发现 Skills

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Carmack-level plan review via RepoPrompt or OpenCode. Use when reviewing Flow epic specs or design docs. Triggers on /flow-next:plan-review.

Multi-agent debate system for complex queries. Four agents (Scholar, Logician, Contrarian, Captain) analyze independently, debate, and synthesize a consensus. Use for deeper analysis, second opinions, or stress-testing decisions.

Map metabolites to biological pathways using KEGG, Reactome, and MetaboAnalyst. Perform pathway enrichment and topology analysis. Use when interpreting metabolomics results in the context of biochemical pathways.

Download, prepare, and manage reference panels for phasing and imputation. Covers 1000 Genomes, HRC, and TOPMed panels. Use when setting up imputation infrastructure or selecting appropriate reference panels for target populations.

Comprehensive variant annotation using bcftools annotate/csq, VEP, SnpEff, and ANNOVAR. Add database annotations, predict functional consequences, and assess clinical significance. Use when annotating variants with functional and clinical information.

General-purpose NZBGeek search and SABnzbd download management with interview and task-monitor integration

Kinematic interface and Bit-Joule bridge to the physical world. Activate when the user mentions 'real-world action', 'physical world', 'IoT', 'robot', 'actuator', 'delivery', 'movement', 'hardware', 'sensor', 'physical automation', or when system output must be translated into an action in the material world with irreversible consequences.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Automate Grist tasks via Rube MCP (Composio). Always search tools first for current schemas.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Use when configuring voice (TTS/STT) in Hermes. Covers: TTS providers (Edge, ElevenLabs, OpenAI, xAI, Mistral, NeuTTS, Piper), STT providers (local/faster-whisper, Groq, OpenAI, Mistral), voice config keys, and provider setup. Triggers on: voice, TTS, STT, speech, transcription, text-to-speech, speech-to-text, voice mode.

Git workflow for HASH including branch naming, PR creation, and PR reviews. Use when creating branches, making commits, opening pull requests, or reviewing PRs.

HashQL testing strategies including compiletest (UI tests), unit tests, and snapshot tests. Use when writing tests for HashQL code, using //~ annotations, running --bless, debugging test failures, or choosing the right testing approach.

Troubleshoot Cursor codebase indexing problems. Triggers on "cursor indexing", "cursor index", "cursor codebase", "@codebase not working", "cursor search broken". Use when working with Cursor indexing functionality. Trigger with phrases like "cursor indexing issues", "cursor issues", "cursor".

This skill should be used when the user asks to "create a 3D model with build123d", "design parametric parts", "use builder mode", "use algebra mode", "select faces or edges", "export STEP or STL", or works with build123d CAD programming.

Use when reviewing or enhancing acceptance criteria for user stories. Applies a systematic methodology to ensure comprehensive AC coverage across all 6 categories.

Continuous Integration and Deployment standards for Flutter apps. Use when setting up CI/CD pipelines, automated testing, or deployment workflows for Flutter.

Standards for creating high-quality, granular manual test cases and QA processes. Use when creating manual test cases, defining QA processes, or reviewing test coverage.

OpenClaw plugin providing TODO commands for a markdown TODO.md file.

Activate an accessibility-focused development mode. Acts as a WCAG compliance specialist for auditing and remediating accessibility issues. Use when reviewing code for accessibility, implementing ARIA patterns, or ensuring inclusive design.

Frigate NVR management with AI-powered object detection. Configure cameras, zones, detection settings, recording policies, and Home Assistant integration. Use when working with Frigate, security cameras, NVR setup, object detection, person/car/animal detection, RTSP streams, or video surveillance.