analyzing-linux-system-artifacts

Examine Linux system artifacts (auth logs, cron/systemd persistence, shell history, SSH keys, and system configuration) to uncover evidence of compromise, detect rootkits or backdoors, and reconstruct user/attacker activity. Use when investigating a compromised Linux server or workstation, hunting for persistence mechanisms, or scoping a Linux-based breach during incident response.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%

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

Highly actionable, with copy-paste executable collection and analysis scripts across a clear five-step workflow. Weaker on conciseness (concept tables that restate common Linux knowledge) and progressive disclosure (bundle files exist but are not linked from the body), and the workflow lacks validation checkpoints for batch forensic operations.

Suggestions

Add validation checkpoints between steps — e.g., confirm the read-only mount succeeded and verify expected artifact counts after collection before proceeding to analysis.

Link the existing bundle files from the body (e.g., 'See references/api-reference.md for full artifact locations and tool syntax' and 'scripts/agent.py for the automated collector') and move the duplicated artifact/tool tables out of SKILL.md into that reference.

Remove or trim the Key Concepts and Tools tables that restate common Linux knowledge Claude already has, keeping only forensics-specific nuance.

Dimension	Reasoning	Score
Conciseness	The bulk is lean executable code, but the Key Concepts and Tools tables explain well-known Linux concepts (what .bash_history, crontab, SUID, LD_PRELOAD are) that Claude already knows, and the ~310-line body could be tightened.	2 / 3
Actionability	Provides fully executable bash collection commands and embedded Python analysis scripts with concrete paths and specific flag combinations — copy-paste ready with no pseudocode.	3 / 3
Workflow Clarity	Five steps are clearly sequenced, but the batch collection/analysis workflow has no validation or verification checkpoints (no mount-success check, no collection-completeness confirmation, no error-recovery loop), which caps this dimension per the batch-operations guideline.	2 / 3
Progressive Disclosure	Sections are organized, but the existing bundle files (references/api-reference.md, scripts/agent.py) are never referenced or signaled from the body, and large inline content (artifact-location tables, tool descriptions) duplicates material that belongs in the reference file.	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 actions, artifact types, and natural trigger phrases while cleanly answering both what the skill does and when to use it. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Examine Linux system artifacts', 'uncover evidence of compromise', 'detect rootkits or backdoors', 'reconstruct user/attacker activity') with named artifact types, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what (examine artifacts to uncover compromise, detect rootkits, reconstruct activity) and when via a clear 'Use when...' clause with multiple concrete triggers.	3 / 3
Trigger Term Quality	Natural trigger phrasing users would say — 'investigating a compromised Linux server', 'hunting for persistence mechanisms', 'scoping a Linux-based breach', 'incident response' — with good coverage and third-person voice.	3 / 3
Distinctiveness Conflict Risk	A clear Linux digital-forensics / incident-response niche with distinct triggers 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
Path: skills/analyzing-linux-system-artifacts/SKILL.md
Commit: e612f49

Reviewed: about 9 hours 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.