meleantonio

Use for read-only checks of economics datasets, data maps, variable coding, panel balance, sample restrictions, and synthetic-data caveats before estimation or replication.

Use 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.

Use 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.

Use for pre-submission economics paper review, referee-style reports, identification checks, and response-to-referee planning on author-owned, public, or approved material.

Use when asked to verify reproducibility, audit a replication package, check a clean run, validate run instructions, or review before sharing research code.

Use 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…

Use 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.

Use when asked to verify reproducibility, audit a replication package, check a clean run, validate run instructions, or review before sharing research code.

Finds 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…

Coordinates 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…

Exports 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.

Guides 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.

Structures 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.

Guides 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.

Supports 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.

Implements 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…

Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.

Commit changes, push to remote, and create a pull request. Use for completing features or fixes ready for review.

Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.

Python code style and formatting standards using Ruff. Use when writing or reviewing Python code.

Git workflow and commit conventions. Use when committing code, creating branches, or making pull requests.

LLM and ML development best practices with LangChain and transformers. Use when building AI/ML applications.

Testing conventions using pytest. Use when writing tests, creating fixtures, or running test suites.

Independently 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,…

Build 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…

Formalize 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…

Attack 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…

Filter 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.

Apply 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,…

Apply 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,…

Apply 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,…

Use 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,…

Use 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.

Use when you want the agent to iterate — implement, verify, flag blockers as new issues, implement again — until the replication-checker and all acceptance criteria return green. Stop when green or when the maximum iteration count is reached.

Use when asked to assess whether the repo can reproduce its documented outputs from a clean setup.

Implements 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…

Independently 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…

Build a CDC-style problem-specific prompt for attacking an open math problem: exact restatement, complete success criteria, non-counting partial results, traps, multi-agent search heuristics, and adversarial audit requirements. Use when creating PROMPT.md,…

Attack 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…

Filter 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…

Lists 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.

Reads 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.

Creates, 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.

Summarizes 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.

How 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.

How 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.

Run 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…

Find, 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…

Conduct 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…