Lists multiple specific concrete actions: 'map code dependencies', 'generate API documentation from source', 'identify undocumented business logic', 'figure out what code does', 'create architecture documentation from implementation'.

Clearly answers both what (reverse-engineering, extracting specifications, mapping dependencies, generating documentation) AND when with explicit 'Use when' clause covering legacy systems, inherited projects, undocumented codebases, plus explicit trigger phrases.

Excellent coverage of natural terms users would say including 'reverse engineer', 'old codebase', 'no docs', 'figure out how this works', 'inherited project', 'legacy analysis', 'code archaeology' - these match how users naturally describe these situations.

Clear niche focused specifically on reverse-engineering and undocumented/legacy code analysis. The trigger phrases like 'code archaeology', 'no docs', 'inherited project' are distinct and unlikely to conflict with general coding or documentation skills.

The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose with no padding or unnecessary context about what reverse engineering is or why documentation matters.

Provides concrete, executable Glob and Grep patterns with real regex examples. The EARS format table gives specific, copy-paste ready templates with clear examples for each requirement type.

Clear 5-step workflow with an explicit validation checkpoint after exploration ('Confirm sufficient file coverage before proceeding'). The workflow includes a feedback loop for incomplete exploration before proceeding to documentation.

Excellent structure with a concise overview in the main file and well-signaled one-level-deep references to four specific reference files. The reference table clearly indicates when to load each resource.