Prompt Engineering

Sibyl 反对者 agent - 挑战主流假设，寻找反面证据和盲点

Control omi reasoning effort level to balance depth, rigor, latency, and token cost.

Prompt debugging skills for LLM developers. Convert conversations from OpenAI, Anthropic, Google, and Helicone into .echo format, and integrate .echo export into your apps. Use with EchoSpace — the local-first prompt debugging workspace.

Learn how to use SKILL by following this SKILL specification.

Capture each prompt into Graphiti memory (episodes) for this repo/user.

解析赛题PDF/Word，抽取任务与数据条件并给出模型选型与验证路线。Invoke when用户提供赛题文档或题目文本，需要确定采用何模型/方法。

**프롬프트 엔지니어링 마스터**: AI 모델(Claude, ChatGPT 등)에게 최적의 결과를 이끌어내는 프롬프트 설계 스킬. 역할지정, 체인오브소트(CoT), 퓨샷, 제로샷, 메타프롬프트 등 26가지 기법을 실무 맥락에 맞게 적용합니다. - MANDATORY TRIGGERS: 프롬프트, prompt, 프롬프트 엔지니어링, AI 질문법, AI 활용법, 프롬프팅, 역할 부여, CoT, chain of thought

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing productio...

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, optimizing for cost or latency, implementing long-running agent systems, agents exhaust memory, or when designing conversation summarization strategies.

Interactive session to create Instructions field content for a Sanity Agent Context MCP. Use this skill whenever users mention tuning agent context, improving agent responses to Sanity data, configuring MCP instructions, setting up content filters, or when their agent gives wrong results from Sanity queries. Also trigger when users say their agent is confused about schema relationships, needs data-specific guidance, or wants to optimize which content the agent can access.

Design effective prompts and optimize context for AI models and agents. Covers prompt engineering foundations (clarity, examples, chain of thought, XML structure), the four context engineering strategies (Write, Select, Compress, Isolate), agent memory and session patterns, and before/after examples showing measurable improvement. Use when writing system prompts, designing agent workflows, optimizing context windows, building prompt templates, structuring few-shot examples, reducing context rot, or improving AI output quality.

Use this skill when you are writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

LLMs, prompt engineering, RAG systems, LangChain, and AI application development

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Recursive Meta-Prompting (RMP) implementation with unified categorical syntax. Supports @mode:iterative, @quality: thresholds, >=> Kleisli composition, and comonadic context extraction. Use when implementing iterative prompt improvement, quality-gated generation loops, or applying categorical fixed-point semantics with convergence guarantees.

Structured prompt construction and quality validation for Jerry Framework. Invoke when building structured prompts, generating NPT-009/NPT-013 constraints, or scoring prompt quality. Guides users through the 5-element prompt anatomy, generates formatted constraints with XML wrapping, and scores prompts against the 7-criterion rubric.

Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

指导在 CodeSpirit 项目中集成 AI 功能的完整开发流程。包括 AI 表单填充、AI 长任务处理、LLM 集成和提示词工程。当用户需要添加 AI 功能、集成 LLM、或开发 AI 驱动的业务功能时使用。

This skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not code. Use it when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.

Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography qualities, dramatic lighting, and editorial-quality aesthetics. Use when users request image generation, need prompt enhancement, or want Midjourney-quality outputs via FLUX 1.1 Pro.

Operational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG grounding/citations, tool/agent workflows, prompt safety (injection/exfiltration), and prompt evaluation/regression testing. Use when designing, debugging, or standardizing prompts for Codex CLI, Claude Code, and OpenAI/Anthropic/Gemini APIs.

Production prompt engineering frameworks for building, testing, versioning, and evaluating prompts. Covers chain-of-thought, few-shot design, system prompt architecture, prompt regression testing, and evaluation rubrics. Use when designing prompts for production systems, running A/B tests on prompts, building prompt libraries, or debugging prompt quality degradation.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Generate optimized indirect prompt injection, H-CoT, and multi-layer attack payloads for AI security testing and CTF competitions with automated family selection and success rate optimization

World-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts, designing AI agents, building knowledge bases, implementing retrieval systems, or optimizing LLM performance at production scale.

Teach Mandarin using an LLM-first pedagogy, backed by a ZFC/Unix-style local engine (`xuezh`) that stores facts, runs mechanical transforms, and produces bounded reports/audio artifacts. Use for review, speaking/tones, graded input, and HSK audits.

Transforms user input prompts into structured, context-aware prompts optimized for CircleTel project workflows

Socratic deep interview with mathematical ambiguity gating before autonomous execution

Critically analyze the output and provide some depth of analysis.

Deep expertise in Azure OpenAI Service — deploy and manage GPT-4o, GPT-4, GPT-3.5-Turbo, Embeddings, DALL-E, Whisper, and TTS models. Covers Standard, Provisioned-Managed, and Global Standard deployment types, fine-tuning workflows, content filtering policies, prompt engineering patterns, Batch API, quota management, and secure production architectures. Uses az cognitiveservices CLI and Azure OpenAI REST API for all operations.

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.

Tari Ootle development instructions for Google Gemini

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.

An Electric Monk engine — two subagents believe fully committed positions on the user's behalf while the orchestrator performs structural contradiction analysis and synthesis. By outsourcing belief work to agents, the user operates from a belief-free position where they can analyze the structure of the contradiction rather than being inside either side. Use when the user wants to stress-test an idea, resolve a genuine tension, build a deeper mental model, or make a high-stakes decision where the tradeoffs are unclear. Works across any domain — technical architecture, product strategy, philosophy, personal decisions, risk analysis, policy, creative direction.

This skill should be used when writing or improving system prompts for AI agents, providing expert guidance based on Anthropic's context engineering principles.

[ARCHIVED] Full 4D Context Canvas reference. For new AI features, use /spec --ai. For debugging, use /ai-debug. For quality checks, use /context-check.

AI music prompt templates and best practices for generating music with AI tools like Suno, Udio, Mureka, and others. Use when user needs to create music prompts, song ideas, or wants guidance on writing effective prompts for AI music generation. Includes bilingual prompt templates for various genres, mood descriptors, instrumentation guidance, and lyric writing tips. Also provides techniques for crafting specific musical outcomes and examples of well-structured prompts in Chinese and English.

Write a simple python function that

generate a more effective response by integrating the provided knowledge before the final

Meta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template generation, prompt optimization, or programmatic prompt composition.

Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".

Recommend suitable prompts from 6000+ Nano Banana Pro image generation prompts based on user needs. Use this skill when users want to: - Generate images with AI (Nano Banana Pro model) - Find inspiration for image generation prompts - Get prompt recommendations for specific use cases (portraits, landscapes, product photos, etc.) - Create illustrations for articles, videos, podcasts, or other content - Translate and understand prompt techniques

AI领域分类器 - 智能分析提示词内容，准确判断所属领域（人像/艺术/设计/产品/视频）

Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.

Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.