macos-reverse

Use for authorized macOS and Mach-O reverse engineering including codesign, Objective-C/Swift recovery, endpoint security surfaces, and Apple platform malware analysis.

Quality

86%

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

72%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.

A well-structured, concise skill body with good progressive disclosure, but the static/dynamic phases lack executable command examples and the workflow has no inter-phase validation checkpoints plus a dangling file reference.

Suggestions

Replace the bare tool-name checkboxes in the static and dynamic phases with concrete, copy-paste-ready invocations (e.g., a real `class-dump -H target -o out/`, an `lldb` breakpoint snippet, and a `frida -U -n target` example).

Add validation checkpoints between phases — e.g., confirm codesign/entitlements and Hardened Runtime status before moving to static analysis, and confirm LC_LOAD_DYLIB findings before dynamic instrumentation.

Fix the dangling reference: the first action directs Claude to read '../field-journal/precedent-reverse.md', which does not exist in the bundle; either create it or remove the instruction.

Dimension	Reasoning	Score
Conciseness	Lean and token-efficient — terse checklists, command snippets, and bullet lists with no explanations of concepts Claude already knows.	3 / 3
Actionability	Section 1 gives executable bash commands, but the static and dynamic phases are bare tool-name checkbox menus ('□ class-dump / swift-demangle / Hopper…') with no invocation syntax, leaving key details missing.	2 / 3
Workflow Clarity	The signature→static→dynamic sequence and a final self-check checklist are present, but there are no validation checkpoints between phases and the first action references a non-existent file ('../field-journal/precedent-reverse.md').	2 / 3
Progressive Disclosure	A lean overview points to a real one-level-deep reference (references/macho-triage.md) with clearly signaled, well-organized sections and easy navigation.	3 / 3
	Total	10 / 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 concise, third-person description with an explicit 'Use for' trigger and several concrete capabilities, hitting all four dimensions at the top of the scale.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'codesign', 'Objective-C/Swift recovery', 'endpoint security surfaces', and 'Apple platform malware analysis' — rather than vague language.	3 / 3
Completeness	Explicit 'Use for…' trigger states when to invoke it, and the enumerated activities state what it does, satisfying both what and when.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'macOS', 'Mach-O', 'reverse engineering', 'malware analysis' — with good domain coverage.	3 / 3
Distinctiveness Conflict Risk	The macOS/Mach-O reverse-engineering niche is clearly bounded and unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhaoxuya520/reverse-skill
Path: skills/macos-reverse/SKILL.md
Commit: 6aa1362

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.