Tag: prompt-engineering
Oracle Context-Aware Prompting CLI
Oracle bundles prompts and selected files into a single request to provide LLMs with real repository context via API or browser automation. It supports advanced file filtering, session management, and multi-engine workflows.
Authoring and Refining Agentic Skills
This skill guides the end-to-end process of designing, improving, and evaluating reusable agent skills. It provides structured methodologies for enhancing trigger quality, auditing skill collections for overlap, and ensuring robust, testabl…
Oracle: Context-Aware Prompt Bundling CLI
A CLI tool that bundles prompts and repository files into single-shot requests for LLMs using API or browser engines. It supports advanced file globbing, session management for long-running tasks, and token usage previews.
Comprehensive prompt evaluation and regression testing tool
This framework facilitates the creation and execution of robust prompt evaluation suites, supporting deterministic assertions, model-graded rubrics, and diverse providers like LLMs and HTTP endpoints. It ensures comprehensive coverage for r…
Redteaming Plugin Development Standards and Guidelines
This guide establishes the required standards and structures for developing redteaming plugins and graders. It details standardized tags, rubric formats, and variable handling, including specific guidance for multimodal prompts, ensuring ro…
Island Rescue Formatting Skill
A prompt-based skill that enforces the insertion of the word STOP after every four words in agentic responses.
Skill Creator for Agentic Workflows
An agentic skill for the end-to-end development of new skills, covering drafting, quantitative evaluation, and iterative refinement. It assists in capturing user intent, authoring structured SKILL.md files, and optimising descriptions for i…
Drafting client-facing legal emails
Provides structured guidelines and formatting rules for drafting professional, client-facing emails accompanying legal deliverables. It focuses on clear, declarative headings, actionable summaries, and appropriate use of footnotes for legal…
AI Agent Cost Optimizer
Optimises AI agent token and credit usage by classifying task complexity and routing requests to the most cost-efficient model tier. It reduces API expenses by up to 75% through prompt quality evaluation, task splitting, and context pruning…
Writing Effective MCP Server Instructions
Provides guidance and templates for authoring the instructions parameter in MCP server initialisation to improve LLM tool orchestration. It focuses on defining cross-tool workflows, operational constraints, and sequencing patterns.
Systematic Agent Prompt and Instruction Optimizer
This skill systematically analyzes and strengthens agent instructions and prompts using advanced prompt engineering techniques. It enforces a rigorous, multi-stage gated flow to ensure reliability, maintain original intent, and prevent the …
Guidelines for Robust LLM Integration
This skill outlines best practices for implementing Language Model functionality, focusing on structured code patterns, mandatory Zod schema validation, and robust error handling. It guides developers on separating system and user prompts w…
AI Visual Art and Design Generation Expert
This skill orchestrates complex visual creative workflows, enabling users to generate, refine, and search for AI-powered images and mockups. It manages multi-step processes, including prompt enhancement, parallel generation, and reference i…
Generate Designer Mockup Prompts from UI Brief
This skill translates a functional UI brief (e.g., dashboard, pricing page) into a highly structured, anti-slop prompt for advanced image generation models. It intelligently selects the optimal model and embeds deep design intelligence, ens…
Prompt Dialect Translator for Image Models
This skill translates normalized asset briefs into the precise prompt dialect required by various image models, including SDXL, Midjourney, and Imagen. It intelligently manages model-specific constraints such as token budgets, negative prom…
T2I Prompt Dialect Transformer
Rewrites asset briefs into the specific prompt syntax, token budgets, and model-specific constraints required by various text-to-image models. It manages negative prompt translation, brand palette injection, and text-in-image character limi…
Software Asset Generation and Routing Skill
This skill classifies software asset briefs and routes them to optimal image models via inline SVG, external prompt, or API execution modes. It manages prompt rewriting for specific model dialects and orchestrates post-processing pipelines …
UI Mockup Prompt Generator
Transforms UI briefs into high-fidelity, anti-slop prompts for advanced image generation models such as Flux 2 and Midjourney. It implements sophisticated routing logic and design principles to avoid common AI-generated UI clichés and produ…
Text-to-Image Prompt Dialect Rewriter
Transforms normalised asset briefs into model-specific prompt dialects for various text-to-image engines including Flux, SDXL, and Midjourney. It automatically manages negative prompt translation, token budgets, and model-specific constrain…
Brand-Consistent Illustration Set Generator
This skill generates cohesive sets of brand illustrations (e.g., empty states, onboarding) by enforcing strict style adherence. It manages brand bundles, injecting style references, hex palettes, and technical constraints across multiple mo…
Anti-Slop UI Mockup Prompt Generator
Transforms UI briefs into high-fidelity, anti-slop prompts for image generation models such as Flux 2 and Midjourney. It intelligently routes requests to the optimal model based on specific requirements like text density or transparency to …
AI Music Composition and Generation Skill
This skill translates complex musical intent into high-quality AI audio using the Lyria 3 models. It supports advanced prompting, including structural tags, lyrics, and detailed genre descriptors, for generating both quick clips and full co…
Advanced AI Image Generation and Editing Skill
This skill provides an advanced workflow for generating, editing, and composing high-fidelity images using Gemini's media models. It handles the entire lifecycle, including expert prompt engineering, model selection, and iterative refinemen…
Image Prompt Dialect Translator for AI Models
This skill translates a normalized asset brief into the precise prompt dialect required by various image generation models (e.g., SDXL, Midjourney, Ideogram). It intelligently manages model-specific constraints, including token budgets, neg…