Adp

Redpanda's Agentic Data Plane: governance infrastructure for building, running, and governing AI agents and MCP servers behind a credential-injecting AI Gateway for LLM providers, operated through the `rpk ai` CLI and the ADP UI at ai.redpanda.com. Use when installing `rpk ai`, signing in to an environment, checking setup with `rpk ai doctor`, managing managed or self-managed AI agents and their triggers with `rpk ai agent` and `rpk ai trigger`, configuring remote or managed MCP servers with `rpk ai mcp-server` (including code mode and user-delegated OAuth), setting up LLM providers and models

9 stars 4 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add redpanda-data/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add redpanda-data/skills --skill adp
Manual install
git clone --depth 1 https://github.com/redpanda-data/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/adp ~/.claude/skills/adp

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agentic Data Plane

The Agentic Data Plane (ADP) runs AI agents and MCP servers behind an AI Gateway that injects
LLM provider credentials. Operate it with the `rpk ai` CLI, and send the user to the ADP UI
(ai.redpanda.com) for tasks the CLI does not cover. This skill keeps only the procedures below.
Look up everything else in the docs (last section).

Governance (access policies, budgets, guardrails, the kill switch, secrets, API keys, OAuth) is
in `/redpanda:adp-governance`. Transcripts, the audit log, and traces are in
`/redpanda:adp-observability`.

## How to work

**Put `enabled: true` in a trigger manifest you apply.** In an `rpk ai trigger apply` manifest,
a missing `enabled` means false, so the trigger is created or left paused and never fires, even
though `rpk ai trigger create` enables a trigger by default. Before you apply a trigger manifest
the user wants live, add `enabled: true`, then confirm with `rpk ai trigger list`.

**Build a GitOps manifest from the live resource before `apply`.** `rpk ai <group> apply` treats
a manifest as the complete desired state, so a field you leave out is cleared on the live
resource. For a change to an existing agent, provider, MCP server, or trigger, start from
`rpk ai <group> get <name> -o yaml`, change only what the user asked for, and check the result
with `diff` before `apply`. Never apply a hand-written partial manifest to an existing resource.

## Use the docs for everything else
Read the full skill on GitHub

Details

Skill name
adp
Path
skills/adp/SKILL.md
License
Apache-2.0
Repo updated
16 November 2026

FAQ

What does the Adp skill do?

Redpanda's Agentic Data Plane: governance infrastructure for building, running, and governing AI agents and MCP servers behind a credential-injecting AI Gateway for LLM providers, operated through the `rpk ai` CLI and the ADP UI at ai.redpanda.com. Use when installing `rpk ai`, signing in to an environment, checking setup with `rpk ai doctor`, managing managed or self-managed AI agents and their triggers with `rpk ai agent` and `rpk ai trigger`, configuring remote or managed MCP servers with `rpk ai mcp-server` (including code mode and user-delegated OAuth), setting up LLM providers and models

How do I install the Adp skill?

Claude Code plugin: /plugin marketplace add redpanda-data/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Adp popular?

It lives in redpanda-data/skills, which has 9 GitHub stars and 4 forks.

Related skills

Adp Governance

9

redpanda-data/skills

Govern what Agentic Data Plane agents may do, spend, and expose, through the `rpk ai` CLI and the ADP UI at ai.redpanda.com, and look up governance features in the Redpanda docs. Use when writing or debugging a Cedar access policy with `rpk ai policy`, giving a new agent access, capping agent spend with `rpk ai budget`, analyzing cost, attaching a guardrail to a provider, containing or releasing an agent with the kill switch, storing or deleting a credential with `rpk ai secret`, minting an API key, masking MCP tool data with data policies, or setting up inbound or outbound OAuth. For signing

AI, LLMs & Agents

Adp Observability

9

redpanda-data/skills

Read what Agentic Data Plane agents did and why, through traces, conversation transcripts, the audit log, and the monitoring views in the ADP UI at ai.redpanda.com and the `rpk ai` CLI. Use when finding which call made an agent run slow, failed, or expensive with `rpk ai trace`, reading or filtering a conversation with `rpk ai agent transcript`, finding conversations with a failed tool call, investigating a denied or masked call with `rpk ai auditlog`, working out on whose behalf an agent acted, or reading the Agent network or Home views. For budgets, cost, and access policies, see `/redpanda:

DevOps & Cloud

Cloud Byoc

9

redpanda-data/skills

Provisions, changes, and tears down Redpanda Cloud BYOC (Bring Your Own Cloud) clusters through the Control Plane API and the `rpk cloud byoc` plugin, where the VPC, IAM roles, and storage stay in your own AWS, GCP, or Azure account. Use when creating or deleting a BYOC cluster or its Network, running `rpk cloud byoc` apply, destroy, or validate, scaling a BYOC cluster, editing its cloud provider tags or cluster properties, configuring its private connectivity and listeners, or setting up Shadow Link disaster recovery, cross-account AWS access, or Enterprise features such as Tiered Storage on

DevOps & Cloud

Vincent Twitter / X.com for Agents

5

HeyVincent-ai/agent-skills

Twitter/X.com data access for agents. Use this skill when users want to search tweets, look up user profiles, or retrieve recent tweets. Pay-per-call via Vincent credit system. Triggers on "search tweets", "twitter", "X.com", "look up user", "tweet search", "twitter profile", "recent tweets".

AI, LLMs & AgentsIn 1 list

Cue Data MCP

8

sensedeal/cue-skills

Use when the user wants an external AI agent to query Cue's public MCP data services — regulatory, macro, disclosures, market data, legal full text, holdings, entity data, academic, IPO, ESOP, buyback, footnote details — by discovering and connecting to live MCP endpoints.

AI, LLMs & AgentsIn 1 list

Vincent Polymarket for Agents

5

HeyVincent-ai/agent-skills

Polymarket prediction market trading for agents. Use this skill when users want to create a Polymarket wallet, browse markets, place bets, manage positions, or withdraw funds. Triggers on "polymarket", "prediction market", "place bet", "browse markets", "trade prediction", "polymarket wallet", "betting", "market odds".

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.