Google Agent Skills
google/skillsGoogle's official collection of about 180 skills for Google Cloud, Gemini APIs, Analytics, Data Manager, sign-in and other Google products.
Single-file Microsoft skill for querying Azure Data Explorer (Kusto) with KQL: query patterns, schema discovery and best practices.
Official and correct, but one file of generic KQL patterns; the batch-search tip is the main addition over what a model already knows.
azure-kusto is a one-file skill (about 8.5 KB) for working with Azure Data Explorer. It describes a four-step workflow: discover clusters and databases in the subscription, explore the schema of the target tables, run KQL queries, then analyze the results. The body contains six query patterns with example KQL: basic retrieval with a time filter, aggregation with summarize and bin, time-series analysis with percentiles and render timechart, joins across tables, schema discovery through the kusto_table_schema_get tool, and a batch-search pattern for locating a table when several candidate clusters, databases or Log Analytics workspaces exist (check them all before saying 'not found'). It adds notes on common field names, how results are returned, KQL best practices (filter early, project only needed columns, use take for exploration) and a list of frequently used functions. It relies on the Azure MCP server's Kusto tools for execution and contains no scripts or reference files.
One 8.5 KB SKILL.md with example queries; no references, scripts or evals.
A single-file skill with KQL query patterns for Azure Data Explorer. It runs queries against your clusters through Azure MCP tools or az rest using your signed-in Azure identity.
The skill folder (1 files) on Oct 29, 2026. Not a full review: it relies on code outside the repository: Azure CLI (az) and the az extensions it installs on demand; not part of the files we have; Azure MCP Server, started by the plugin through npx; its configuration sits outside this skill folder.
NVIDIA SkillSpector static scan: 0 pattern hits. No SkillSpector hits; the skill is a single SKILL.md of KQL query patterns.
A review, not a certification. Skills change after we check them — read the files before installing.
MIT (declared in the SKILL.md frontmatter); the repo is a mirror synced from microsoft/GitHub-Copilot-for-Azure and has no top-level LICENSE file in our copy. Commercial use allowed under MIT.
Not really. Interactive query assistance with no loop, stop conditions or state.
Google's official collection of about 180 skills for Google Cloud, Gemini APIs, Analytics, Data Manager, sign-in and other Google products.
Cloudflare's official 19-skill pack for building on Workers, Durable Objects, the Agents SDK, Cloudflare One and more, with an optional bundled MCP server.
Neon's official skills for Lakebase Postgres and its Auth, Functions, Object Storage, AI Gateway and Realtime services, with branch-first workflows and evals.
A skill in Microsoft's Azure plugin for querying and analyzing Azure Data Explorer with KQL: discovering clusters and databases, exploring schema, running queries and interpreting results.
Install Microsoft's Azure plugin: /plugin install azure@claude-plugins-official in Claude Code, or add microsoft/azure-skills as a Codex marketplace. The Azure MCP server executes the Kusto tools.
Probably only for its workflow habits (schema first, batch-search candidate sources). The query patterns themselves are standard KQL.
azure-kusto is for ad-hoc analytics queries over ADX data. azure-diagnostics is a troubleshooting workflow for Azure services that includes KQL reference queries.