Skip to content

Claude Skills by SylphxAI

github.com/SylphxAI

61 skillsA× 618 installs50 views

Reference OriginalityAAssess whether a work copies a reference — specific expression evidence, similarity metrics, and provenance. Use when the user asks to review originality, similarity, or copying against a reference. Do not use for legal infringement conclusions.ai-agentsexpressVotes: 0GitHub stars: 2
Resolve Customer Support CaseAResolve one customer support case through a truthful outcome, authorized action, and verified closure. Use for a single ticket, not for designing the support system.ai-agentsVotes: 0GitHub stars: 2
Review DomainAAssess one product or operations domain into ranked findings for a named go/no-go, hold, or risk decision. Use when the user asks for a domain review or assessment that no dedicated review listing covers. Do not use to design the system under review, critique a single claim, or synthesize a literature.ai-agentsgoVotes: 0GitHub stars: 2
Run Incident ResponseACoordinate a production incident from declaration through mitigation, recovery, and learning. Use for live outages, elevated errors, security events, or material data-integrity risk.ai-agentssecurityVotes: 0GitHub stars: 2
Run Product Feedback LoopACluster support tickets, in-app feedback, and authorized store reviews into owned product work and close the loop with the people who wrote in. Use when triaging feedback, mining reviews, or asking what customers said after a launch. Do not use to answer one ticket.ai-agentsVotes: 0GitHub stars: 2
Saas PlatformADesign a multi-tenant SaaS web platform from public acquisition through authenticated workspace — tenancy, entitlements, routes, and first value. Use when the user asks to design a SaaS, web platform, or public-to-authenticated service. Do not use for an app, a game, a single UI flow, or a pricing catalog.ai-agentsVotes: 0GitHub stars: 2
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Select Dependency VersionsASelect an exact package, runtime, framework, SDK, or tool version from the current official registry and support policy. Use when adding, upgrading, pinning, or replacing a dependency, or when the user asks what version to use. Do not use to configure Dependabot or renovate.ai-agentsVotes: 0GitHub stars: 2
Select Next WorkASelect and claim the next high-value work item from current product and repository state. Use when the user wants the agent to choose from an existing backlog. Do not use to finish an already accepted objective.ai-agentsVotes: 0GitHub stars: 2
Synthesize Evidence BriefASynthesize multi-source evidence into one bounded brief with residuals, conflicts, and the next observation worth buying. Use when a consequential question needs a traceable literature or evidence synthesis. Do not use for a single-claim critique, a domain go/no-go review, or ordinary product implementation.ai-agentsgoVotes: 0GitHub stars: 2
Ui FlowADesign or implement one product UI flow with loading, empty, error, and success states, verified on a real render. Use when the user asks to build a screen, fix a form, design a flow, or match an existing design system. Do not use to review an existing flow, extract a design system, or produce store screenshots.ai-agentsVotes: 0GitHub stars: 2
Ui ReviewAReview one product UI flow on a real render — accessibility, responsive composition, motion, performance, and reachable states. Use when the user asks to review UX, check accessibility, verify a screen, or judge whether a flow is ready. Do not use to design or implement the flow, or to produce store screenshots.ai-agentsperformanceVotes: 0GitHub stars: 2