Analyzes Windows Security, System, and Sysmon event logs in Splunk to detect authentication attacks, privilege escalation, persistence mechanisms, and lateral movement using SPL queries mapped to MITRE ATT&CK techniques. Use when SOC analysts need to investigate Windows-based threats, build detection queries, or perform forensic timeline analysis of Windows endpoints and domain controllers.
85
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its domain (Windows event log analysis in Splunk), lists specific capabilities (detecting authentication attacks, privilege escalation, persistence, lateral movement), and provides explicit trigger guidance via a 'Use when' clause. It uses appropriate third-person voice throughout and includes rich, natural trigger terms that SOC analysts would actually use in their queries.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzes Windows Security/System/Sysmon event logs, detects authentication attacks/privilege escalation/persistence mechanisms/lateral movement, uses SPL queries mapped to MITRE ATT&CK techniques, builds detection queries, performs forensic timeline analysis. | 3 / 3 |
Completeness | Clearly answers both what (analyzes Windows event logs in Splunk to detect various attack types using SPL queries mapped to MITRE ATT&CK) and when (explicit 'Use when' clause specifying SOC analysts investigating Windows-based threats, building detection queries, or performing forensic timeline analysis). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a SOC analyst would use: 'Windows Security', 'Sysmon', 'Splunk', 'SPL queries', 'MITRE ATT&CK', 'authentication attacks', 'privilege escalation', 'lateral movement', 'persistence', 'forensic timeline', 'domain controllers', 'SOC analysts', 'detection queries'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Windows event logs + Splunk + MITRE ATT&CK + specific attack categories. Very unlikely to conflict with other skills due to the precise domain focus on Windows security log analysis in Splunk specifically. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent, production-ready SPL queries covering major Windows threat detection categories mapped to MITRE ATT&CK. Its main weaknesses are the monolithic structure (everything in one large file without references to supplementary materials), some unnecessary explanations of tools Claude already knows, and the lack of validation/tuning guidance for the detection queries. The content would benefit from trimming explanatory sections and adding result validation steps.
Suggestions
Remove or significantly trim the 'Tools & Systems' section and 'Key Concepts' table — Claude already knows what Splunk, Sysmon, and common event codes are; the queries themselves demonstrate their usage.
Add validation checkpoints after query execution, such as 'Verify results by checking: (1) baseline normal count for this environment, (2) exclude known service accounts, (3) cross-reference with asset inventory' to improve workflow clarity.
Split detailed queries into referenced files (e.g., AUTH_DETECTION.md, PERSISTENCE_DETECTION.md) and keep SKILL.md as an overview with one example per category, improving progressive disclosure.
Add tuning guidance for the Common Scenarios section — either include the actual SPL queries or reference a separate file, rather than leaving them as one-line descriptions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) with some sections that could be trimmed. The 'Tools & Systems' section explains what Splunk and Sysmon are (Claude knows this), and the 'Key Concepts' table explains basic event codes that are already evident from the queries themselves. However, the SPL queries themselves are dense and valuable, and the MITRE ATT&CK mappings add real value. | 2 / 3 |
Actionability | Excellent actionability — every detection scenario includes fully executable SPL queries that are copy-paste ready with specific field names, event codes, thresholds, and filtering logic. The queries include practical details like status code mappings, logon type interpretations, and exclusion patterns for known-good processes. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced from authentication attacks through privilege escalation, persistence, lateral movement, and forensic timeline building. However, there are no validation checkpoints — no guidance on verifying query results are accurate, no feedback loops for tuning false positives, and no verification steps after building lookups or timelines. For detection engineering workflows, validation of results is important. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with all queries inline. The 'Common Scenarios' section lists additional techniques (Kerberoasting, DCSync, Golden Ticket) without queries — these could be in a separate reference file. The lookup CSV data, output format template, and detailed queries for each attack category could benefit from being split into referenced files for better navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
c15f73d
Table of Contents
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.