Prompt Engineering Agent Skills

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

Detects prompt injection attacks targeting LLM-based applications using regex pattern matching, heuristic scoring, and DeBERTa transformer classification.

Learn and apply prompt engineering techniques for LLMs, image generators, and video models using the inference.sh CLI.

Learn best practices for writing effective AI video generation prompts, covering shot types, camera movements, lighting, style keywords, and model-specific tips for Veo, Seedance, Wan, Grok, and others.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Explains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Optimize AI agents through automated evolution cycles using LLM-driven mutation of prompts, skills, and memory against measurable benchmarks.

Build complex AI systems with declarative programming, optimize prompts automatically, and create modular RAG systems and agents using Stanford NLP's DSPy framework.

Debug, evaluate, and monitor LLM applications with tracing, datasets, and built-in evaluators.

Control LLM output with regex and grammars to guarantee valid JSON, XML, or code generation, enforce structured formats, and build multi-step workflows using Microsoft Research's Guidance framework.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Extract structured data from LLM responses with Pydantic validation, automatic retries, and streaming support across multiple providers.

Train AI models to be harmless through self-critique and AI feedback using a set of constitutional principles, without requiring human labels for harmful outputs.

Generates high-fidelity images using reasoning-driven prompts and structured creative briefs via muapi.ai.

Generate a high-cut-density action/fight scene by composing a 16-cell storyboard image and driving Seedance 2.0 image-to-video from that storyboard.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Transforms fuzzy problems into structured briefs that AI agents can reason about, critique, and act upon, while evaluating how much of the problem can be automated.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Search and browse Civitai models, images, and videos; extract generation prompts; and get download commands for LoRAs and checkpoints.

Covers AI, machine learning, LLMs, prompt engineering, and blockchain development with code examples and best practices for building AI applications and smart contracts.

从OCR识别后的医疗票据文本中提取日期、医生姓名、病人姓名、诊断和总消费，并进行文本矫正，输出JSON格式。

Enhances plain-language requests into structured, reviewable prompts and inspects a self-hosted MCP gateway with provider-free defaults.

Designs or reviews Agentforce agent actions, covering Flow, Apex invocable, and prompt-template actions, including naming, input/output contracts, confirmation, and error behavior.

Runs regression evaluations comparing agent edits against human-approved golden projects, and registers new goldens after human approval.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new problems.

Generates optimized prompts for AI video and image generation across multiple platforms, using cinematic styles and behavioral frameworks for commercial outcomes.

Generates creative launch blueprints for memecoins on pump.fun, including names, symbols, narratives, visual themes, and buyback strategies, with safety guardrails and mandatory disclaimers.

Transforms a rough idea into a detailed design document with an implementation plan through iterative requirements clarification, research, design, and planning.

Estrutura prompts para geradores de imagem e vídeo, otimizando custo e consistência com a marca.

Forces a second, harder escalation pass using the original glazer prompt words verbatim, pushing for a sharper replacement thesis rather than more polish.

Builds or debugs Anthropic Claude integrations using @anthropic-ai/sdk, covering messages, tool use, extended thinking, prompt caching, and streaming.