Diagnose which agent enforcement mechanisms (rules, hooks, skills) fired during a task and which did not. Produces a FIRED / NOT FIRED / N/A report per mechanism. Use when the user asks to review what worked, check enforcement, audit the agent system, or evaluate whether rules gripped. For fixing gaps found, hand off to reviewing-agent-infrastructure.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "reviewing-agent-effectiveness" with this command: npx skills add Jose-Luis-Nunez/skillsmp-jose-luis-nunez-jose-luis-nunez-reviewing-agent-effectiveness
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Review Swift/SwiftUI code and validate changes. Checks for architecture violations, hardcoded styling, dead code, missed reuse, AppStyle consistency, layout robustness, MVVM compliance, referential integrity, and anti-patterns. Use when the user asks to review code, audit styling, verify architecture, validate changes, or clean up after refactoring.
Scaffold a new SwiftUI feature module, extend an existing feature, or create a picker sheet with correct project conventions. Use when the user asks to create a new feature, screen, page, module, view, tab, picker, calendar, schedule, dashboard, settings, or add functionality to an existing feature. Also use when asked to build a neue Seite, neues Feature, neuer Screen, new screen, or new page in the FitnessApp iOS project.
Diagnose and fix failing XCUITest UI tests in the FitnessApp project. Investigate selector-not-found errors, scheme/build-config issues, fixture seeding mismatches after SwiftData refactors, and timing flakes. Use when a UI test fails, when a selector is not found, when investigating timeout errors, or when production-code changes broke UITestLaunchStrategy or test-fixture seeding.
Conduct systematic deep research on technical topics with source verification, triangulation, and citation-backed reports. Use when the user asks for deep research, comprehensive analysis, technology comparison, trend analysis, state of the art review, or architecture evaluation. Not for simple lookups, debugging, or questions answerable with 1-2 searches.