Loading...
Loading...
Found 1,059 Skills
Comprehensive MDX component patterns (Note, Pitfall, DeepDive, Recipes, etc.) for all documentation types. Authoritative source for component usage, examples, and heading conventions.
Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need domain specialization, you want cheaper models to match expensive ones, you heard "fine-tuning will make us AI-native", you have 500+ training examples, or you need to train on proprietary data. Covers DSPy BootstrapFinetune, BetterTogether, model distillation, and when to fine-tune vs optimize prompts.
Comprehensive documentation specialist covering API documentation, technical writing, design documentation, migration guides, and changelog generation. Use when creating OpenAPI/Swagger specs, generating SDKs, writing user guides, creating README files, documenting architecture, writing design specs, creating ADRs, writing migration guides, or generating changelogs from git commits. Handles versioning, examples, developer experience, and user-facing documentation.
Provides comprehensive uni-app-x component and API integration guidance. Use when the user needs official uni-app-x components or APIs, wants per-component or per-API examples, or needs cross-platform compatibility details for uni-app-x.
Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques. Use when building LLM applications requiring reliable outputs, implementing RAG systems, creating AI agents, or optimizing prompt quality and cost. Covers OpenAI, Anthropic, and open-source models with multi-language examples (Python/TypeScript).
Generate Zod-based environment variable management code from .env.example files. Use when you need to create type-safe env management, standardize env handling, or generate env schemas.
Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.
shadcn-vue component integration for Inertia Rails Vue 3 (NOT Nuxt): forms, dialogs, tables, toasts, dark mode, and more. Use when building UI with shadcn-vue components in an Inertia + Vue app or adapting shadcn-vue examples from Nuxt. Wire shadcn-vue inputs to Inertia Form via name attribute and #default scoped slot. Flash toasts require Rails flash_keys initializer config.
shadcn-svelte (bits-ui) component integration for Inertia Rails Svelte (NOT SvelteKit): forms, dialogs, tables, toasts, dark mode, and more. Use when building UI with shadcn-svelte components in an Inertia + Svelte app or adapting shadcn-svelte examples from SvelteKit. Wire shadcn-svelte inputs to Inertia Form via name attribute and {#snippet} syntax. Flash toasts require Rails flash_keys initializer config.
Analyze and extract design patterns from visual examples. Deconstructs design systems, color palettes, typography, and layout principles from reference materials.
Optimize, rewrite, and evaluate prompts using the Anthropic 1P interactive prompt-engineering tutorial patterns (clear/direct instructions, role prompting, XML-tag separation, output formatting + prefilling, step-by-step “precognition”, few-shot examples, hallucination reduction, complex prompt templates, prompt chaining, and tool-use XML formats). Use for 提示词优化/Prompt优化/Prompt engineering, rewriting system+user prompts, enforcing structured outputs (XML/JSON), reducing hallucinations, building multi-step prompt templates, adding few-shot examples, or designing prompt-chaining/tool-calling scaffolds.
Help developers write Services in accordance with project guidelines, following the best practices of the tRPC + Service + DAO architecture. Provide guidance on Service structure, dependency injection, error handling, code examples, templates, boilerplate code generation, and best practice validation. Use this when creating or refactoring Service files in the codebase.