Leverages Splunk Enterprise Security and SPL (Search Processing Language) to investigate security incidents through log correlation, timeline reconstruction, and anomaly detection. Covers Windows event logs, firewall logs, proxy logs, and authentication data analysis. Activates for requests involving Splunk investigation, SPL queries, SIEM log analysis, security event correlation, or log-based incident investigation.
68
82%
Does it follow best practices?
Impact
—
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 a strong skill description that clearly articulates specific capabilities (log correlation, timeline reconstruction, anomaly detection), covers relevant data types, and provides explicit trigger conditions. It uses proper third-person voice throughout and includes both a 'what' and 'when' clause with natural trigger terms that security professionals would use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'investigate security incidents through log correlation, timeline reconstruction, and anomaly detection' and specifies data types: 'Windows event logs, firewall logs, proxy logs, and authentication data analysis.' | 3 / 3 |
Completeness | Clearly answers both what ('investigate security incidents through log correlation, timeline reconstruction, and anomaly detection') and when ('Activates for requests involving Splunk investigation, SPL queries, SIEM log analysis, security event correlation, or log-based incident investigation'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Splunk', 'SPL', 'SIEM', 'log analysis', 'security event correlation', 'incident investigation', 'Windows event logs', 'firewall logs', 'proxy logs', 'authentication data'. These are terms a security analyst would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Splunk Enterprise Security and SPL-based investigation. The combination of specific tool (Splunk), language (SPL), and domain (security incident investigation) makes it very unlikely to conflict with other skills. | 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 strong, actionable skill with excellent SPL query examples covering the full incident investigation lifecycle. Its main weaknesses are verbosity in supporting sections (glossary, tools descriptions) that Claude doesn't need, and the absence of validation checkpoints or feedback loops within the investigation workflow. The monolithic structure would benefit from splitting reference material into separate files.
Suggestions
Remove or drastically trim the Key Concepts table and Tools & Systems section — Claude already knows what SPL, sourcetypes, and Sysmon are. Keep only non-obvious, project-specific definitions.
Add explicit validation checkpoints between workflow steps, e.g., 'Verify Step 1 returns results before proceeding' and 'If no events found, expand time range or check sourcetype availability'.
Split the Common Scenarios, Output Format template, and reference tables into separate files (e.g., SCENARIOS.md, REPORT_TEMPLATE.md) and reference them from the main skill to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured but includes some unnecessary content: the Key Concepts table defines terms Claude already knows (SPL, sourcetype, timechart), the Tools & Systems section describes well-known tools at a level Claude doesn't need, and some inline comments restate what the SPL already shows. The core SPL queries are efficient, but the surrounding prose could be trimmed significantly. | 2 / 3 |
Actionability | The skill provides fully executable SPL queries for each investigation step, covering authentication analysis, process tracing, network correlation, timeline building, and detection rule creation. Queries are copy-paste ready with realistic field names, event codes, and CIM-compliant syntax. The scenario section provides a concrete step-by-step approach. | 3 / 3 |
Workflow Clarity | The six-step workflow is clearly sequenced and logically progresses from scoping through timeline reconstruction to detection creation. However, there are no explicit validation checkpoints or feedback loops — for instance, no step to verify query results are non-empty before proceeding, no guidance on what to do if a step yields unexpected results, and no verification that the correlation search in Step 6 actually fires correctly. For an investigation workflow involving potentially destructive actions (creating notable events, collecting to indexes), this is a gap. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers, but it's a monolithic document (~200+ lines) with no references to external files. The Key Concepts table, Tools & Systems section, Common Scenarios, and Output Format template could all be split into separate reference files to keep the main skill lean. For a skill of this complexity, the lack of any external references means everything is inline. | 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 | |
0f429d0
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.