ff-oce-kusto

Use this skill for any Kusto query or telemetry investigation specifically related to Fluid Framework or its partners. Triggers include: writing or running a Kusto query against the Office Fluid database, investigating Fluid Framework telemetry or error rates, querying Office_Fluid_FluidRuntime_* tables, looking up a Fluid session by Session_Id or docId, investigating a Fluid-related error in Loop or Whiteboard telemetry, monitoring an FF bump or partner ring deployment, checking Fluid render reliability or Scriptor errors, or when the user mentions Fluid-specific tables (Office_Fluid_FluidRuntime_*, OwhLoads, HostTracker, Scriptor) or Fluid-specific error types (dataCorruptionError, dataProcessingError, DeltaConnectionFailureToConnect, ICE, ACE). Do NOT trigger for general Kusto questions that are not related to Fluid Framework.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured skill body: concise, concrete, and properly split into an overview plus a single one-level-deep reference file. The main limitation is that most executable query examples and the step-by-step investigation workflow live in the reference file rather than the body itself, which slightly caps inline actionability and workflow sequencing.

Suggestions

Include one or two copy-paste-ready starter queries inline (e.g., a session-by-Session_Id lookup or an error timechart) so Claude can act without first opening the reference file.

Add a short numbered investigation workflow inline (e.g., 1. confirm VPN, 2. query Office_Fluid_FluidRuntime_Error, 3. correlate via Session_Id, 4. consult cookbook) with an explicit validation/feedback step before delegating to the reference cookbook.

Trim the Part 1-4 descriptive enumeration slightly or convert it to a bulleted 'what's in the reference' pointer to tighten token use.

Dimension	Reasoning	Score
Conciseness	Lean overview that assumes Claude's competence (no padding about what Kusto or telemetry is); each line earns its place, though the descriptive Part 1-4 enumeration of the reference file's contents is slightly more prose than a tight pointer would need.	4 / 5
Actionability	Provides concrete, executable specifics (cluster URL, database IDs to use as the database parameter, table names, required filters like 'Data_stack !has .goskope.com', the hll()/dcount_hll pattern) with only minor gaps — most ready-to-run queries live in the reference file rather than inline.	4 / 5
Workflow Clarity	Clear orientation flow (cluster/access -> primary tables -> correlation ID hierarchy -> load full reference -> key reminders) with a validation checkpoint (the VPN-required reminder to check before troubleshooting), but the investigation workflow itself is delegated to the reference cookbook rather than sequenced inline.	4 / 5
Progressive Disclosure	Clean one-level-deep structure: a concise SKILL.md overview pointing to a single real references/kusto-query-reference.md file, which is confirmed to exist and is well-signaled with an explicit path and a summary of its four parts for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally strong description: specific, comprehensive in trigger terms, fully answers what-and-when, and includes an explicit negative boundary clause that sharply reduces conflict risk with general Kusto skills. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (writing/running Kusto queries, investigating telemetry, looking up sessions by Session_Id/docId, monitoring FF bumps, checking render reliability) and specific database targets, giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers 'what' (Kusto query/telemetry investigation for Fluid Framework) and 'when' with concrete trigger phrases, and additionally provides a 'Do NOT trigger' boundary clause for non-Fluid Kusto questions.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms and concrete identifiers users would say ('Fluid', 'Kusto', 'Loop', 'Whiteboard', 'telemetry', 'error rates', 'docId', 'Session_Id') plus specific table and error-type names that act as strong trigger keywords.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Fluid Framework telemetry in the Office Fluid Kusto cluster) with distinct, product-specific triggers (Office_Fluid_FluidRuntime_*, dataCorruptionError, ICE/ACE) and an explicit negative boundary, minimizing conflict with general Kusto skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/FluidFramework
Path: .agency/plugins/ff-oce/skills/ff-oce-kusto/SKILL.md
Commit: c1f54db

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.