“llm implementation”的搜索结果

Auto-activates when generating Product Requirements Prompt (PRP) documents from synthesized design outputs, providing structured templates and comprehensive implementation guidance.

中文简介正在准备中。当前显示原文说明。

Design system architecture, API contracts, and data flows. Use when translating analyzed requirements into technical design for feature implementation.

中文简介正在准备中。当前显示原文说明。

Create distinctive, production-grade frontends by composing design dimensions and tech-specific implementations

中文简介正在准备中。当前显示原文说明。

Turn a feature idea into INVEST-compliant user stories, epics, PRPs/PRDs, and sprint plans. Use when breaking down a feature for implementation or planning a sprint. Trigger on "write user stories", "break this into stories", "create a PRP", "plan the sprint", "story".

中文简介正在准备中。当前显示原文说明。

Validate user stories — INVEST scoring, story-to-test coverage mapping, PRP completeness, and development-readiness assessment. Use after writing stories and before starting implementation. Trigger on "validate the stories", "are these stories ready", "INVEST check", "story coverage", "is this ready to build".

中文简介正在准备中。当前显示原文说明。

Design component architecture, REST API contracts, and data models (Pydantic schemas) before implementation. Use when planning how to build a feature, defining endpoints, or modeling data. Trigger on "design the architecture", "design the API", "data model", "how should I structure this feature".

中文简介正在准备中。当前显示原文说明。

Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.

中文简介正在准备中。当前显示原文说明。

Analyze feature requirements, dependencies, and security considerations. Use when starting feature implementation from GitHub issues to understand scope, technical feasibility, and risks.

中文简介正在准备中。当前显示原文说明。

Update all project documentation including implementation docs, user guides, API docs, and architecture diagrams. Use when finalizing features to ensure comprehensive documentation.

中文简介正在准备中。当前显示原文说明。

Dispatch reviews to external companion AIs (Codex, Gemini, Claude) for an independent second opinion on code changes, PR readiness, doc completeness, architecture, or implementation status. Use when you want a fresh-eyes review beyond Claude-native. Trigger on "get a second opinion", "companion review", "review my changes", "review the PR". For Claude-only quality checks use /code-review.

中文简介正在准备中。当前显示原文说明。

Build production-grade Claude Code CLI skills with fallback architecture, TypeScript implementation, and creativity directives. Based on Critical Thinking Bug Bounty Podcast Episode 166 — "Building Claude Skills as a Bug Bounty Hunter."

中文简介正在准备中。当前显示原文说明。

Scan projects for credential leaks, secrets in code, insecure patterns, LLM API key exposure, PII leakage to external AI services, and .env/.gitignore misconfigurations. Especially useful for data and API integrations, regardless of implementation language.

中文简介正在准备中。当前显示原文说明。

Build high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Covers design principles, architecture, implementation patterns, and evaluation-driven development.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

AI-powered design review for Figma components with weighted dual-scoring system. Evaluates Style Guide Implementation (70%) and LLM Metadata Accessibility (30%). For export, hands off to atomic-design skill.

中文简介正在准备中。当前显示原文说明。

You are an expert in the interface between LLMs and the outside world. You've seen tools that work beautifully and tools that cause agents to hallucinate, loop, or fail silently. The difference is almost always in the design, not the implementation.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

Graded exposure for anxiety disorders: Fear hierarchy, SUDs scale, exposure planning and guidance. Psychoeducation only, not implementation.

中文简介正在准备中。当前显示原文说明。

Structured problem solving in 6 steps: Problem definition, goals, brainstorming, evaluation, implementation, and review.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

Use when evaluating, critiquing, transforming, or generating a Master's Informatics thesis idea, research gap, novelty, research question, experiment, AI/ML/CV/NLP/LLM/Edge-AI method, or when distinguishing R&D research from software implementation using the Frascati Manual 2015.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

Behavioral guardrails for implementation work. Reduces common LLM coding mistakes: overcomplication, silent assumption-picking, scope drift, and unverifiable success criteria. Load on Builder and software-engineer-mode.

中文简介正在准备中。当前显示原文说明。