analyzing-network-traffic-for-incidents
Analyzes network traffic captures and flow data to identify adversary activity during security incidents, including command-and-control communications, lateral movement, data exfiltration, and exploitation attempts. Uses Wireshark, Zeek, and NetFlow analysis techniques. Activates for requests involving network traffic analysis, packet capture investigation, PCAP analysis, network forensics, C2 traffic detection, or exfiltration detection.
60
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-network-traffic-for-incidents/SKILL.mdQuality
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 scope (network traffic forensics for security incidents), lists specific capabilities and tools, and provides explicit activation triggers. It uses proper third-person voice throughout and covers both common and technical trigger terms that users in this domain would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzing network traffic captures, identifying C2 communications, lateral movement, data exfiltration, exploitation attempts. Also names specific tools (Wireshark, Zeek, NetFlow). | 3 / 3 |
Completeness | Clearly answers both 'what' (analyzes network traffic to identify adversary activity including C2, lateral movement, exfiltration) and 'when' (explicit 'Activates for requests involving...' clause with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'network traffic analysis', 'packet capture', 'PCAP analysis', 'network forensics', 'C2 traffic detection', 'exfiltration detection', plus domain-specific but commonly used terms like 'Wireshark', 'Zeek', 'NetFlow'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on network traffic forensics during security incidents. The specific mention of PCAP, Wireshark, Zeek, C2 detection, and exfiltration clearly separates this from general security, log analysis, or endpoint forensics skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels in actionability with concrete, executable commands across tcpdump, Wireshark, and Zeek, plus a realistic output template. However, it is significantly too verbose — defining terms and tools Claude already knows, and inlining content (glossary, tool descriptions, scenario details, output templates) that should be in separate bundle files. The workflow lacks validation checkpoints important for forensic analysis.
Suggestions
Remove the Key Concepts table and Tools & Systems section entirely — Claude knows what PCAP, Wireshark, and Zeek are. If retained for reference, move to a separate REFERENCE.md.
Move the Common Scenarios section and the detailed Output Format template into separate bundle files (e.g., SCENARIOS.md, OUTPUT_TEMPLATE.md) and reference them from the main skill.
Add explicit validation checkpoints in the workflow, e.g., 'Verify PCAP contains expected traffic before proceeding' after Step 1, and 'If no beaconing pattern found, adjust time window and re-filter' in Step 2.
Trim the Prerequisites section to a brief bullet list of required tools without explanatory parentheticals — Claude knows what a SPAN port and network tap are.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose at ~250+ lines. The Key Concepts table defines terms Claude already knows (PCAP, DNS Tunneling, NetFlow). The Tools & Systems section explains what Wireshark and Zeek are. The Prerequisites section is padded with obvious context. Much of this could be cut by 40-50% without losing actionable content. | 1 / 3 |
Actionability | The skill provides fully executable tcpdump commands, Wireshark display filters, Zeek log parsing commands with zeek-cut and awk, and specific protocol/port references. The commands are copy-paste ready with realistic IPs and parameters, and the scenario walkthrough gives a concrete step-by-step approach. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced and logically ordered from capture through documentation. However, there are no explicit validation checkpoints or feedback loops — no step says 'verify your capture is complete before proceeding' or 'if no beaconing is found, broaden your filter and retry.' For a forensic workflow where errors can mean missed evidence, this is a gap. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files. The Key Concepts table, Tools & Systems section, Common Scenarios, and detailed Output Format template could all be split into separate reference files. Everything is inline, making the skill unnecessarily long for the main SKILL.md. | 1 / 3 |
Total | 7 / 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
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
0445030
- 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.