PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.

Use when the user asks to install, initialize, integrate, upgrade, or document GitHub Spec Kit. Creates a repository-specific constitution and SPECKITINIT.md with complete copy-paste workflows using the public workflow catalog. Do NOT use to implement application features; use the installed Spec Kit implementation command.

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques, compression strategies, memory architectures, multi-agent patterns, evaluation, tool design, and project development.

Use when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and OpenAPI generated automatically. Covers concrete actions such as defining tools and handlers, configuring authentication middleware, setting up HTTP and stdio transports, generating OpenAPI documentation, wrapping existing APIs via proxy mode, and wiring up the full CLI workflow.

Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.

Implement cross-cutting Hotwire UX feedback patterns: loading states, busy indicators, progress bars, optimistic UI, render interception, and view/page transitions. Prefer this skill when the core goal is perceived performance and user feedback, independent of a single feature domain. Use hwc-forms-validation for form correctness and validation behavior, hwc-navigation-content for navigation/history/cache mechanics, hwc-realtime-streaming for push/stream orchestration, hwc-media-content for media-specific behavior, and hwc-stimulus-fundamentals for base Stimulus API questions.

Implement real-time Hotwire behavior: Turbo Streams over WebSocket/SSE, custom stream actions, inline stream tags, live list updates, and cross-tab state synchronization. Prefer this skill when the core problem is push-based updates or stream action orchestration. Use hwc-navigation-content for pull-based pagination/tab/lazy-navigation flows, hwc-forms-validation for form lifecycle and validation, hwc-media-content for media upload/playback behavior, hwc-ux-feedback for generic loading/progress/transitions, and hwc-stimulus-fundamentals for non-stream Stimulus fundamentals.

Build Hotwire navigation and content-discovery flows: Turbo Frame pagination, tabbed navigation, lazy loading, faceted filtering/search, cache lifecycle, scroll restoration, and visit/render control. Prefer this skill when the core problem is request/response navigation state and browser history behavior. Use hwc-forms-validation for form validation and inline edit flows, hwc-realtime-streaming for WebSocket/Turbo Stream push updates, hwc-media-content for image/video/audio features, hwc-ux-feedback for generic loading/progress/transition polish, and hwc-stimulus-fundamentals for Stimulus APIs not centered on navigation.

Handle media-heavy Hotwire features: image/video/audio uploads, previews, playback controls, progress tracking, and third-party media integrations (for example WaveSurfer, Swiper, Picture-in-Picture, Blurhash). Prefer this skill when the core problem is media rendering, playback state, or media library integration. Use hwc-realtime-streaming for server-pushed Turbo Stream updates, hwc-navigation-content for non-media pagination/tab/lazy-navigation flows, hwc-forms-validation for form validation and inline-edit behavior, hwc-ux-feedback for generic loading/transition patterns, and hwc-stimulus-fundamentals for Stimulus primitives not specific to media.

Handle Hotwire form workflows: form submission lifecycle, inline editing, validation errors, typeahead/autocomplete, modal forms, and external form controls. Prefer this skill when the core problem is correctness and UX of form interaction. Use hwc-navigation-content for pagination/tabs/filter navigation, hwc-realtime-streaming for WebSocket/Turbo Stream broadcasting, hwc-media-content for image/video/audio behavior, hwc-ux-feedback for generic loading/transition polish, and hwc-stimulus-fundamentals for framework-level Stimulus APIs not tied to forms.

Entry signal patterns with historical success rates. Use when deciding whether to open a position.

[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.

Generates Tzatziki-based Cucumber BDD tests (.feature files) from a functional specification. Use this skill whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin — especially in Java/Spring projects using Tzatziki step definitions for HTTP, JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions writing integration tests, acceptance tests, or end-to-end tests in a project that already has Tzatziki/Cucumber dependencies, including TestNG-based setups.

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.

Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.

Use when writing or reviewing Go code in this repo that transcribes prerecorded audio with Listen v1 REST or streams live audio with Listen v1 WebSockets. Route text generation to deepgram-go-text-to-speech, text analysis to deepgram-go-text-intelligence, audio analytics overlays to deepgram-go-audio-intelligence, and Flux or other v2 conversational work to deepgram-go-conversational-stt.