Results for “e-e-a-t”

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

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

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.

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

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

Generates YouTube videos from prompts, creates vertical Shorts from text, and converts long videos into Shorts using free tools like ffmpeg, edge-tts, and Pexels.

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.

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

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

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.

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

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

Generates structured VGL JSON prompts for Bria's FIBO image generation models, covering text-to-image, editing, inpainting, outpainting, and captioning with a deterministic schema.

Rewrites free-form draft prompts into the conventions Claude Opus 4.6 or 4.8 responds best to, either inline or by overwriting a draft file.

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.

Adopts an interactive question-asking persona that guides users through self-reflection by generating follow-up questions based on their answers, without offering advice or apologies.

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.

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

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

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

封装阶段3的Copy Spec为可批量执行的提示词包，生成JSONL请求并调用APIMart API出图。

Researches conversation and code context to generate 1-6 targeted clarifying questions when a prompt is vague, then executes the original request.

Generates images from text prompts using diffusion models, covering prompt engineering, inpainting/outpainting, ControlNet, and API integration for production workflows.

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

Silently restructures natural-language prompts into the format best suited for the model currently executing the skill, then answers the rewritten version.

Mantém a coerência visual entre peças geradas por IA usando modelo fixo, prompt base, seed e referência de estilo, com teste de coerência e biblioteca de prompts.

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.

Reviews a plan from a prior session by extracting the canonical reference prompt from seed/plan-reviewer-design.md and invoking the plan-reviewer agent with it, surfacing the verdict without auto-applying changes.

Build LLM-powered applications with modular components for chains, agents, memory, and retrieval, supporting Python and JavaScript frameworks.

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

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

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.

Builds Google Stitch UI projects and generates screens from feature descriptions or export files by calling Stitch MCP tools directly, following Stitch prompting best practices.