analyzing-lnk-file-and-jump-list-artifacts

Analyze Windows LNK shortcut files and Jump List artifacts with LECmd, JLECmd, and manual Shell Link Binary Format parsing to establish evidence of file access, program execution, and user activity that persists even after the target file is deleted. Use when investigating Windows user activity, reconstructing file-access or program-execution timelines, or examining recent/frequently-used file evidence in a forensic exam.

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%Weight 40%Scale 1-3

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

Actionable and tool-rich, but the body is a monolithic inline reference that ignores its own bundle files and carries verbose conceptual and example-output padding. Linking out to the existing references/scripts and trimming the Overview and mock output would materially improve it.

Suggestions

Replace the inline header-structure tables, AppID hash list, EZ-tool syntax, and Python parser with concise pointers to references/api-reference.md, references/workflows.md, and scripts/agent.py so SKILL.md reads as an overview rather than a duplicate of the bundle.

Trim the Overview's explanation of what LNK/Jump List files are and condense the ~70-line mock example output to a short representative excerpt.

Add explicit validation checkpoints to the investigation workflows (e.g. confirm LNK header signature == 0x4C, verify AppID mapping, cross-check volume serials against MFT/USBSTOR) so each use case reads as a verifiable sequence rather than a descriptive list.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference tables and commands, but the Overview explains concepts Claude already knows (what LNK files are and how they are created), a ~70-line mock example-output block is verbose, and the Win10/Win11 section is vague and time-sensitive ('Recent research (IEEE 2025)', 'may not generate').	2 / 3
Actionability	Provides fully executable LECmd/JLECmd commands with real flags and a complete, copy-paste Python struct-based LNK header parser with FILETIME conversion.	3 / 3
Workflow Clarity	Numbered use-case steps (file access, removable media, network share) are listed, but there are no validation checkpoints or feedback loops, and batch directory scanning lacks any verification step.	2 / 3
Progressive Disclosure	A rich bundle exists (references/api-reference.md, standards.md, workflows.md; scripts/agent.py, process.py; assets/template.md) but the body never links to any of them and inlines header-structure tables, AppID hashes, command syntax, and a Python script that duplicate the reference files.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 pairs concrete named actions (LECmd, JLECmd, manual Shell Link parsing) with explicit, natural-language use triggers, cleanly answering both what and when.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions—'Analyze Windows LNK shortcut files and Jump List artifacts with LECmd, JLECmd, and manual Shell Link Binary Format parsing to establish evidence of file access, program execution, and user activity'—rather than vague language.	3 / 3
Completeness	Explicitly states both what the skill does (analyze LNK/Jump List artifacts to establish evidence) and when to use it via a clear 'Use when investigating Windows user activity...' trigger clause.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say—'Windows user activity', 'file-access or program-execution timelines', 'recent/frequently-used file evidence', 'forensic exam'—alongside the domain terms LNK and Jump List.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Windows LNK and Jump List forensics with named tools) with triggers unlikely to overlap with 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-lnk-file-and-jump-list-artifacts/SKILL.md
Commit: e612f49

Reviewed: 7 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.