发现 Skills

Run an end-to-end smoke test against a Pipecat voice agent: spin up a candidate bot via voice-agent-qa, drive N turns, persist the transcript to the backend, fetch the resulting report, and diff against a known-good baseline. Surface regressions clearly. Use when the user says "smoke test the voice agent", "run nightly QA", "check the voice pipeline", "test the bot end-to-end", or similar.

Use when adding or improving tests in a React project that uses Vitest — covers component testing with Testing Library, mocking hooks, and coverage configuration.

Secure secret handoff from human to AI. Use when you need sensitive information from the user (API keys, passwords, tokens, credentials, secrets). Never ask for secrets via chat — use Confidant instead.

Generate and animate procedural maps using cellular automata rules on a TileMap in Godot 4, with configurable tile IDs and update rate.

Best practices and patterns for building robust PyQt6 desktop applications

Apple Human Interface Guidelines for Apple TV. Use when building tvOS apps that rely on focus-based navigation, Siri Remote input, or living-room viewing experiences. Triggers on tasks involving Apple TV, tvOS, 10-foot UI, or media playback.

Expert in Jungian analytical psychology, depth psychology, shadow work, archetypal analysis, dream interpretation, active imagination, addiction/recovery through Jungian lens, and the individuation process - grounded in primary sources and clinical frameworks. Activate on 'Jung', 'Jungian', 'shadow work', 'archetypes', 'dream interpretation', 'active imagination', 'individuation', 'anima', 'animus', 'collective unconscious', 'addiction', 'recovery', 'spiritus contra spiritum'. NOT for therapy or diagnosis (only licensed analysts diagnose), active psychosis, severe dissociation, or replacing the relational container of actual Jungian analysis.

Expert in residential hollow space detection, hidden room discovery, and safe room planning. Helps map house dimensions, identify anomalies suggesting hidden spaces, and safely explore potential voids. Knowledge of architectural history, construction methods, and non-destructive investigation techniques. Activate on "panic room", "hidden room", "secret room", "hollow space", "house mapping", "find hidden space", "room dimensions", "hidden door", "false wall", "priest hole", "prohibition era", "safe room". NOT for illegal entry, structural modifications without permits, or bypassing security systems.

Fix build errors and breaking changes after upgrading MSTest from v3 to v4, or plan a complete MSTest v3-to-v4 migration. Use when a user says "upgrade to MSTest v4", "MSTest 4 migration", "MSTest v4 breaking changes", "tests don't compile after upgrading MSTest", or sees errors CS0507, CS0103, CS1061, CS1615 after updating MSTest packages from 3.x to 4.x. USE FOR: Execute to ExecuteAsync, CallerInfo constructor on TestMethodAttribute, sealed custom attributes, ClassCleanupBehavior removal, TestContext.Properties Contains to ContainsKey, Assert.ThrowsException to ThrowsExactly, Assert.IsInstanceOfType out parameter removal, ExpectedExceptionAttribute removal, TestTimeout enum removal, [TestMethod("name")] to DisplayName syntax, TreatDiscoveryWarningsAsErrors, TestContext.TestName in ClassInitialize, MSTest.Sdk MTP changes, dropped TFMs (net6.0/net7.0 to net8.0+). DO NOT USE FOR: migrating from MSTest v1/v2 to v3 (use migrate-mstest-v1v2-to-v3 first), migrating between different test frameworks, or general .NET upgrades.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Expert guidance for creating, managing, and using Terraform modules. Use this skill when the user wants to create reusable infrastructure components, standardize Terraform patterns, or needs help with module structure and best practices for AWS, GCP, or Azure.

Quality assurance specialist for security, performance, accessibility, comprehensive testing, and quality standard alignment. Use for test, review, security audit, OWASP, coverage, lint work, and ISO/IEC 25010 or ISO/IEC 29119-aligned QA recommendations.

Benchmark skill cost/quality against Opus baseline. Monitor LiteLLM spend, generate cost dashboards, compare runs. 3 modes: run, report, compare. v1.0.

Market and competitive analysis toolkit. Research competitors, analyze market positioning, identify differentiation opportunities, and create comprehensive competitive landscape assessments for software projects.

Compresses the current session context by identifying relevant info, summarizing key findings, and discarding noise. Produces a compact briefing that replaces long conversation history. The mid-session equivalent of generate-handover.

Transform verbose voice input into optimized Claude prompts

Advanced log analysis for openstack-k8s-operators operators with pattern matching and intelligent insights

A code design and public API specification review skill for the OpenLark Rust SDK (focused on crates/modules). It systematically checks entry points and API surface design, feature gating, Request/Service/Builder consistency, endpoint taxonomy, Config and error handling, export and documentation synchronization, testing and alerting controls, and generates a prioritized remediation checklist and actionable refactor plans. Trigger keywords: design review, crate design, API design, public API, feature flag, endpoint, Builder/Service, architectural consistency.

Provide proven marketing strategies and growth ideas for SaaS and software products, prioritized using a marketing feasibility scoring system.

Activates the Pickle Rick persona. Use this ONLY when the user explicitly requests to start the "Pickle Rick" mode or loop. DO NOT use this for general greetings (e.g., "hi") normal assistance.

Fivemanage SDK for FiveM — installation, screenshots (takeImage, takeServerImage, uploadImage), and centralized logs (Log, Info/Warn/Error). Use when integrating Fivemanage, capturing player screenshots, uploading images, or sending logs to the Fivemanage dashboard.

Excel file processing and manipulation using the Excel MCP Server

Manually trigger plan-sync to update downstream task specs after implementation drift. Use when code changes outpace specs.

Query dbSNP for rsID lookups, variant annotations, and cross-references to other databases. Use when mapping between rsIDs and genomic coordinates or retrieving basic variant information.