Design discipline for coding agents: name the mathematical object before writing code, make the math the spec, borrow models from the sciences, measure where you are and the null, build the smallest thing that meets the bound, and prove it holds. Includes a stdlib-only exact-statistics CLI.
0 on GitHubby Quan Duongv0.1.0MITupdated 15 days ago
/
Plugin math-first from marketplace nagisanzenin in nagisanzenin/claude-code-plugins. Commands read from the repo's manifest — 12 days ago.
What it installs
Skills (1)
math-first
Math-first design discipline. Before writing code, name the mathematical object the problem really is, make the math the spec, borrow models from the sciences, measure where you are (and the null case), build the smallest thing that meets the bound, and prove it holds. Use when a task involves desig
14 AI agents for all software engineering work. Adaptive routing with 10 execution modes — from full greenfield builds to adding features, code review, testing, hardening, deployment. 4 engagement modes, scale-driven architecture, quality-first parallelism.
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
Portable operating method: session lifecycle agents, pre-ship code review, deploy with live verification and state doc update, and production log health check
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Includes LaTeX templates, citation verification, reviewer guidelines, publication-quality figure generation, systems paper structural blueprints, and conference presentation slides.
98 skills
Orchestra-Research/AI-Research-SKILLs 14,502
Maintain math-first?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.