CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sentinel-xdr-rule-converter

Convert every Microsoft Sentinel analytic rule in a solution into a Defender XDR Custom Detection YAML under the solution's XDR Detections folder.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/sentinel-xdr-rule-converter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, actionable CLI workflow with copy-paste commands, explicit checkpoints, and clear guardrails for a risky batch conversion. The main gaps are unspecified migration-config.yaml contents, implicit error-recovery loops, and an unheaded versioning section that hurts organization.

Suggestions

Specify the expected structure or keys of migration-config.yaml (or reference a template) so deterministic rewrites can be authored without guessing.

Add an explicit error-recovery loop, e.g. "If doctor fails, fix the reported issue and re-run" and "Resolve conflicts, then re-run convert with --overwrite after approval".

Move the versioning rules ([3.1.0, 4.0.0) bounds, patch bump behavior) into their own "## Versioning" section so they are separated from entity-mapping policy.

DimensionReasoningScore

Conciseness

The body is dense and imperative, consisting almost entirely of domain-specific policy (entity mapping rules, version bounds) Claude would not already know, with no padded explanations. It is not 5 because of minor redundancy — the "[3.1.0, 4.0.0)" bound is stated twice and the entity-mapping section repeats its caveats ("It is not an acceptance or review decision and does not clear other findings" vs. "query execution and preserved custom details do not prove entity correlation or alert parity").

4 / 5

Actionability

Provides copy-paste-ready commands ("sentinel-xdr-migration doctor", "setup --non-interactive", "inspect --solution \"<solution-path>\"", "convert --solution \"<solution-path>\"") plus concrete output paths like the transformation-report.html location. It is not 5 because the migration-config.yaml's required content is never specified and "Continue offline when authentication is unavailable" offers no executable step.

4 / 5

Workflow Clarity

A clear 8-step numbered sequence with real checkpoints for a batch operation (doctor pre-flight, "Review the analytic-rule count and source paths", "Do not overwrite conflicting generated files without explicit approval", reporting warnings/errors), so the missing-validation cap does not apply. It is not 5 because error-recovery feedback loops are implicit — nothing says what to do when doctor fails or how to resolve conflicts before re-running convert.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so the single-file skill is appropriately self-contained, organized under Inputs/Workflow/Best-effort headers with only inline path references. It is not 5 because at ~85 lines the dense versioning policy (three paragraphs on [3.1.0, 4.0.0) bounds and patch bumping) has no section header of its own and reads as a wall appended to the entity-mapping section; it is not 3 because the rest is well placed with no clearly misfiled content.

4 / 5

Total

16

/

20

Passed

Description

70%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.

The description states one fully-specified, highly concrete conversion action with excellent domain distinctiveness and strong domain keywords. Its main weaknesses are the complete absence of 'Use when' trigger guidance (capping completeness) and missing natural keyword variations.

Suggestions

Add an explicit trigger clause, e.g. "Use when migrating a Microsoft Sentinel solution to Defender XDR, or when the user mentions Sentinel analytic rules, XDR detections, or custom detection YAML."

Broaden keyword coverage with natural variations users would say, such as "detection rules", "migration", or "KQL".

Optionally mention ancillary capabilities (inspect, validate, report) so the description's coverage matches the skill's full behavior.

DimensionReasoningScore

Specificity

The single action is fully specified with source ("Microsoft Sentinel analytic rule"), target ("Defender XDR Custom Detection YAML"), and destination ("under the solution's XDR Detections folder"), which is far more concrete than anchor 3's generic examples. It is not 5 because only the conversion action is described — ancillary capabilities the skill performs (inspect, validate, report) are absent, leaving minor gaps in coverage.

4 / 5

Completeness

It clearly answers 'what' ("Convert every Microsoft Sentinel analytic rule... into a Defender XDR Custom Detection YAML") but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Includes the natural domain keywords a user would say ("Microsoft Sentinel", "analytic rule", "Defender XDR", "Custom Detection YAML", "solution"), giving good keyword coverage. It is not 5 because common variations and synonyms users might naturally say (e.g., "detection rules", "migration", "KQL", "SIEM") are missing.

4 / 5

Distinctiveness Conflict Risk

"Microsoft Sentinel analytic rule" to "Defender XDR Custom Detection YAML" is a clear niche with distinct triggers; virtually no other skill would match this vocabulary, giving minimal conflict risk. This clearly matches the anchor-5 example's profile rather than the 'minor overlap risk' of anchor 4.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Azure/Azure-Sentinel

Path

.github/skills/sentinel-xdr-rule-converter/SKILL.md

Reviewed

Table of Contents

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.