Build and deploy production ML pipelines with data processing, model training, evaluation, and deployment using TensorFlow, PyTorch, or Scikit-learn.
Transform basic instructions into high-quality prompts with optimized structure and clear constraints. Evaluate existing prompts for clarity and specificity while receiving actionable improvement sugg
Continuous self-improvement through learning from corrections and task self-evaluation. Use when: (1) User corrects the agent (No that is wrong, Actually, I...
Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...
Coordinates specialized AI agents to design novel drug candidates with synthesis routes, inventory checks, ADMET/Tox evaluation, pharmacology scoring, and pa...
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Provide comprehensive due diligence support by integrating various data sources and tools to streamline the evaluation process. Enable efficient access to relevant documents, perform analyses, and gen
Analyzes empirical law and economics papers by systematically evaluating problems, empirical challenges, identification strategies, key findings, and academi...
Evaluate any address for home buyers and renters. Get nearby schools, transit, grocery stores, parks, restaurants, and walkability using Camino AI's location...
BTC PoW grind nonce till skill/output benchmark score > threshold. Verifiable excellence for antifragile meritocracy—no hype, pure quality proof. Use for skill evaluation, fork scoring, collab verific
Act as a University Admission Interviewer. You are conducting an interview for a prospective student applying to ${universityName}. Your task is to evaluate the candidate's suitability for the program
Meta-skill: evaluate any Factory Droid skill against the current project codebase and suggest concrete improvements. Use when: a skill feels incomplete, prod...
Craft complete, tailored grant proposals including needs statement, project narrative, budget justification, evaluation plan, sustainability, and support let...
M&A strategy for acquiring companies or being acquired. Due diligence, valuation, integration, and deal structure. Use when evaluating acquisitions, preparin...
Agent-to-Agent task marketplace on Base L2 — create, fund, claim, submit, and settle USDC-backed tasks with AI Oracle evaluation.
Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth.
You are a **quantitative sports betting analyst** tasked with evaluating whether a statistically defensible betting edge exists for a specified sport, league, and market. Using the provided data (hist
Assess ISO/IEC 42001:2023 AI Management System (AIMS) readiness and generate compliance gap analysis with remediation roadmap. Use when evaluating AI governa...
Multi-agent validation framework — 6 independent AI critics evaluate artifacts against rubrics with evidence-grounded findings.
Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting b...
Monte Carlo Crypto Trading Core. Simulates thousands of future price paths (Geometric Brownian Motion) to evaluate win probabilities, risk of ruin, and stop-...
Act as a Code Review Agent. You are an expert in software development with extensive experience in reviewing code. Your task is to provide a comprehensive evaluation of the code provided by the user.
Generate and evaluate ad creatives for Meta (Facebook/Instagram), TikTok Ads, YouTube Ads, Google Ads, and Amazon Ads with script generation, performance sco...