mcpbeat Sign in

Asim Parser Filter Validator Agent Skill

Validates ASIM parser filtering parameters by running filter tests against a Log Analytics workspace. Pure PowerShell using az CLI for authentication — no Python or Azure SDK packages required. Use this skill after creating or modifying an ASIM parser to verify that its filtering parameters work correctly.

12k tokens
context cost
the whole folder, loaded on every use
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
6042
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Azure/Azure-Sentinel --skill asim-parser-filter-validator

What comes with it

42 302 bytes besides the instruction
scripts/asimFilterTest.ps1

The instruction itself

9 sections, as written by the author

ASIM Parser Filter Validator

Validates that an ASIM parser's filtering parameters (e.g. disabled, starttime, endtime, srcipaddr_has_any_prefix, etc.) behave correctly by running queries against a Log Analytics workspace.

This skill is a pure PowerShell implementation that uses az CLI for authentication. No Python, Azure SDK packages, or YAML modules are required.

  • PowerShell 7+
  • Azure CLI (logged in via az login)

What it tests

For every filtering parameter declared in the parser's KQL function signature:

| Parameter type | Tests performed |

| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |

| disabled | disabled=true returns 0 rows; disabled=false returns rows |

| datetime (starttime / endtime) | Filtering by the midpoint timestamp returns fewer rows than unfiltered |

| Scalar (string, int) | Filtering by a real value returns exactly that value; filtering by a fictitious value returns 0 rows |

| dynamic (*_has_any, *_has_all, *_has_any_prefix) | Filtering by one/two real values returns fewer rows; fictitious value returns 0 rows; substring / prefix variants tested where applicable |

Supported schemas

AgentEvent, AlertEvent, AssetEntity, AuditEvent, Authentication, DhcpEvent, Dns, FileEvent, NetworkSession, ProcessEvent, RegistryEvent, UserManagement, WebSession.

Inputs

| Input | Required | Description |

| --------------- | -------- | ----------------------------------------------------------------- |

| Parser KQL path | Yes | Path to the ASIM parser .kql file to test |

| Schema name | Yes | ASIM schema name (e.g. Dns, Authentication, NetworkSession) |

| Workspace ID | Yes | Log Analytics workspace GUID to run queries against |

How to run

.\scripts\asimFilterTest.ps1 -ParserFile "{PathToFilterParserKQL}" -SchemaName "{SchemaName}" -WorkspaceId "{your-workspace-guid}"

Prerequisites

  • Azure CLI authenticated — run az login if not already logged in. If you get an authentication error, use the az-cli-command-runner skill to verify login status.
  • The workspace must contain data for the tables referenced by the parser.

Interpreting results

  • Green — test passed.
  • FAIL — the filtering parameter did not behave as expected. The failure message indicates which parameter failed and what was expected.
  • Known partial validations — AuditEvent (EventResult), Authentication (EventType), and Dns (EventType) have known single-failure scenarios that are automatically ignored.

Known acceptable failure reasons (can be ignored)

When analyzing filter-validation failures, a failure can be ignored if it matches one of these inherent-limitation categories:

  • Documented schema known exception — The schema defines a known exception for a parameter (e.g. a multi-value test that cannot succeed because the value combinations do not co-exist in that schema's data). Check whether the ASIM schema documentation lists the parameter as a known exception.
  • Constant or single-value field by design — The parser maps the filtered field to a single constant value, so multi-value or reduction-based filtering cannot reduce rows further. This is expected when the source provides only one possible value for that field.
  • Insufficient distinct values in the test window — The 2-day query window does not contain enough distinct values for the field to exercise multi-value filtering. This is a data-availability limitation, not a parser bug.

When reviewing filter-validation output, analyze each failure message against these categories. If all other parameters pass and every failure maps to one of the reasons above, the parser's filtering implementation is considered correct.

Troubleshooting

| Symptom | Fix |

| ------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |

| Failed to acquire access token via az CLI | Run az login |

| No data in the provided workspace | Ensure the workspace has ingested data for the relevant tables within the last 2 days |

| Schema: X - Not supported | The schema name is not in the supported list — update the $AllSchemasParameters hashtable in asimFilterTest.ps1 |

Other skills for the same job

different authors, same section of the catalogue
MCP Builder
by anthropics
vendor ×13

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

30k tokens scripts
Changelog Generator
by frostant
×9

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

774 tokens
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
MCP Builder
by JayZeeDesign
×7

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

37k tokens scripts
Vercel React Native Skills
by vercel-labs
vendor ×6

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

39k tokens
Vercel React Best Practices
by ratacat
×5

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

34k tokens
Next Best Practices
by vercel-labs
vendor ×4

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling

20k tokens
Using Git Worktrees
by ZhanlinCui
×4

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

1k tokens

How to use it

Copy the folder

Take azure/asim-parser-filter-validator from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.