Catalog
All AI skills
157 skills. Every one is readable here; downloads and live use need a subscription.
swiftui-performance-audit
Audit SwiftUI performance issues from code review and profiling evidence.
test-guard
Review generated or changed test code against universal testing rules before it ships or is presented for approval.
thick-client
Authorized security testing of desktop thick clients: local storage, update channels, IPC, traffic interception, and client-side trust-boundary review.
threat-modeling-expert
Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use PROACTIVELY for security architecture reviews, threat identification, or building secure-by-design systems.
ui-score
Score a UI file's design quality 0-100 against StyleSeed's design language — per-category breakdown, the worst offenders, and a prioritized fix list. A quantified version of /ss-review.
uncle-bob-craft
Use when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.
vibe-delegate
Delegate coding tasks to the Mistral Vibe CLI (`vibe`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
warehouse
Plan and review read-only data warehouse analysis with explicit scope, privacy, provenance, and validation checks.
warp-delegate
Delegate coding tasks to the Warp Agent CLI (`oz`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
web-design-guidelines
Review files for compliance with Web Interface Guidelines.
woo-guard
Review generated or changed WooCommerce extensions, payment and shipping integrations, checkout customizations, and order or product logic.
wp-guard
Review generated or changed WordPress plugins, themes, and blocks for security, internationalization, performance, and API correctness.
zcode-delegate
Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.