analyzing-windows-lnk-files-for-artifacts

Parse Windows LNK shortcut files to extract target paths, MAC timestamps, volume serial numbers, and machine identifiers for forensic timeline reconstruction. Use when investigating recently-accessed files, tracking removable media or network paths referenced by shortcuts, or building a DFIR timeline from LNK artifacts.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

The content is highly actionable with complete executable examples and a recognizable multi-step workflow, but it underuses its own bundle by duplicating inline what scripts/agent.py and references/api-reference.md already provide. The forensic batch/copy workflow also lacks the validation checkpoints the rubric expects for risky batch operations.

Suggestions

Replace the inline Step 3/4 Python with a callout to scripts/agent.py (e.g. `python3 scripts/agent.py --lnk-dir ... --action full_analysis`) to remove the duplicated ~80 lines and lean on the bundled agent.

Add a validation/verification checkpoint to Step 1's forensic-image copy — verify sha256sums against the acquired image and report count/hash before parsing, so the batch evidence-handling has a feedback loop.

Signal the bundle explicitly from the body: a one-level-deep reference such as "For the LnkParse3 JSON schema and field mappings, see [references/api-reference.md](references/api-reference.md)" instead of restating the structure inline.

Dimension	Reasoning	Score
Conciseness	The body is accurate and free of beginner-concept padding, but Steps 3 and 4 reproduce ~80 lines of inline Python that largely duplicate the bundled scripts/agent.py; these could be referenced rather than embedded, so it is mostly efficient with unnecessary bulk.	2 / 3
Actionability	All steps provide fully executable, copy-paste-ready bash and Python with concrete paths (e.g. LECmd.exe invocations, LnkParse3 parsing loop, CSV export) — no pseudocode placeholders.	3 / 3
Workflow Clarity	A clear four-step sequence exists, but Step 1 performs batch copy operations on forensic evidence with no validation/verification checkpoint (e.g. hash verification or error-recovery loop); per the rubric, missing feedback loops for batch operations cap this at 2.	2 / 3
Progressive Disclosure	The body is a monolithic wall (full inline scripts, large tables, four scenarios) while bundle files references/api-reference.md and scripts/agent.py exist but are never referenced or signaled from the body — content that should be split out is inline.	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.

The description is a strong, third-person statement that concretely enumerates capabilities and pairs them with explicit, natural-language use triggers. It cleanly answers both what the skill does and when to invoke it within a clearly delineated forensic niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Parse Windows LNK shortcut files to extract target paths, MAC timestamps, volume serial numbers, and machine identifiers" — naming specific extractable artifacts rather than vague capabilities.	3 / 3
Completeness	Explicitly answers both what (parse and extract specific artifacts for "forensic timeline reconstruction") and when ("Use when investigating recently-accessed files, tracking removable media... or building a DFIR timeline").	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "LNK shortcut files", "recently-accessed files", "removable media", "network paths", "DFIR timeline" — across both file-type and scenario language.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Windows LNK forensic analysis with distinct triggers; the specificity of "LNK shortcut files" and "DFIR timeline" makes overlap with other skills unlikely.	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-windows-lnk-files-for-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.