Prompt Engineering Agent Skills

Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Optimizes agent context setup by structuring rules, specs, source files, error output, and conversation history to improve output quality.

Creates, lists, retrieves, versions, and deletes managed prompts in Google Cloud Agent Platform using the Python SDK.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Create, run, and analyze evaluation suites for Microsoft 365 Copilot declarative agents using the @microsoft/m365-copilot-eval CLI.

Build synthetic datasets and data generation pipelines using the Data Designer library.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Generates and edits images using GPT Image 2 across three modes: direct generation via OpenAI-compatible API, prompt engineering for host-native image tools, or pure prompt advisory. Includes 80+ structured templates for posters, UI mockups, product visuals, maps, slides, and more.

Analyze draft prompts to identify intent, scope, and missing context, then generate an optimized prompt with ECC component recommendations. Advisory only — never executes the task.

Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines with observability and security.

Provides guidance and code for production AI workflows including RAG pipelines, vector databases, embedding indexing, prompt engineering, cost estimation, semantic caching, and quality evaluation.

Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.

Injects up to 1 million tokens of external context into AI agent memory, auto-summarizes conversations with tone and intent preservation, and compresses multi-turn history into dense token sequences.

Guides building production-grade AI features with LLM integration patterns, RAG architecture, prompt engineering, and cost optimization.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Provides authoritative, current guidance from OpenAI developer docs using the developers.openai.com MCP server, including model selection, API migration, and prompt-upgrade guidance.

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Performs a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture fitness, and safety — producing a scored report with prioritized remediation actions.

Implement iterative evaluation and refinement loops for AI agent outputs, using self-critique, evaluator-optimizer patterns, and rubric-based scoring to improve quality.

Creates and runs LLM-as-judge evaluators on Arize, including managing tasks, column mappings, and continuous monitoring.

Refines and polishes prompt files by applying proven best practices for structure, wording, and clarity while preserving original intent and formatting.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations from Arize AI.

Reminds the agent to act as an interactive programmer using a live REPL for exploration and modification, with structural editing and todo list management.

Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness, providing detailed improvement recommendations with frameworks, testing methodologies, and educational content.

Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits.

Translates Mermaid sequence diagrams of cryptographic protocols into ProVerif formal verification models (.pv files) for proving security properties like secrecy, authentication, and forward secrecy.

Automates hypothesis generation and testing on tabular datasets using LLMs, combining data-driven discovery with literature integration for scientific research.

Analyze any text to extract a cognitive fingerprint across 12 dimensions, revealing reasoning patterns, decision styles, and thinking signatures.

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Correlate findings across OSINT sources—username enumeration, email lookups, social media profiles, domain records, breach databases, and dark-web mentions—into unified intelligence profiles with confidence scoring and link analysis.