Agent Skills

by datadog-labs

Set up the Datadog Azure integration with Terraform - creates an Entra ID app registration and service principal, assigns Monitoring Reader across the chosen subscriptions and management groups, grants the Microsoft Graph permissions Datadog needs for resource discovery, and registers the tenant so Azure metrics and resource collection start flowing. Use when the user wants to monitor Azure VMs, App Service, SQL Database, or AKS, wants to connect an Azure subscription or management group or tenant to Datadog, or asks to set up or repair the Azure integration. Does not set up log forwarding.

dd-aws-integration

by datadog-labs

Set up the Datadog AWS integration with Terraform - creates the cross-account IAM role Datadog assumes (external ID, no stored credentials), attaches the permission policies Datadog publishes, and registers the account through datadog_integration_aws_account so AWS metrics, the resource catalog, and CSPM findings start flowing. Use when the user has AWS resources they want to monitor, wants to connect an AWS account to Datadog, asks to set up or repair the AWS integration, or needs the Datadog IAM role and external ID provisioned. Does not set up log forwarding.

dd-account-setup

by datadog-labs

Ensure the user has an authenticated Datadog account with a valid DD_API_KEY on the right region before any Datadog setup or instrumentation. Detects existing DD_API_KEY / DD_APP_KEY / DD_SITE, validates them against the Datadog API, and fixes the common wrong-region 403. If no usable key exists, signs the user in (OAuth) or creates a new account, then obtains and validates a key. Use this whenever a user needs a Datadog account or API key, hits a 403 / wrong-region error, or is about to run any Datadog *-setup or instrumentation skill.

agent-observability-replay-trace

by datadog-labs

Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.

agent-observability-experiment-bootstrap

by datadog-labs

Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK. Use for experiment, dataset, evaluator, benchmark, regression, or LLM-as-a-judge scaffolding. The legacy Python invocation remains supported.

agent-observability-build-eval-from-annotations

by datadog-labs

Fit a Datadog LLM-Obs evaluator to human labels. Takes an annotation queue, works out where in the trace the labelled property actually lives, drafts an LLM-judge that predicts the human label, scores that judge against the already-labelled rows with a metric agreed with the user, then hill-climbs it — inspect the errors, make one focused change, re-score, keep it only if it beats the best — for a bounded number of iterations, and finally publishes the winner to Datadog as a DISABLED evaluator (not a Datadog draft — a real evaluator with `enabled: false`). Use when the user says "build an eval from my annotations", "build an evaluator from the annotation queue", "turn my annotations into an evaluator", "learn an evaluator from my labels", "fit a judge to the annotation queue", "auto-label", "auto labelling", "automate this annotation queue", "scale up my human labels", or wants the rest of a queue graded the way the humans graded the first rows. Needs an annotation queue with at least two classes present in the human labels (e.g. one true and one false for a boolean).

agent-observability-auto-experiment

by datadog-labs

Run an iterative code-improvement hill-climb against real Datadog LLM-Obs data, locally, with Claude Code as the agent. Establishes a baseline eval, makes one focused change, re-scores with the same harness, keeps the change if it improves the score in the goal's direction (labeling within-noise gains tentative), and repeats. Use when the user says "run an auto experiment", "hill-climb this code", "iteratively improve X and measure the delta", "optimize this prompt/file against my traces", "auto-optimize against LLM-Obs", or wants the local equivalent of the auto_experiments worker. Works from an ml_app, a dataset_id, an annotation_queue_id (a queue of human-labelled interactions), a list of trace_ids, or (by exception) a local dataset file. The corpus and its val/test splits live in Datadog LLM-Obs Datasets, created once per run with a timestamp in their names.

notion-spec-to-implementation

by notion

Converts Notion product or technical specs into implementation plans, linked tasks, and evidence-based progress updates. Use for planning or implementing a spec, creating tasks from requirements, or reconciling implementation with spec changes.

notion-research-documentation

by notion

Researches questions across Notion sources and synthesizes cited briefs, comparisons, or reports. Use when answering requires discovering and reconciling workspace information, optionally with external research, and returning or saving the findings.

notion-meeting-intelligence

by notion

Prepares meeting agendas, internal pre-reads, and decision briefs using Notion context and relevant research. Use for meeting preparation, recurring meeting context, or updating meeting outcomes; use knowledge-capture for a standalone record of an existing discussion.

notion-knowledge-capture

by notion

Captures conversations and supplied notes as Notion wiki pages, how-to guides, FAQs, decision records, or retrospectives. Use when saving or updating durable knowledge from existing context; use research-documentation when new source discovery and synthesis is the main task.

dv-connect

by microsoft

One-step setup for a Dataverse environment — installs tools, authenticates, registers the MCP server, and writes `.env`. Use when starting a new project, switching environments, fixing authentication, or troubleshooting an MCP connection that won't come up.

dv-security

by microsoft

Security-role assignment, user access, application users, business units, and admin self-elevation in Dataverse environments. Use when the user wants to give someone access, grant a role, become an admin, or add a service principal.

dv-overview

by microsoft

Tool routing and cross-cutting rules for Dataverse work — which skill applies to which task, environment-confirmation, and pull-to-repo. Use when the user mentions Dataverse, Dynamics 365, Power Platform, or CRM; this skill picks the specialist (dv-connect / dv-data / dv-metadata / dv-query / dv-solution / dv-admin / dv-security) for the request.

🔥🔥✓ VerifiedFree

dv-data

by microsoft

Record-level CRUD and bulk operations via the Python SDK — create, update, delete, upsert, CSV import, multi-table foreign-key loads, AI-generated sample data. Use when the user wants to write, modify, seed, or import data records into Dataverse tables.

dv-metadata

by microsoft

Dataverse schema authoring via the Python SDK and Web API — tables, columns, relationships, forms, and views. Use when the user wants to define or evolve the data model — add a column, create a table, set up a lookup, customize a form, or build a view.

dv-query

by microsoft

Bulk reads, multi-page iteration, and analytics over Dataverse data via the Python SDK and Web API. Use when the user wants to read, list, filter, aggregate, group, join, or analyze records — including pandas DataFrame workflows and notebook exploration.

dv-solution

by microsoft

Dataverse solution lifecycle — create, export, import, promote across environments, and validate deployments. Use when the user wants to package customizations, deploy to another environment, or move work between dev / test / prod.

dv-admin

by microsoft

Environment-level Dataverse administration — bulk delete, retention/archival, organization settings, OrgDB settings, recycle bin, audit, and the 37 allowlisted PPAC toggles. Use when the user wants to clean up data at scale, configure audit, change environment settings, or manage retention policies.

suggest

by brave

USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.

answers

by brave

USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.

🔥🔥🔥🔥✓ VerifiedFree

local-descriptions

by brave

USE FOR getting AI-generated POI text descriptions. Requires POI IDs obtained from web-search (with result_filter=locations). Returns markdown descriptions grounded in web search context. Max 20 IDs per request.

🔥🔥✓ VerifiedFree

local-pois

by brave

USE FOR getting local business/POI details. Requires POI IDs obtained from web-search (with result_filter=locations). Returns full business information including ratings, hours, contact info. Max 20 IDs.

🔥🔥Free

llm-context

by brave

USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.

🔥🔥🔥🔥✓ VerifiedFree

images-search

by brave

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

bx

by brave

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking

🔥🔥🔥🔥✓ VerifiedFree

news-search

by brave

USE FOR news search. Returns news articles with title, URL, description, age, thumbnail. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.

videos-search

by brave

USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.

bx-search

by brave

Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google this", and any request needing current or external information. Prefer this over the built-in web_search tool whenever bx is available. Also use for: documentation lookup, troubleshooting research, RAG grounding, news, images, videos, local places, and AI-synthesized answers.

Needs API keys

spellcheck