a Notebook. Takes the .ipynb produced by the migration skill (plus its supporting project files), reminds the user to fix flagged code, uploads the whole project to a Snowflake stage, and creates the Notebook from the stage. Triggers: deploy notebook, deploy migrated notebook, create notebook from migration output, upload project to stage, deploy scos notebook, deploy snowpark notebook.
- ▌ Snowpark Connect 2 · snowflake-labs bundleSnowpark Connect (SCOS) skills for migrating and validating PySpark, Spark Scala, and Spark Java workloads on Snowflake. Generates SMA-compatible reports (Issues.csv, InputFilesInventory.csv, ArtifactDependencyInventory.csv) using EWI codes (SPRKCNTPY* for Python, SPRKCNTSCL* for Scala/Java) for use with dvp-sma-dashboard-generator. Use when: migrating PySpark or Spark Scala/Java to Snowpark Connect, validating SCOS migrations, analyzing Spark compatibility, assessing a Spark workload before migration, producing a migration readiness report, or working with Snowpark Connect for Spark. Triggers: snowpark connect, scos, pyspark migration, spark connect, scala spark migration, java spark migration, spark java, validate migration, pyspark compatibility, scala compatibility, java compatibility, assess pyspark, assess spark, assess databricks, spark assessment, databricks assessment, migration readiness, spark workload assessment, pyspark readiness, spark compatibility report, analyze spark, analyze pyspark, analyz
- ▌ Deploy Code Bundle 2 · snowflake-labs bundleDeploy a migrated Snowpark/SCOS project to Snowflake as a Code Bundle. Takes the migrated project (its .py entrypoint + supporting modules/config), reminds the user to fix flagged code, writes a code_bundle.yml spec, uploads the whole project to a Snowflake stage, and creates the Code Bundle from the stage — on a warehouse (default) or a compute pool. No .ipynb is involved. Triggers: deploy code bundle, deploy to code bundle, run as code bundle, create code bundle from migration output, execute code bundle, snow bundle.
- ▌ Well Architected Framework Assessment 2 · snowflake-labs bundleUse when running a Snowflake Well-Architected Framework (WAF) assessment for a customer account. Three-tier scale: On Track / Needs Improvement / Needs Attention. Results displayed inline; optional HTML export. Triggers: WAF assessment, well-architected, architecture review, WAF review, security assessment, pillar assessment, security and governance, reliability, cost optimization, operational excellence, performance.
- ▌ Snowflake Notebook Migration 2 · snowflake-labs bundleMigrates Databricks (DBX) notebooks to Snowflake Workspace notebooks. Preserves original code, only fixes incompatible patterns, flags unsupported features as migration notes. Use when: migrating Databricks notebooks, converting DBX notebooks to Snowflake, fixing Databricks-specific patterns. Triggers: migrate databricks, convert dbx, databricks to snowflake, dbx notebook, migrate notebook, databricks migration.
- ▌ Stage Conversion 2 · snowflake-labs bundleReplace embedded file paths in SMA-converted Snowpark code. Use when: migrating Spark code via SMA, fixing file path references, updating storage locations, changing stage prefix. Triggers: replace embedded file paths, embedded file paths, file paths, SMA file paths, Snowpark paths, change stage prefix.
- ▌ Dvp Ewi Fixer 2 · snowflake-labs bundleScan .py, .ipynb, and .scala files for SMA (Snowpark Migration Accelerator) EWI codes and resolve them. Triggers: fix EWIs, resolve SPRKPY, resolve SPRKSCL, resolve PNDSPY, SMA warnings, migration issues, Scala migration.
- ▌ Dvp Test Runner 2 · snowflake-labsExecute generated pytest suites for source and migrated workloads. Fixes runability issues, ensures source tests pass, ensures migrated tests execute. Triggers: run tests, execute tests, validate migration, test runner.
- ▌ Dvp Code Adapter 2 · snowflake-labsAdapt source and migrated workloads for testing: inject session parameters, add enableHiveSupport(), defer env vars, and record adapted_source in entrypoints.json. Status: design phase.
- ▌
- ▌ Dvp Asg Generation 2 · snowflake-labs bundleGenerate Abstract Semantic Graph (ASG) from source code (PySpark or Scala) — a structured representation of data flow consumed by downstream DVP skills.
- ▌ Sma Dashboard Generator 2 · snowflake-labs bundleGenerate interactive SMA dashboard to track EWIs from conversion. Triggers: sma dashboard, ewi tracker, track EWIs, conversion issues.
- ▌ Dvp Notebook To Script 2 · snowflake-labs bundleConvert Jupyter notebooks to Python scripts for testing. Triggers: convert notebook, notebook to script, ipynb to py, databricks notebook.
- ▌ Dvp Migrated Test Fixer 2 · snowflake-labsFix migrated Snowpark test code until all tests PASS (not just run). Uses git-based iteration to diagnose and resolve PySpark-to-Snowpark API incompatibilities. Triggers: fix migrated tests, make migrated tests pass, snowpark test errors, migration test failures.
- ▌ Assess Pyspark Workload 2 · snowflake-labsStandalone assessment of PySpark and Databricks workloads for Snowflake SCOS compatibility. Produces a MigrationReadinessReport.html and AssessmentIR.json without committing to migration. Use when: analyzing Spark workload complexity, generating a migration readiness report, understanding migration effort before deciding, evaluating PySpark compatibility with SCOS, assessing a Databricks workload for Snowflake, or producing a pre-migration feasibility report.
- ▌ Dvp Io Schema Identifier 2 · snowflake-labs bundleIdentify input and output data (files and tables) from source workloads and infer column schemas. Triggers: identify IO, find inputs outputs, map data flow, discover tables files, extract schema.
- ▌ Dvp Test Setup Generator 2 · snowflake-labs bundleGenerate pytest files for source and migrated workloads based on entrypoints.json.
- ▌ Dvp Entrypoint Identifier 2 · snowflake-labs bundleGenerate dvp/04-results/entrypoints.json from an ASG (Warp EntrypointDetector). Triggers: entrypoints, pipelines, entry point inventory.
- ▌ Migrate Pyspark To Snowpark API 2 · snowflake-labsFresh PySpark → Snowpark API conversion via the SMA CLI. Bundled sub-skill of `snowpark-api`, loaded only after the parent has determined that the user wants a NEW SMA conversion (intent=migrate, language=Python). Owns SMA CLI detection, the SMA invocation itself, progress monitoring, and SMA output-layout resolution. Delegates the entire post-conversion tail to `validate-pyspark-to-snowpark-api`.
- ▌ Dvp Synthetic Data Generator 2 · snowflake-labs bundleGenerate synthetic test data (CSV files) for all pipeline inputs based on data_io_schema.json and optionally the ASG for constraints and relationships.
- ▌ Validate Pyspark To Snowpark API 2 · snowflake-labsPost-conversion pipeline owner for the Snowpark API path. Bundled sub-skill of `snowpark-api`. Loaded by `migrate-pyspark-to-snowpark-api` after a fresh SMA run, AND directly by `snowpark-api/SKILL.md` when the user wants to operate on an already-migrated SMA output. Owns: git init, EWI dashboard, notebook migration, EWI fixer, stage conversion, DVP orchestrator (steps 1–13), dashboard re-open, and the final summary. Also the entry point for individual API-side operations. Triggers (when invoked directly): already migrated, fix ewis, open sma dashboard, run stage conversion, resume dvp, dvp orchestrator, ewi fixer.
- ▌ Migrate Pyspark To Snowpark Connect 2 · snowflake-labs bundleMigrate PySpark and Databricks workloads to Snowflake SCOS (Snowpark Connect for Spark). Use when: converting Spark code to run on Snowflake, analyzing PySpark compatibility, updating imports to Spark Connect equivalents, or migrating from Databricks. Generates SCOS-compatible reports (Issues.csv, InputFilesInventory.csv, ArtifactDependencyInventory.csv) for the dvp-scos-dashboard-generator using official SCOS EWI codes (SPRKCNTPY*). Triggers: migrate pyspark, convert spark, scos migration, spark connect, pyspark compatibility, snowpark connect.
- ▌ Validate Pyspark To Snowpark Connect 2 · snowflake-labs bundleValidate a completed PySpark to Snowpark Connect migration across an entire workload. Surveys every entrypoint, weights each by table complexity, groups them into semantic sections, packs them into balanced batches, and runs a pool of dedicated SDK worker sessions (one per batch) that each validate one batch in an isolated git worktree (original on local PySpark + Delta vs migrated on real Snowpark Connect / SCOS). Consolidates the migration fixes onto the deliverable branch and produces a merged validation report. Use for SCOS validation, migration verification, entrypoint parity checks, and documenting remaining divergences or manual-review cases. Triggers: validate scos, verify migration, run scos test suite.
- ▌ Migrate Spark Java To Snowpark Connect 2 · snowflake-labs bundleMigrate Spark Java workloads to Snowflake SCOS (Snowpark Connect for Spark). Use when: converting Java Spark code to run on Snowflake, analyzing Java Spark compatibility, updating imports to Spark Connect equivalents, or migrating from standalone Spark Java. Generates SMA-compatible reports (Issues.csv, InputFilesInventory.csv, ArtifactDependencyInventory.csv) for the dvp-sma-dashboard-generator using official SMA EWI codes (SPRKCNTSCL* — JVM family). Triggers: migrate java spark, convert java spark, scos java migration, spark connect java, java compatibility, snowpark connect java.
- ▌ Migrate Spark Scala To Snowpark Connect 2 · snowflake-labs bundleMigrate Spark Scala workloads to Snowflake SCOS (Snowpark Connect for Spark). Use when: converting Scala Spark code to run on Snowflake, analyzing Scala Spark compatibility, updating imports to Spark Connect equivalents, or migrating from standalone Spark Scala. Generates SMA-compatible reports (Issues.csv, InputFilesInventory.csv, ArtifactDependencyInventory.csv) for the dvp-sma-dashboard-generator using official SMA EWI codes (SPRKCNTSCL*). Triggers: migrate scala spark, convert scala, scos scala migration, spark connect scala, scala compatibility, snowpark connect scala.
- ▌ Validate Spark Java To Snowpark Connect 2 · snowflake-labs bundleValidate a completed Spark Java to Snowpark Connect (SCOS) migration by surveying the workload, asking the user to choose up to 10 entrypoints, synthesizing mock data, provisioning isolated test schemas, running the original workload on local Spark + Delta, running the migrated workload on real Snowpark Connect / SCOS, and comparing end-state snapshots. Use for SCOS validation, migration verification, entrypoint parity checks, and documenting remaining divergences or manual-review cases. Triggers: validate java scos, verify java migration, run java scos test suite, validate spark java, check java migration, test java migration correctness.
- ▌ Validate Spark Scala To Snowpark Connect 2 · snowflake-labs bundleValidate a completed Spark Scala to Snowpark Connect (SCOS) migration across an entire workload. Surveys every entrypoint, weights each by table complexity, optionally scopes to a subset, packs balanced batches, synthesizes mock data, provisions isolated test schemas, runs the original workload on local Spark + Delta, runs the migrated workload on real Snowpark Connect / SCOS, and compares end-state snapshots. Use for SCOS validation, migration verification, entrypoint parity checks, and documenting remaining divergences or manual-review cases. Triggers: validate scala scos, verify scala migration, run scala scos test suite, validate spark scala, check scala migration, test scala migration correctness.
- ▌ AI Ready Data · snowflake-labs bundleAssess and optimize data for AI workloads across platforms. Scan estates for prioritization, assess assets against profiles, and guide remediation.
- ▌ Cocoscout · snowflake-labsRelevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
- ▌ Cocowatch · snowflake-labs bundleDeveloper engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.
- ▌ Cocobehavior · snowflake-labs bundleCortex-specific behavioral guidelines — always-on inner constraint layer for all CocoPlus personas
- ▌ Meta Capi Pipeline · snowflake-labs bundleBuild and manage Meta Conversions API (CAPI) pipelines in Snowflake. Triggers: set up Meta CAPI, create CAPI pipeline, discover tables, find CAPI candidates, get signal recommendations, run pipeline, send events to Meta, check CAPI status, pipeline health, debug CAPI, CAPI errors, resend failed events.
- ▌ Marketing Identity Resolution · snowflake-labs bundleBuild a first-party identity resolution pipeline on any set of source tables in Snowflake. Discovers source schemas, maps columns to canonical identity fields, generates a fully incremental Dynamic Table pipeline with deterministic and probabilistic matching, graph resolution, a keyring, and a golden record with field-level survivorship. Use for: identity resolution, IDR, identity graph, customer deduplication, identity stitching, master customer ID, golden record, customer 360 identity, first-party data graph, merge duplicate customers, link customer records across systems. Triggers: identity resolution, build IDR, identity graph, deduplicate customers, stitch identities, master customer, golden record, link records, merge duplicates, resolve identities, first-party identity, 1PD identity, identity pipeline, customer dedup.
- ▌ Cloudflare R2 Logpush Agent · snowflake-labs bundleBuild an end-to-end Cloudflare HTTP log analytics pipeline in Snowflake with a Cortex Agent. Ingests Logpush data from R2 into a parsed view, semantic view, and queryable agent. Use when: cloudflare logs, R2 logpush, http log analytics, web traffic agent, cloudflare to snowflake. Triggers: cloudflare, logpush, R2, http logs, web analytics agent.
- ▌ Install Geocoding · snowflake-labs bundleOne-command installer for Snowflake-native geocoding (forward + reverse) built on the Overture Maps Marketplace share, with an optional libpostal SPCS service for international addresses. Deploys the GEOCODING.PUBLIC UDFs and stored procedures, auto-detecting whichever Overture Addresses share is installed. Idempotent and self-owning: detects-and-reuses existing objects. Use when: install geocoding, deploy geocoding, set up address geocoding, geocode addresses in Snowflake, reverse geocode lat/lon, build the geocoding service, deploy Overture geocoding. Do NOT use for: high-accuracy/routing-grade geocoding (use a partner solution) or changing the Overture data source. Triggers: install geocoding, deploy geocoding, set up geocoding, address geocoding, forward geocode, reverse geocode, geocode my addresses, Overture geocoding, libpostal, international geocoding.
- ▌ Deploy Tileserver · snowflake-labs bundleOne-command installer for the Snowflake vector-tile demo: dynamic ST_AsMVT tiles served by Martin on SPCS (arm 1), a precomputed PMTiles archive baked from the same data (arm 2), and native H3 aggregation for client-side deck.gl (arm 3). The viewer is Martin's built-in Web UI on the public ingress. Idempotent and self-owning: detect-reuse-else-create for the Snowflake Postgres + PostGIS instance, SPCS infra (image repo, compute pool, stages, secret, EAIs), and the Martin service. Use when: install the tileserver, deploy Martin vector tiles on Snowflake, set up the Snowflake vector-tile demo, serve ST_AsMVT tiles, dynamic tiles on Snowflake Postgres, bake PMTiles from Snowflake, PostGIS MVT function source. Pass --no-pmtiles to skip the heavy bake. Triggers: install tileserver, deploy-tileserver, deploy martin, martin vector tiles, snowflake vector tiles, ST_AsMVT tiles, PMTiles bake, dynamic tiles snowflake postgres, postgis tile server.
- ▌ Openflow Bootstrap · snowflake-labsInternal bootstrap skill shared by all OpenFlow demo skills. Scaffolds project files, resolves Snowflake connection, installs tools, and confirms runtime readiness.
- ▌ Openflow Gdrive Demo · snowflake-labs bundleDeploy, clean up, or manage the Google Drive CDC connector (no DWD) on OpenFlow. Use when: openflow demo, gdrive connector, deploy google drive connector, cleanup, reset demo, setup openflow, deploy connector, start connector, configure openflow.
- ▌ Openflow Gdrive Setup · snowflake-labsInteractive setup for OpenFlow Google Drive demo. Prompts for missing config, creates infrastructure, writes to manifest.
- ▌ Openflow Gdrive Deploy · snowflake-labsDeploy the Google Drive CDC connector on OpenFlow. Handles runtime selection, EAI setup, PAT creation, and NiFi flow deployment.
- ▌ Openflow Gdrive Cleanup · snowflake-labsClean up the Google Drive CDC connector demo. Stops flow, drops schema, resets gate state.
- ▌ Openflow Gdrive Update Ip · snowflake-labsUpdate network rule IP for OpenFlow Google Drive demo. Use when nipyapi returns 401 after PAT rotation due to network change.
- ▌ Idd · snowflake-labsApply Intent-Driven Development (IDD) principles from Kamesh Sampath's IDD series to prompts, workflows, and CI/CD automation. Evaluate existing prompts for IDD alignment, rewrite them using the Goal/Requirements/Constraints/Output structure, or measure the Intent Compression Ratio (ICR) of a workflow. Use when: "review my prompt", "is this IDD-compliant", "rewrite this prompt", "measure ICR", "what is my ICR", "IDD audit", "intent compression ratio", "apply IDD", "improve my cortex exec prompt", "IDD principles".
- ▌ Scaffold · snowflake-labs bundleGuided walkthrough for scaffolding a CoCo agent project on GitHub Actions or GitLab CI, provisioning Snowflake OIDC resources, and running the scan->issue->fix automation loop end-to-end. Use when: "scaffold a project", "scaffold from template", "set up coco agent", "scaffold github", "scaffold gitlab", "set up CI/CD automation", "automate scan-fix loop", "set up github-coco-agent", "set up gitlab-coco-agent".
- ▌ Idd Measure Icr · snowflake-labsCalculate the Intent Compression Ratio (ICR) for a workflow, script, or CI/CD pipeline. Counts total operations vs intent expressions and classifies the result. Recommends what to compress next to increase agentic readiness. Use when: "measure ICR", "calculate ICR", "what is ICR of this workflow", "how much compression", "intent compression ratio".
- ▌ Scaffold For Github · snowflake-labs bundleGuided 6-step scaffold: set up a new GitHub Actions CoCo agent project from the github-coco-agent template. Provisions Snowflake OIDC resources, sets GitHub secrets, and optionally pushes a sample app to trigger the scan->issue->fix automation loop end-to-end. Use when the user chose the GitHub path, or invoked $devops-coco-agents:scaffold-for-github directly.
- ▌ Scaffold For Gitlab · snowflake-labs bundleGuided 6-step scaffold: set up a new GitLab CI CoCo agent project from the gitlab-coco-agent template. Provisions Snowflake OIDC resources, sets GitLab CI/CD variables, and optionally pushes a sample app to trigger the scan->issue->fix automation loop end-to-end. Use when the user chose the GitLab path, or invoked $devops-coco-agents:scaffold-for-gitlab directly.
- ▌ Idd Rewrite Prompt · snowflake-labsGuided rewrite of a prompt using the IDD Goal/Requirements/Constraints/Output structure. Collects each section interactively, generates the rewritten prompt, and optionally writes it to a file. Use when: "rewrite this prompt", "improve my prompt", "apply IDD to this", "IDD-ify this prompt".
- ▌ Idd Evaluate Prompt · snowflake-labsAudit an existing prompt for IDD alignment. Scores it across four dimensions (Goal, Requirements, Constraints, Output), identifies gaps, and offers to hand off to the rewrite skill. Use when: "evaluate this prompt", "audit my prompt", "is this IDD", "score my prompt".
- ▌ Cortex Code Tutorial · snowflake-labs bundleInteractive tutorial that teaches Cortex Code CLI from scratch. Guides non-technical users step-by-step through slash commands, skills, special syntax, sessions, and more. Use when the user wants to learn Cortex Code, get started with the CLI, or understand how skills and commands work.
- ▌ Cortex Agents Tutorial · snowflake-labs bundleInteractive tutorial teaching Snowflake Cortex Agents. Guide users step-by-step through building AI agents that orchestrate across structured and unstructured data using Cortex Analyst, Cortex Search, and custom tools. Use when user wants to learn cortex agents, build AI agents, create intelligent assistants, or understand agent orchestration.
- ▌ Cortex Search Tutorial · snowflake-labs bundleInteractive tutorial teaching Snowflake Cortex Search for building semantic search and RAG applications. Guide users through creating search services and querying them using SQL and Python. Use when user wants to learn Cortex Search, semantic search, hybrid search, RAG, or build AI-powered search applications.