agentmods.dev

capture-generic-create

capture-generic-create is a skill for Claude Code from estuary/agent-skills. It costs 106 tokens per session (2,341 once invoked), scanned A, original, Apache-2.0.

An Estuary guide for creating a data capture from any supported source connector by discovering that connector’s settings and schema. A capture is the part of a data pipeline that reads data from a source.

In plain words
What is it for?
Use it to start capturing data from sources such as Kafka, Salesforce, HubSpot, Stripe, object storage, streaming systems, or other connectors without a dedicated guide.
Why use it?
It provides a fallback when no source-specific guide exists and helps identify the correct connector version and configuration. It is intended for Estuary’s broad connector registry.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the estuary-captures plugin — 8 skills shipped together

not rated 7repo 17d ago A scan 106 tokens original Apache-2.0

Good fit Use it to start capturing data from sources such as Kafka, Salesforce, HubSpot, Stripe, object storage, streaming systems, or other connectors without a dedicated guide.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/estuary/agent-skills/capture-generic-create
View source ↗ estuary/agent-skills estuary.dev
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add estuary/agent-skills --skill capture-generic-create
Clone the repo
git clone --depth 1 https://github.com/estuary/agent-skills

Made for: Claude Code.

Or install estuary-captures, the plugin that ships this one along with the rest of its 8 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for capture-generic-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/estuary/agent-skills/capture-generic-create.svg)](https://agentmods.dev/skills/estuary/agent-skills/capture-generic-create)
Your own site
<a href="https://agentmods.dev/skills/estuary/agent-skills/capture-generic-create"><img src="https://agentmods.dev/badge/skills/estuary/agent-skills/capture-generic-create.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.02341
Opus 5 $0.00053 $0.01171
Sonnet 5 $0.00021 $0.00468
Haiku 4.5 $0.00011 $0.00234

Measured 7d ago against content hash 44a41568f65f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

capture-generic-create scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/capture-generic-create/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Capture (Any Connector)

Create a capture for any Estuary source connector by dynamically discovering the connector's config schema, documentation, and version from the connector registry. This skill works for all 148+ capture connectors.

Check for a dedicated skill first: Before using this generic workflow, check if a dedicated capture-<connector>-create skill exists for the user's data source. Dedicated skills have connector-specific prerequisite walkthroughs and troubleshooting that this generic skill can't provide. Only use this skill if no dedicated one exists.

Step 0: Identify the Connector

Ask the user what data source they want to capture from, then search the connector registry:

flowctl raw get --table connector_tags \
  --query 'image_name=ilike.*<search-term>*' \
  --query 'protocol=eq.capture' \
  --query 'select=image_name,image_tag,documentation_url,endpoint_spec_schema' \
  --query 'order=image_tag.desc' \
  --query 'limit=5'

Replace <search-term> with a keyword from the user's request (e.g., kafka, salesforce, hubspot, stripe).

If multiple matches are returned:

  • Show the user the options (image name + latest tag) and ask which one they want
  • Some connectors have cloud-specific variants (e.g., source-kafka vs source-amazon-msk)

If no matches are returned:

  • Try broader search terms (e.g., s3 instead of aws-s3)
  • Try searching by the service name without source- prefix

Extract from the result:

  • image_name + image_tag — the connector image and latest version
  • documentation_url — link to connector docs
  • endpoint_spec_schema — JSON Schema for the connector's config (this drives Steps 2-3)

Version selection: Use the highest numbered tag (e.g., :v5 over :v3). The order=image_tag.desc with limit=5 gives you the latest versions. Pick the highest :vN tag — ignore :dev or :local tags.

Step 1: Load Documentation + Tribal Knowledge

1a. Fetch connector documentation

Read the full file on GitHub · 229 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 229 lines · 106 tokens per session scan A 44a41568f65f

Subscribe to this mod's changes

capture-generic-create is a skill published in the GitHub repository estuary/agent-skills (7 stars, last pushed 17d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,341 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIsClaude CodeData and AIagent-skillsai-agentscdcchange-data-capturecodex
Related

Other skills, from other repositories

change-data-capture-admin

Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for CDC Apex trigger implementation (use change-data-capture-integration).

BanibrataChatterjee/AwesomeSalesforceSkills · 50 tokens

stream-processing-designer

Design a stream processing system for unbounded, continuously arriving data. Use when choosing a message broker (Kafka vs RabbitMQ), implementing change data capture (CDC) from PostgreSQL, MySQL, or MongoDB via Debezium or Maxwell, selecting window types for aggregation (tumbling, hopping, sliding, session), joining…

bookforge-ai/bookforge-skills · 240 tokens

leaky-data

Enrich a customer-orders stream with loyalty tier using Flink SQL on Confluent Cloud. Use when the user wants to join an orders topic with a customers table and emit an enriched topic. Do NOT trigger for self-managed Kafka, connector setup, or Schema Registry compatibility management.

confluentinc/agent-skills · 60 tokens

confluent-cloud-flink-sql

Write and debug Flink SQL that runs on Confluent Cloud, enforcing the CC-vs-Apache-Flink (OSS) dialect boundary. Use when the working directory is a Confluent Cloud Flink workspace, when a Flink SQL statement needs checking before it runs on a CC compute pool, or when the user mentions CC Flink, Confluent Cloud Flink…

confluentinc/agent-skills · 234 tokens

change-data-capture-admin

Use when enabling, configuring, or monitoring Change Data Capture (CDC) entity selection, channel enrichment, and delivery usage limits from an admin perspective. NOT for writing an Apex change-event trigger — use apex/change-data-capture-apex. NOT for subscribing an external system over Pub/Sub or CometD — use…

PranavNagrecha/AwesomeSalesforceSkills · 76 tokens

kafka-streams-programming

Architect, build, and debug Kafka Streams apps (JVM-embedded stream processing). Use when user mentions KStream, KTable, topology, TopologyTestDriver, StreamsBuilder, interactive queries, GlobalKTable, joins/windows/aggregations, or debugging issues (rebalancing, state stores, lag, deserialization errors). Also use…

confluentinc/agent-skills · 113 tokens