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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced network-forensics workflow with strong executable examples, but it is padded with glossary content Claude already knows, lacks explicit validation checkpoints, and fails to link its existing bundle files.

Suggestions

Add a 'References' section linking references/api-reference.md and scripts/agent.py from the body, and offload the inline tshark/Zeek/Suricata/Scapy API detail into those files for clearer progressive disclosure.

Trim the 'Key Concepts' glossary and 'Tools & Systems' descriptions of well-known items (PCAP, Wireshark, Zeek), keeping only non-obvious specifics such as JA3/JA3S fingerprinting.

Insert explicit validation checkpoints between steps — e.g., confirm the C2 channel and beacon interval before quantifying exfiltration, and verify extracted IOCs against threat intel before documenting findings.

Dimension	Reasoning	Score
Conciseness	The bulk is lean executable code, but the 'Key Concepts' glossary (PCAP, Wireshark, Zeek definitions) and 'Tools & Systems' descriptions re-explain well-known concepts Claude already knows, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready tcpdump, zeek-cut, awk, and Wireshark display-filter examples throughout every step, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The six steps are clearly sequenced, but there are no explicit validation checkpoints or feedback loops (e.g., confirm the C2 channel before quantifying exfiltration), which the score-3 anchor requires.	2 / 3
Progressive Disclosure	Bundle files exist (references/api-reference.md, scripts/agent.py) but are never referenced from the body, and detailed tool-API content is inline rather than signaled — matching the 'references present but not clearly signaled' anchor.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong, third-person description that names concrete capabilities and provides explicit activation triggers with natural keyword coverage. It clearly answers both what the skill does and when to use it with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'command-and-control communications, lateral movement, data exfiltration, and exploitation attempts' — plus named techniques 'Uses Wireshark, Zeek, and NetFlow analysis techniques', matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ('Analyzes network traffic captures and flow data to identify adversary activity') and when ('Activates for requests involving...'), satisfying the explicit-trigger anchor rather than capping at 2.	3 / 3
Trigger Term Quality	Covers natural analyst terms — 'network traffic analysis, packet capture investigation, PCAP analysis, network forensics, C2 traffic detection, or exfiltration detection' — that a user would naturally say, in proper third person voice.	3 / 3
Distinctiveness Conflict Risk	A clear network-forensics-for-incident-response niche with distinct triggers and named tooling makes it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mukul975/Anthropic-Cybersecurity-Skills
Commit: 673da1f

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

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.