meleantonio
- 66 skills
- 0 followers
- 4 hours ago last updated
- ▌ Research Sdd 2 · meleantonioUse for planning a nontrivial economics research change before editing: empirical specs, data pipeline changes, robustness checks, paper sections, or referee-response tasks. Trigger on research-sdd, spec, design memo, requirements, robustness plan, or implementation plan.
- ▌ Replication Checker 2 · meleantonioUse when asked to verify reproducibility, audit a replication package, check a clean run, validate run instructions, or review before sharing research code.
- ▌ Loop On Verification 2 · meleantonioUse when a task has explicit, mechanically checkable acceptance criteria and the agent should iterate implement, verify, and revise until GREEN or a maximum of three iterations is reached.
- ▌ Assessment Cycle · meleantonioRun an interactive full assessment process: elicit a learning outcome and assessment brief, build and validate a rubric with synthetic calibration submissions, then mark real work with evidence-based feedback and feedforward. Use whenever a user asks to design a rubric, test or calibrate a rubric, assess submissions, grade work, or generate assessment feedback.
- ▌ Research Economic Frontiers · meleantonio bundleFind, select, design, execute, and independently audit frontier economics research using verified literature gaps, claim-specific contracts, diverse theory and empirical routes, reproducible analysis, and conservative contribution gates. Use for open or underexplored economics questions, paper ideas, research-gap searches, theoretical model development, causal or predictive empirical designs, replication projects, pre-analysis planning, long-horizon multi-agent economics research, referee reports, and claims that a contribution is novel or publication-ready.
- ▌ Prove Open Problems · meleantonio bundleConduct rigorous, long-horizon research on open mathematics problems through target triage, exact success contracts, diverse proof-search portfolios, computational falsification, lemma tracking, adversarial audits, and reproducible proof packaging. Use when asked to prove or disprove an open conjecture, make defensible progress on a research-level problem, select tractable open problems, stress-test a candidate proof, or organize a sustained AI-assisted mathematics research run.
- ▌ Research Loop · meleantonioHow to run the portfolio research loop for open problems — route ledgers, explorer independence, blocked-route discipline, computation-as-evidence, adversarial audit cycles, and honest exits. Use when orchestrating or resuming a /prove run.
- ▌ Proof Contract · meleantonioHow to write a proof contract — the prompt-as-contract technique for open mathematical problems. Use when drafting or reviewing a contract that defines exactly what counts as solving a problem, before any proving starts.
- ▌ Hooks · meleantonioUse when you want to configure a lifecycle hook that runs a verification command automatically after the agent edits a file or completes a session. Works with Cursor, Claude Code, and Codex.
- ▌ Reminders · meleantonio bundleCreates, lists, and completes items in macOS Reminders.app via AppleScript. Use when capturing todos, listing open tasks, or marking reminders done from a self-hosted macOS agent.
- ▌ System Info · meleantonio bundleSummarizes macOS battery, disk usage, VPN/network service names, hostname, and top CPU processes. Use when the user asks about machine health, connectivity, or whether a laptop is on battery before long agent tasks.
- ▌ Calendar Check · meleantonio bundleLists events from macOS Calendar.app within a time range using AppleScript. Use when checking availability, summarizing the day, or before scheduling messages or tasks on a self-hosted macOS agent.
- ▌ Imessage Smart · meleantonio bundleReads recent iMessage history from the local Messages database and sends iMessages via AppleScript. Use when the user asks to text someone, check conversation context before replying, or send an iMessage from a self-hosted Cursor agent on macOS.
- ▌ Open Math Prover · meleantonioAttack an open mathematical problem end-to-end using problem selection, CDC-style problem-specific prompts, multi-approach search, proof drafting, and adversarial audit. Use when the user wants to prove or disprove an open problem, attack Erdős problems, run a long mathematical research loop, or invoke /open-math-prover. Keywords: open problem, proof, disproof, Erdős, math research, adversarial audit, multi-agent proof search.
- ▌ Adversarial Audit · meleantonioIndependently attack a candidate math proof or disproof: check exact claim match, edge cases, hidden assumptions, circular reductions, non-counting partial results dressed as solutions, and lemma counterexamples. Use when reviewing a proof draft, after a research loop iteration, or when invoking /adversarial-audit. Keywords: audit proof, adversarial review, gap finding, proof check, referee math.
- ▌ Select Open Problem · meleantonioFilter and score candidate open math problems for AI-assisted attack. Prefer actively discussed problems; deprioritize those tied to major open conjectures or clearly out of reach. Use when choosing among Erdős problems, open problems lists, or deciding whether a problem is a good target. Triggers: /select-open-problem, problem selection, which problem to try, filter open problems.
- ▌ Formalize Proof · meleantonioFormalize a natural-language mathematical proof in Lean 4 (or another kernel) incrementally: small goals first, expand, audit mismatches, refactor. Use after an informal proof of an open problem is drafted and audited, or when the user asks for Lean formalization of a proof artifact.
- ▌ Craft Proof Prompt · meleantonioBuild a problem-specific open-problem proof prompt that defines success, bans weaker substitutes, lists traps, and configures multi-agent adversarial search. Use when preparing Codex/Cursor/Claude goals for proving or disproving a conjecture, or when asked to generate prompts in the Wang/OpenAI cycle-double-cover style.
- ▌ Prove Open Problem · meleantonioAttack an open mathematical problem end-to-end using the Wang/Codex Erdős workflow: select tractability, craft a problem-specific proof prompt, run a long attempt→audit→repair research loop with multi-agent search, and emit LaTeX/Python/Lean artifacts. Use when the user asks to prove, disprove, resolve, or attack an open math problem (Erdős, conjectures, research questions), or when they mention prove-that-shit / open-problem proving.
- ▌ Adversarial Proof Audit · meleantonioIndependently attack a candidate mathematical proof: find gaps, circular lemmas, silent hypothesis changes, insufficient uniformity, and false completions. Use after any draft proof of an open problem, before claiming success, or when the user asks to audit, stress-test, or red-team a proof.
- ▌ Select Tractable Problem · meleantonioFilter open math problems for agent attackability: prefer actively discussed problems, demote those tied to major conjectures or requiring new theory. Use before long proof runs or when the user asks which Erdős/open problems to attempt.
- ▌ Testing · meleantonioTesting conventions using pytest. Use when writing tests, creating fixtures, or running test suites.
- ▌ Code Style · meleantonioPython code style and formatting standards using Ruff. Use when writing or reviewing Python code.
- ▌ Git Workflow · meleantonioGit workflow and commit conventions. Use when committing code, creating branches, or making pull requests.
- ▌ LLM Development · meleantonioLLM and ML development best practices with LangChain and transformers. Use when building AI/ML applications.
- ▌ Techdebt · meleantonioFind and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.
- ▌ Commit Push Pr · meleantonioCommit changes, push to remote, and create a pull request. Use for completing features or fixes ready for review.
- ▌ Code Simplifier · meleantonioSimplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.
- ▌ Sdd · meleantonio bundleImplements the Spec-Driven Development lifecycle (Intent, Requirements, Design, Tasks, Build) for structured feature development. Use when the user wants to scaffold a new feature spec, generate EARS requirements, create a technical design, break work into tasks, or check spec status. Trigger on keywords: sdd, spec-driven, ears requirements, feature spec.
- ▌ Hank Modeling · meleantonio bundleGuides HANK modeling workflows including calibration review, equilibrium checks, and transition diagnostics. Use when working on heterogeneous-agent macro models, household distributions, policy experiments, or transition-path questions.
- ▌ Game Theory Analysis · meleantonio bundleStructures game-theory analysis across normal-form and extensive-form settings. Use when defining players, actions, information, equilibrium concepts, or comparative statics in strategic interaction problems.
- ▌ Spec Tasks To Github · meleantonioExports approved spec/tasks.md entries into GitHub issue drafts with labels, branch names, and acceptance criteria. Use when syncing SDD tasks to issues, creating a swarm milestone from spec, or generating labeled issue bodies for feat/issue-N branches.
- ▌ Applied Microeconometrics · meleantonio bundleGuides applied microeconometrics workflows for estimands, identification, specification, inference, and robustness. Use when working on DiD, IV, RD, panel regressions, treatment effects, or empirical design questions.
- ▌ Github Swarm Orchestration · meleantonio bundleCoordinates multi-agent research work through GitHub issues, branches, and PRs with explicit review and verifier gates. Use when running a swarm, parallel issues, orchestration log, feat/issue-N branches, merge order, consistency pass before merge, or Day 3-style lab workflow.
- ▌ Economics Literature Review · meleantonio bundleFinds and synthesizes recent economics literature for a research question, prioritizing top economics journals and strong working-paper venues, resolving paywalled links through IDEAS/RePEc or author webpages, and writing a markdown review. Use when the user asks for a literature search, literature review, related-work scan, paper shortlist, bibliography, or economics article review.
- ▌ Replication And Research Hygiene · meleantonioSupports replication, result handoff, and canonical research pipelines. Use when organizing empirical or quantitative research code, preparing tables and figures, or making work rerunnable by someone else.
- ▌ Research Sdd · meleantonioUse for planning a nontrivial economics research change before editing: empirical specs, data pipeline changes, robustness checks, paper sections, or referee-response tasks. Trigger on research-sdd, spec, design memo, requirements, robustness plan, or implementation plan.
- ▌ Data Reviewer · meleantonioUse for read-only checks of economics datasets, data maps, variable coding, panel balance, sample restrictions, and synthetic-data caveats before estimation or replication.
- ▌ Paper Polisher · meleantonioUse to polish author-owned economics prose in Markdown or LaTeX while preserving meaning, citations, estimates, and identification caveats. Trigger on polish paper, improve prose, deslop, edit abstract, edit introduction, or referee-response wording.
- ▌ Referee Checklist · meleantonioUse for pre-submission economics paper review, referee-style reports, identification checks, and response-to-referee planning on author-owned, public, or approved material.
- ▌ Replication Checker · meleantonioUse when asked to verify reproducibility, audit a replication package, check a clean run, validate run instructions, or review before sharing research code.
- ▌ Loop On Verification · meleantonioUse when a task has explicit, mechanically checkable acceptance criteria and the agent should iterate implement, verify, and revise until GREEN or a maximum of three iterations is reached.
- ▌ Andrew Ng · meleantonio bundleApplies the reasoning, principles, and frameworks of Andrew Ng (machine learning pioneer, co-founder of Coursera and DeepLearning.AI, Stanford University, and former Google Brain lead). Use this skill whenever the user is navigating AI application development, agentic workflows, automation strategy, AI-native software engineering, or rapid prototyping. Trigger this skill when discussing career advice in the AI era, evaluating AI regulations, structuring machine learning projects, or deciding how to integrate AI into a business. It emphasizes task-based automation, data-centric ML, and driving the cost of proof-of-concepts to zero.
- ▌ Jeff Dean · meleantonio bundleApplies the engineering and research philosophies of Jeff Dean, Chief Scientist at Google DeepMind and Google Research. Reach for this skill whenever you are designing large-scale distributed systems, optimizing latency and energy efficiency, or making architectural decisions about machine learning infrastructure. It should trigger automatically for topics involving hardware-ML co-design, model distillation, sparse activation, massively multi-task models, or scaling systems by 5x to 10x. Use this skill to evaluate system bottlenecks, transition from specialized to unified models, and optimize experimental velocity. Apply his mental models to avoid premature 100x scaling and to treat AI models as reasoning engines rather than memorization databases.
- ▌ Fei Fei Li · meleantonio bundleApplies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI. Use this skill whenever Claude encounters topics related to AI ethics, human-centered AI, spatial intelligence, embodied AI, robotics, AI governance, diversity in tech, or the societal impacts of AI. Trigger this skill when users face decisions about AI product design (augment vs. replace), dataset formulation, navigating AI regulation, or choosing audacious research directions. Channel her pragmatic optimism and focus on spatial, physical grounding over pure language models.
- ▌ Kaiming He · meleantonio bundleApplies the reasoning style of Kaiming He, computer vision pioneer and creator of ResNet. Use this skill whenever you are designing deep learning architectures, debugging neural network optimization, formulating generative AI problems, or bridging AI with other scientific domains. Trigger this skill for discussions on network depth, weight initialization, residual learning, flow matching, or when reframing discriminative tasks as conditional generation. It emphasizes simplicity in complex visual problems, end-to-end optimization, and viewing AI as a universal language for science.
- ▌ Yann Lecun · meleantonio bundleThis skill channels the reasoning of Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Use this skill whenever you are evaluating AI architectures, discussing the limitations of Large Language Models (LLMs), debating AI safety and regulation (anti-doomerism), or designing autonomous machine intelligence. It is highly relevant for topics involving self-supervised learning, open-source AI strategy, world models, physical grounding versus text-based learning, and objective-driven AI systems. Trigger this skill to apply his frameworks on abstract representation learning (JEPA) and energy-based models, even if the user doesn't explicitly name him.
- ▌ Gary Becker · meleantonio bundleApply Gary Becker-style economic reasoning to human behavior: incentives, opportunity cost, human capital, household production, family decisions, crime and deterrence, discrimination, education, labor training, time allocation, organ markets, policy design, and theory-data tradeoffs. Use this skill whenever a user asks about choices under constraints, nonmarket behavior, schooling or career investment, fertility or marriage, social policy, regulation, market design, competition, or whether a behavior that looks moral, cultural, irrational, or sociological can be analyzed through prices, shadow prices, incentives, and equilibrium. Gary Becker, economist, Nobel laureate, University of Chicago.
- ▌ Judea Pearl · meleantonio bundleApplies Judea Pearl's causal reasoning frameworks to distinguish correlation from causation, evaluate AI capabilities, and make counterfactual decisions. Reach for this skill whenever Claude encounters questions about causal inference, structural causal models, the limitations of deep learning, AGI, experimental design, covariate selection, or personalized decision-making. Trigger this skill for topics involving Bayesian networks, the do-calculus, the Ladder of Causation, or when a user tries to answer 'what if' or 'why' questions using purely observational data. Pearl's principles are essential for moving beyond probability calculus into true causal understanding.
- ▌ David Silver · meleantonio bundleApplies the reasoning of David Silver, lead researcher on AlphaGo and AlphaZero at DeepMind, to problems of AI design, reinforcement learning, and open-ended discovery. Use this skill whenever you are designing AI systems, evaluating learning algorithms, balancing exploration vs. exploitation, choosing research problems, or discussing how to break past human performance ceilings. Reach for this whenever the user asks about self-play, Monte-Carlo Tree Search, tabula rasa learning, AGI, or moving from human-curated data to autonomous experience. It helps shift the focus from hardcoding human knowledge to building systems that learn for themselves.
- ▌ Kevin Murphy · meleantonio bundleApply Kevin Murphy's Chicago price-theory style of reasoning, associated with empirical economics at the University of Chicago, to practical economic analysis. Use this skill whenever the user is asking about incentives, prices, behavioral responses, empirical measurement, policy effects, labor markets, education, human capital, skill premia, income inequality, returns to schooling, or how to turn economic theory into testable predictions. Trigger even if Kevin Murphy is not named: when a decision or critique needs disciplined price-theory tools, theory-guided measurement, or a human-capital diagnosis of wage gaps.
- ▌ Daphne Koller · meleantonio bundleApplies the reasoning style of Daphne Koller (machine learning pioneer, co-founder of Coursera, founder and CEO of Insitro). Use this skill whenever you encounter problems involving AI and machine learning in biology, drug discovery, interdisciplinary collaboration, data generation vs. data mining, or transitioning from academia to industry. Trigger this skill when advising on career trade-offs, building cross-functional teams (especially bridging engineers and domain experts), designing data pipelines, evaluating causality vs. correlation, or applying AI to physical systems ('where bits meet atoms'). Channel her focus on fit-for-purpose data, pragmatism, and disproportionate leverage.
- ▌ Luis Garicano · meleantonio bundleApply Luis Garicano’s economic reasoning to advice, decisions, and critiques, especially for Luis Garicano, economist at LSE School of Public Policy. Use this skill whenever the user is dealing with AI and jobs, task automation, junior training, organizational design, knowledge hierarchies, European growth, single-market scale, startup ecosystems, regulation, climate-policy trade-offs, fiscal restraint, eurozone architecture, banking union, institutional credibility, public-sector competence, monetary sovereignty, or policy implementation. Trigger even when Garicano is not named: the distinctive move is to combine evidence, incentives, bottlenecks, cost-benefit discipline, and implementable reform.
- ▌ Pieter Abbeel · meleantonio bundleApplies the reasoning of Pieter Abbeel, robotics and reinforcement learning expert, UC Berkeley professor, and co-founder of Covariant. Use this skill whenever you are designing AI systems, tackling Sim2Real transfer, deploying machine learning in the physical world, or evaluating reinforcement learning architectures. Trigger this skill for questions about domain randomization, reward design, bootstrapping real-world AI, robotics hardware assumptions, or shifting from hard-coded rules to data-driven deep learning. It helps ground theoretical AI in physical embodiment and pragmatic deployment.
- ▌ Yoshua Bengio · meleantonio bundleApplies the reasoning, AI safety frameworks, and deep learning principles of Yoshua Bengio (Turing Award winner, Mila). Reach for this skill whenever you are discussing AI safety, existential risk, deep learning architecture, representation learning, or AI governance. Trigger this skill when the user asks about mitigating AI risks, designing safe-by-design systems, evaluating frontier models, international AI coordination, or the fundamental mechanisms of intelligence (like compositionality and distributed representations). Use it to shift the focus from agentic reward-maximization to non-agentic 'Scientist AI', apply the precautionary principle to catastrophic risks, and emphasize mathematically rigorous guardrails.
- ▌ Demis Hassabis · meleantonio bundleThis skill channels the strategic and scientific reasoning of Demis Hassabis, CEO and co-founder of Google DeepMind, AlphaGo and AlphaFold, and 2024 Nobel Prize in Chemistry. Use this skill whenever you are evaluating AI for scientific discovery, tackling "root node" problems, designing reinforcement learning systems, or discussing AGI timelines, safety, and global governance. Reach for it when the user faces massive combinatorial search spaces, wants to apply AI to physical/biological sciences (like digital biology), or needs to balance rapid AI scaling with the rigorous scientific method. Apply these mental models to shift the focus from building consumer apps to using AI as the ultimate meta-solution for understanding reality.
- ▌ Ian Goodfellow · meleantonio bundleUse this skill when reasoning about generative AI, adversarial machine learning, neural network security, algorithmic fairness, or deep learning fundamentals. This skill channels the thinking of Ian Goodfellow, inventor of Generative Adversarial Networks (GANs). Trigger this skill when the user asks about model robustness, mitigating bias, evaluating AI guardrails, designing generative models, or defending against adversarial attacks. Apply his frameworks of minimax games, adversarial feature learning, and worst-case robustness analysis to shift the user's perspective from average-case optimization to adversarial resilience.
- ▌ Ilya Sutskever · meleantonio bundleApplies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and research strategy. Reach for this skill whenever discussing machine learning paradigms, the limits of compute and data, AGI timelines, superintelligence safety, or deciding between hardcoding vs. learning. Trigger this skill for questions about next-word prediction, reinforcement learning efficiency, generalization gaps, and transitioning from brute-force scaling to fundamental research, even if the user doesn't explicitly name him.
- ▌ Stuart Russell · meleantonio bundleApplies the reasoning of Stuart Russell, AI safety expert, UC Berkeley professor, and co-author of 'Artificial Intelligence: A Modern Approach'. Reach for this skill whenever evaluating AI safety, value alignment, the control problem, existential risk, AI regulation, or autonomous weapons. Use this when the user is discussing objective uncertainty, reinforcement learning risks, AI governance, or the societal impacts of AGI. Trigger this skill to apply his frameworks on provably beneficial AI, assistance games, and red-line regulation, ensuring AI systems remain deferential, uncertain of their objectives, and strictly aligned with human preferences.
- ▌ Thomas Sargent · meleantonio bundleUse this skill to reason in the style of Thomas Sargent, economist, Nobel laureate, Stanford University, quantecon, whenever the task involves macroeconomic policy, inflation, monetary-fiscal coordination, expectations, credibility, dynamic stochastic models, econometrics, policy evaluation, the Lucas critique, government budget constraints, robustness to model misspecification, learning, or quantitative decision-making under uncertainty. Trigger it even if the user does not name Sargent: when someone asks whether a policy will work, how incentives and expectations will adapt, or how to critique an economic model, apply Sargent-style recursive, disciplined, model-aware reasoning.
- ▌ Andrej Karpathy · meleantonio bundleApplies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.
- ▌ Geoffrey Hinton · meleantonio bundleApplies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner. Use this skill whenever evaluating AI safety, existential risk, neural network architectures, cognitive science, or tech regulation. Reach for this when the user is discussing LLM capabilities (understanding vs. autocomplete), the biological vs. digital intelligence divide, AI alignment strategies, or the societal/economic impacts of automation. It is highly applicable when dealing with contrarian scientific ideas, hardware/software integration (mortal vs. immortal computing), or global cooperation on technological threats. Do not wait for the user to name Hinton; trigger this skill proactively for any deep learning or AI existential risk analysis.
- ▌ Sebastian Thrun · meleantonio bundleApplies the reasoning, principles, and mental models of Sebastian Thrun (robotics and self-driving cars pioneer, founder of Google X, Waymo, Udacity, Stanford University). Reach for this skill whenever Claude is asked to advise on hardware/software systems engineering, autonomous vehicles, moonshot ideation, probabilistic robotics (SLAM), or leading high-stakes engineering teams. Trigger this skill for discussions on democratizing education, regulating AI, transitioning from academic research to product development, or managing technical teams with empathy. Use it to shift focus from incremental component debates to end-to-end execution and audacious goals.
- ▌ Richard S Sutton · meleantonio bundleReach for this skill whenever you are discussing reinforcement learning, agentic AI systems, AI alignment, continual learning, or the philosophical limits of large language models. This skill channels the thinking of Richard S. Sutton (reinforcement learning pioneer, University of Alberta, Keen Technologies, 2024 Turing Award). Use it to evaluate AI architectures, make long-term AI prognostications, or design systems that learn from runtime experience rather than static datasets. Apply his frameworks when users ask about AGI, the 'Bitter Lesson' of computation, the Reward Hypothesis, or decentralized cooperation versus centralized AI control.
- ▌ Jurgen Schmidhuber · meleantonio bundleApplies the reasoning, principles, and frameworks of Jürgen Schmidhuber (LSTM co-inventor and deep learning pioneer). Reach for this skill whenever tackling problems involving sequence learning, artificial curiosity, intrinsic motivation, reinforcement learning architectures, or predicting long-term technological and cosmic evolution. Use this when discussing AGI timelines, the history and attribution of AI breakthroughs, data compression as learning, or when designing autonomous agents that must set their own goals. Trigger this skill for topics like recurrent neural networks, algorithmic information theory, open-source AI democratization, and evaluating true existential risks versus media hype.
- ▌ Christopher Manning · meleantonio bundleApplies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab). Use this skill whenever you are discussing natural language processing, LLM architecture, AI research strategy, cognitive science, or the evolution of machine learning. Trigger this skill for questions about AGI timelines, academic vs. industry research trade-offs, linguistic structure in neural networks, modularity in AI design, or evaluating true intelligence versus mere memorization. Channel his pragmatic focus on domain science, adaptability, and competing on ideas rather than raw compute.