Estuary Agent Skills

Set up Estuary data pipelines through your AI assistant. No docs to stitch together, no flowctl commands to remember.

Ask your AI to "capture my Postgres into Snowflake" or "why is this materialization failing?" — these skills give it everything it needs to run the right commands, build the right specs, and explain the gotchas.

Works with Claude Code, GitHub Copilot, Cursor, OpenAI Codex, Gemini CLI, and 30+ other tools via the open SKILL.md standard.

Which skills do I need?

You can do all of this without these skills. Install a group when you want your AI assistant to know the workflow and the gotchas. Install only what you need.

If you want help with	Install
Setting up a source	estuary-captures, only the skills for your sources
Setting up a destination	estuary-materializations, only the skills for your destinations
Writing a derivation	estuary-derivations, derivation-basics plus the types you use
Changing how fields materialize	estuary-schema
Running and troubleshooting pipelines	estuary-operations

What's included

Captures (sources)

Install these if you want help creating captures, only the ones matching your sources.

Skill	Description
capture-postgres-create	PostgreSQL CDC (vanilla, RDS, Aurora, Cloud SQL, Supabase, Neon)
capture-mysql-create	MySQL CDC via binlog replication (RDS, Aurora, Cloud SQL, Azure)
capture-mongodb-create	MongoDB CDC (Atlas, DocumentDB, self-hosted)
capture-sqlserver-create	SQL Server CDC (RDS, Azure SQL, Cloud SQL)
capture-alpaca-create	Alpaca stock trade data (historical backfill + real-time websocket stream)
capture-hubspot-create	HubSpot real-time CRM capture (contacts, companies, deals, tickets)
capture-http-ingest-create	HTTP webhook capture (GitHub, Shopify, Stripe, or any JSON source)
capture-generic-create	Any of 148+ source connectors via dynamic schema discovery

Materializations (destinations)

Install these if you want help creating materializations, only the ones matching your destinations.

Skill	Description
materialize-postgres-create	PostgreSQL destination
materialize-snowflake-create	Snowflake destination (JWT auth)
materialize-bigquery-create	BigQuery destination (GCS staging)
materialize-redshift-create	Amazon Redshift destination (S3 staging)
materialize-databricks-create	Databricks destination (Unity Catalog)
materialize-clickhouse-create	ClickHouse destination (native protocol)
materialize-hubspot-create	HubSpot CRM write-back (contacts, companies, deals, tickets)
materialize-generic-create	Any destination connector via dynamic schema discovery

Derivations (transformations)

Install these only if you write derivations. Start with derivation-basics, then add the types you use.

Skill	Description
derivation-basics	Foundation: what derivations are, language choice, project layout, and workflow — read first
derivation-filter-transform	Stateless filtering, field selection, and per-document field transformation
derivation-aggregate-metrics	Daily totals, running counts, min/max, and lifetime metrics via reduction annotations
derivation-join-collections	Join two or more collections on a shared key into an enriched collection
derivation-flatten-array	Flatten a nested array into one output document per element
derivation-stateful-logic	Custom SQLite state for balances, inventory, approval workflows, and deduplication
derivation-windowing	Sliding time-window state (e.g. last-24h events) via readDelay expiration
derivation-python	Write derivations in Python (async transforms, Pydantic types, uv deps) for ML/embeddings/async APIs

Operations

Install these if you want help running and troubleshooting pipelines.

Skill	Description
estuary-flowctl-setup	Install, authenticate, and update the flowctl CLI
estuary-task-health	End-to-end health check for a task: status, data flow, errors, and history
estuary-catalog-status	Check control-plane status of a task with flowctl catalog status
estuary-task-stats	Inspect data volume, document counts, and hourly throughput for a task
estuary-catalog-history	Review publication history and recent spec changes
estuary-logs	Search and analyze task logs with jq filtering
estuary-connector-restart	Pause and restart connectors via shard management
estuary-ssh-tunnels	Diagnose and fix SSH tunnel connection issues

Schema

Install these only if you modify how fields materialize.

Skill	Description
schema-projections	Rename fields or map nested JSON paths to flat column names
schema-field-selection	Include or exclude fields in materializations using depth modes and overrides
schema-custom-types-ddl	Override default column types via castToString or custom DDL
schema-field-redaction	Block or hash sensitive fields (PII, credentials)
schema-null-defaults	Set default values for missing fields and handle nullable primary keys
schema-define-fields	Add or define fields in a collection's readSchema (pruned, refined, or required)

Prerequisites

• An Estuary account
• flowctl CLI — the estuary-flowctl-setup skill walks you through installation and authentication

Installation

Skills CLI

Install all 37 skills:

npx skills add estuary/agent-skills

Or list them and pick:

npx skills add estuary/agent-skills --list
npx skills add estuary/agent-skills --skill capture-postgres-create --skill materialize-snowflake-create

Claude Code

Add the Estuary marketplace:

/plugin marketplace add estuary/agent-skills

Then install only the groups you need:

/plugin install estuary-captures@estuary
/plugin install estuary-materializations@estuary
/plugin install estuary-derivations@estuary
/plugin install estuary-operations@estuary
/plugin install estuary-schema@estuary

Or run /plugin to browse from the Discover tab. Installed skills auto-update when the marketplace refreshes.

Manual installation

Clone this repo and copy the skill folders into your AI tool's skill directory:

git clone https://github.com/estuary/agent-skills.git
cp -r agent-skills/skills/* your-project/.claude/skills/

Common paths by tool:

Tool	Path
Claude Code	.claude/skills/
Cursor	.cursor/skills/
GitHub Copilot / VS Code	.github/skills/
OpenCode	.opencode/skills/
Codex	.codex/skills/

Usage

Once installed, ask your AI assistant in plain English:

"Capture my Postgres database into Estuary"

"Materialize my collections into Snowflake"

"Capture from MySQL and materialize into Redshift"

"Why is my materialization failing?"

Resources

• Estuary documentation
• Estuary MCP integration
• flowctl CLI installation
• Connector catalog
• SKILL.md standard

Feedback and support

• Open an issue in this repo
• Join the Estuary Slack community
• Contact support@estuary.dev

License

Apache 2.0 — see LICENSE for details.