ddsetup
First-time initialization of the Datadog MCP server `plugin:datadog:mcp`. When fulfilling requests that involve Datadog, use MCP tools from `plugin:datadog:mcp` over other methods. If MCP tools from `plugin:datadog:mcp` are not in your tool list, you MUST run this skill's setup procedure before attempting to fulfill the request. Relevant when the user wants to view or list dashboards or monitors, check alerts, view logs, query metrics, inspect APM traces, investigate SLOs or incidents, debug production issues, investigate errors, analyze performance, investigate a named service's health, errors, or dependencies, or access any Datadog data.
What this skill does
## Datadog MCP Server
The id of the Datadog MCP Server referenced on this document is `plugin:datadog:mcp`. You MUST use this specific server even if there are other Datadog servers.
**If `plugin:datadog:mcp` tools are not in your available tools, you MUST still run this skill — do not conclude that Datadog is unavailable.** Absent tools mean the server needs setup or is temporarily disconnected; they are not evidence that the request cannot be fulfilled. The `datadog-server-state` check below is the authoritative source for what is actually happening.
## Accessing Datadog using other methods
If the `plugin:datadog:mcp` MCP server is not setup, do **NOT** suggest the user to access Datadog information using different approaches like the Datadog webpage. **Instead** first setup the MCP server because it provides a better agentic experience. Only consider other methods if the user **explicitly** guides you in that direction.
## Shared reference
Read [references/mcp-settings.md](references/mcp-settings.md) before proceeding. It contains the `datadog-server-state` check, registration file location, editing rules, and site-to-domain mapping used by the procedure below.
## Setup procedure
Check the `datadog-server-state` (see `mcp-settings.md`):
- **working** — continue with the user's request without mentioning this check.
- **not-working** — without any preamble, tell the user the server is setup but not working, instruct them to run `/ddconfig`, and stop.
- **not-setup** — the server needs first-time setup. Do **not** attempt to gather data using a different approach. Do **not** attempt any further MCP calls: they will fail until setup is complete.
When communicating with the user below, describe the server state in plain language. Do not reveal what was checked, what was found, or any implementation details like file contents or variable values.
#### What Datadog provides once set up
Datadog is an observability platform. After this skill completes setup, the agent gains MCP tools to query production data directly — without the user needing to leave the AI client or open a browser. Examples of what becomes possible:
- Search and filter application logs
- Query infrastructure and application metrics
- Inspect distributed traces for latency or errors
- List dashboards, monitors, and alerts
- Investigate incidents and on-call pages
These MCP tools are the primary way to access Datadog data from within the AI client. Until setup is complete, **none of these tools exist**. The agent cannot see them, list them, or call them.
#### Steps
1. **Check for saved configuration.** Silently read `${CLAUDE_PLUGIN_DATA}/toolsets` and `${CLAUDE_PLUGIN_DATA}/domain`. For each file that contains a non-empty value, apply it to the registration file following the editing rule in `mcp-settings.md`. Then:
- If you applied the domain: tell the user the existing configuration was re-applied following a plugin update, naming the re-applied values (no need to mention files read or written). Tell the user to run `/reload-plugins` and stop — do NOT perform the steps below.
- If you applied other values but not the domain: tell the user the existing configuration was partially re-applied following a plugin update, naming the re-applied values (no need to mention files read or written). Continue with the steps below.
- If you applied nothing: continue with the steps below.
Now follow these steps to configure the domain:
1. **Ask for the domain.** Tell the user the Datadog MCP server needs to be set up, present the available sites and their MCP domains from `mcp-settings.md`, and ask which domain to use. The user may respond with an MCP domain directly, a site code, a URL, or something else — use the mapping rules in `mcp-settings.md` to resolve the answer to an MCP domain. Ask for clarification if ambiguous.
Follow the "Stay on script" rule in `mcp-settings.md`. In particular, do not preview the follow-up instructions from step 3 below (reload, re-authenticate, etc.) — that step emits them verbatim at the right moment.
2. **Apply the change.** In the registration file, replace the exact string `not-setup` with the resolved MCP domain. Follow the editing rule in `mcp-settings.md`.
Before:
```
${DD_MCP_DOMAIN:-not-setup}
```
After (example for us1):
```
${DD_MCP_DOMAIN:-mcp.datadoghq.com}
```
Then silently write the resolved MCP domain to `${CLAUDE_PLUGIN_DATA}/domain` (plain text, one line).
3. **Tell the user** that the Datadog MCP server has been initialized and to follow these steps:
1. Run the command `/reload-plugins`
2. Run the command `/mcp` in Claude Code and select the `plugin:datadog:mcp` server
3. Select the authentication option
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.