Adp Observability
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:
Install
/plugin marketplace add redpanda-data/skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add redpanda-data/skills --skill adp-observabilitygit clone --depth 1 https://github.com/redpanda-data/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/adp-observability ~/.claude/skills/adp-observabilityPersonal 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: Observability The Agentic Data Plane (ADP) keeps three records of what ran: traces (`rpk ai trace`), conversation transcripts (`rpk ai agent transcript`) and the audit log (`rpk ai auditlog`). The docs cover all of them, so this skill carries no procedure of its own. Sign in and select an environment first, as described in `/redpanda:adp`. ## Use the docs Look up commands, flags, filters, columns, statuses, permissions and UI views in the docs instead of from memory: - Follow `/redpanda:redpanda-docs`. Use `get_rpk_command` for one `rpk ai` command's flags and help (for example `rpk ai auditlog list`), `list_rpk_commands` with `plugin: "ai"` to find a command, and `ask_redpanda_question` for everything else. ADP docs are not versioned, so pass no `version`. - The ADP docs live at https://docs.redpanda.com/agentic-data-plane/. Most useful pages: https://docs.redpanda.com/agentic-data-plane/monitor/traces/, https://docs.redpanda.com/agentic-data-plane/monitor/transcripts/, https://docs.redpanda.com/agentic-data-plane/monitor/audit-log/ and https://docs.redpanda.com/agentic-data-plane/monitor/agent-network/. If the Docs MCP server refuses for quota and you can't fetch the page, tell the user to sign in through `/mcp` rather than answering from memory. `rpk ai <command> --help` on the installed plugin is the live check for flags in that version.
Details
- Skill name
adp-observability- Repository
- redpanda-data/skills
- Path
skills/adp-observability/SKILL.md- License
- Apache-2.0
- Repo updated
- 16 November 2026
FAQ
What does the Adp Observability skill do?
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:
How do I install the Adp Observability 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 Observability popular?
It lives in redpanda-data/skills, which has 9 GitHub stars and 4 forks.
Related skills
Adp
9redpanda-data/skills
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
Adp Governance
9redpanda-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
Cloud Byoc
9redpanda-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
Create Pasqal Cloud Account
9pasqal-io/agent-marketplace
Get access to Pasqal Cloud - create the account on portal.pasqal.cloud and optionally couple it to Google Cloud Marketplace, which is what makes real QPUs and the advanced emulators available. For requests such as "create a Pasqal Cloud account", "I need a PASQAL_PROJECT_ID", "subscribe to Pasqal on GCP Marketplace", "how do I run on FRESNEL", or "my project only shows EMU_FREE". Access only, not running experiments. Unsure which route fits? Use choose-access-method.
Cloud Byoc Sizing
9redpanda-data/skills
Estimates the Redpanda units (RPUs) and the supported broker deployment that a Kafka workload needs on AWS, GCP or Azure, for a single point in time or as a projection over months or quarters, by running a bundled zero-dependency sizing script. Use when sizing or capacity-planning a BYOC cluster from ingress and egress throughput and partition counts; working out how many RPUs or brokers a workload needs and which resource limit drives that number; projecting cluster size and RPU-hours as a workload grows or as new workloads come online; finding the month a growing workload must scale up or ou
Schrodinger AWS Hpc Ssm Connector
5bioteam/claude-science-hpc-integrations
Connect Claude Science to a remote Schrödinger Suite jobserver running on an AWS ParallelCluster (or any Slurm HPC) that is reachable only through AWS SSM, and submit/monitor/harvest Schrödinger jobs from it. Use this skill whenever the user mentions Schrödinger, jobserver, jsc, testapp, Maestro, Glide, Desmond, FEP+, or MMLIBS licensing on a remote cluster; whenever they want to reach an HPC head node "over SSM", "through Session Manager", "in a private subnet", or via an ssh_config ProxyCommand; or whenever an SSH compute provider that proxies over SSM fails to connect. It covers reducing SS
Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.