Lists multiple specific concrete actions and domains: allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, hot-path optimization, and performance code review. The 'if X bottleneck, then apply Y' framing adds methodological specificity.

Clearly answers both 'what' (Golang performance optimization patterns covering allocation reduction, CPU efficiency, etc.) and 'when' (explicit 'Use when profiling or benchmarks have identified a bottleneck' and 'when performing performance code review'). Also includes explicit 'Not for' exclusions referencing other skills, which strengthens the 'when' guidance.

Includes strong natural keywords users would say: 'performance optimization', 'profiling', 'benchmarks', 'bottleneck', 'allocation reduction', 'GC tuning', 'caching', 'hot-path', 'performance code review'. These cover a wide range of terms a Go developer would naturally use when seeking optimization help.

Highly distinctive with explicit boundary-setting via 'Not for measurement methodology (see golang-benchmark skill) or debugging workflow (see golang-troubleshooting skill)'. This directly addresses potential overlap with related skills and creates a clear niche for optimization patterns specifically.

The content is lean and efficient. It avoids explaining what Go, GC, or pprof are. Every section delivers actionable patterns or decision tables without padding. The philosophy section is brief and justified by the optimization context.

The iterative methodology provides concrete commands (benchstat, go test -bench flags), and the decision tree maps signals to actions. However, the actual optimization patterns are delegated to reference files, and the main skill lacks executable code examples showing before/after optimization patterns. The common mistakes table is actionable but mostly declarative.

The iterative optimization cycle is clearly sequenced with 8 explicit steps including baseline measurement, single-change discipline, statistical comparison via benchstat, and a repeat loop. The 'Rule Out External Bottlenecks First' section adds a validation checkpoint before even starting optimization. The decision tree provides clear routing from diagnosis to action.

The skill has excellent structure with a clear overview, decision tree routing to deep dives, and well-signaled references to 6 reference files and multiple cross-referenced skills. However, no bundle files were provided, so the referenced files (references/memory.md, references/cpu.md, etc.) cannot be verified to exist, and the actual optimization patterns that are the core value of this skill are entirely in those unverifiable references.