Prompting Skill Leaderboard

A code quality toolkit for performing repository audits, identifying deletable code, and tracking technical debt.

Adjusts AI output for ADHD users by leading with next actions, numbering steps, and suppressing verbose tangents.

A prompt repository for automating codebase documentation, routing agentic workflow requests, and performing maintainability reviews.

Generates and optimizes tool-specific prompts for LLMs, coding agents, and generative AI tools.

Technical guidance for Three.js 3D materials, high-poly asset optimization, and web design implementation.

Analyzes reference images to extract high-fidelity prompts for recreating visual styles, compositions, and textures in AI image generators.

Rewrites tool descriptions, system prompts, and technical instructions using ASD-STE100 standards to prevent AI parsing errors.

Guidance for designing provider-neutral agent architectures, covering tool design, memory lifecycles, planning, and observability.

Recommends image generation prompts from a library of 10,000+ curated examples with sample images, covering portraits, products, social media, posters, and content illustration.

A set of skills for LLM evaluation, covering synthetic data generation, judge prompt engineering, RAG evaluation, and the creation of human-in-the-loop review interfaces.

A set of 28 critical-thinking skills and mental models, including Bounded Rationality and Circle of Competence, for Agent Skills-compatible AI tools.

A set of skills for product managers and HR operations to automate release notes, changelogs, and 360-degree feedback processes.

Resolves underspecified agent requests into structured IntentSpecs by analyzing sources and asking targeted clarification questions.

Optimizes Claude Code skills by running autonomous loops that score outputs against binary evals and mutate prompts to improve reliability.

A library of 30 Seedance 2.0 prompt generators covering 15 video formats including cinematic, 3D CGI, animation, e-commerce, real estate, social media, and brand storytelling for editors, creators, and marketers.

Transforms vague tasks into structured /goal commands with defined success criteria, boundaries, and verification steps.

Archives Codex-generated images into Eagle, syncing prompts as annotations and organizing files into tags and folders.

A comprehensive prompt library for Higgsfield AI focusing on cinematic acting, 3D mesh generation, and audio-visual control.

Applies banned words, structural variety, punctuation limits, accuracy rules, and voice calibration to produce human-sounding text across tweets, emails, articles, reports, and other formats.

Generates cinematic AI video prompts using a five-stage structure for narrative shorts and complex visual sequences.

A set of behavioral guidelines for LLMs to ensure surgical code changes, minimize over-engineering, and surface assumptions before coding.

Runs a tournament of sub-agents that compete, critique, and revise solutions in a single-elimination bracket to find the optimal answer.

Analyzes and rewrites prompts using 31 research-backed frameworks categorized by intent, including agentic and reasoning tasks.

Documentation-first project planner that outputs specification, implementation plan, task breakdown, branding, and a single-shot agent prompt for autonomous execution.