triage-malware
Triage a suspected malicious file hash. Use when investigating malware alerts or suspicious files. Analyzes GTI file report, behavioral indicators, identifies affected hosts, enriches network IOCs, and recommends containment actions.
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 a well-crafted skill description that clearly defines its purpose, lists specific actions, includes an explicit 'Use when' clause with natural trigger terms, and occupies a distinct niche in security/malware investigation. It follows the recommended pattern of stating what it does and when to use it, with concrete domain-specific terminology that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzes GTI file report, behavioral indicators, identifies affected hosts, enriches network IOCs, and recommends containment actions. | 3 / 3 |
Completeness | Clearly answers both what ('Triage a suspected malicious file hash... Analyzes GTI file report, behavioral indicators, identifies affected hosts, enriches network IOCs, and recommends containment actions') and when ('Use when investigating malware alerts or suspicious files') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'malicious file hash', 'malware alerts', 'suspicious files', 'IOCs', 'containment'. These cover the natural vocabulary of a security analyst investigating threats. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on file hash triage in a malware/security context with specific terms like 'GTI file report', 'network IOCs', and 'containment actions' that are 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 solid, actionable malware triage skill with clear tool-specific commands and a well-defined workflow. Its main weaknesses are the lack of validation/error-handling checkpoints in the workflow (e.g., what if no execution events are found?) and some inline content (severity matrix, recommended actions) that could be offloaded to reference files. The required outputs table and concrete tool call syntax are strong points.
Suggestions
Add explicit validation checkpoints and branching logic (e.g., 'If GTI returns no results, note as unknown and proceed' or 'If no execution events found, skip to Step 6 and note no host impact').
Move the Severity Assessment Matrix and Recommended Actions by Severity into a separate reference file (e.g., SEVERITY_GUIDE.md) and link to it, keeping SKILL.md focused on the workflow.
Add a brief error-handling note for tool call failures (e.g., API timeouts or permission errors) to prevent the workflow from stalling silently.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and domain-specific, but the Severity Assessment Matrix and Recommended Actions sections add bulk that could be trimmed or referenced externally. The content doesn't over-explain concepts Claude knows, but the tables and action lists are somewhat verbose for inline content. | 2 / 3 |
Actionability | Each step provides specific tool calls with exact function names and parameters. The search queries show concrete syntax, the outputs table specifies exact expected values, and the documentation template gives a clear structure to follow. This is copy-paste ready for a SOAR/SIEM workflow. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and logically ordered, but it lacks explicit validation checkpoints or error handling. There's no guidance on what to do if GTI returns no results, if SIEM searches return empty, or if tool calls fail — important for a security triage workflow where incomplete data changes the analysis path. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but the Severity Assessment Matrix and Recommended Actions tables could be split into a separate reference file. The skill references other skills (/enrich-ioc, /find-relevant-case, /document-in-case) which is good, but the inline content is heavier than ideal for a SKILL.md overview. | 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 | |
- Repository
- dandye/ai-runbooks
- Commit
086cbf6
- 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.