Skill Claude CodeCodex
One-time bootstrap — seed /.mindfunnel/ with AGENTS.md, SOUL.md, USER.md, and PROJECT.md.example from the plugin's bundled templates. Use the first time you run the mindfunnel plugin on a new machine, or when /.mindfunnel/ is missing. Idempotent — detects existing files and never overwrites. Also creates a CLAUDE.md…
Skill Claude CodeCodex
Read project memory and produce a tight "where we are + next action" brief, then wait for direction. Invoke ONLY when the user explicitly asks to resume, catch up, or get oriented on prior work — e.g. "spin up", "catch up", "resume", "where were we", "get up to speed", "what were we working on". Do NOT auto-fire on…
Plugin Claude Code
tuneml — a read-first advisor for training and evaluating neural networks well: the scientific method for tuning, and the speed↔quality frontier, in one place. Prices every candidate change in time-to-target-quality rather than throughput, grades the evidence behind it, and names what it would silently break. Five…
Skill Claude CodeCodex
Extract insight from a finished study and return a variance-aware adopt verdict — search-space boundaries, sampling density, infeasible fraction, training-curve pathologies, isolation plots, then adopt or not. Use for /tml:analyze, "here are my sweep results", "which config should I pick", "did this change actually…
Skill Claude CodeCodex
Read a training/evaluation pipeline and emit ranked, evidence-graded, priced findings across the algorithmic (A), systems (B), protocol (C) and architecture (D) tiers. Use for /tml:audit, "why is my training slow", "how do I speed this up without losing accuracy", "review my training loop", "what am I leaving on the…
Skill Claude CodeCodex
Choose an operating point on the speed↔quality frontier, fix the training-step budget, and turn findings into an ordered, gated change plan — with a quality floor, named non-negotiables, revert triggers, a measurement contract, and a stop rule. Use for /tml:plan, "which of these should I actually do", "I have N…
Skill Claude CodeCodex
Adversarially review a proposed or applied change to a training/evaluation pipeline: did the claimed mechanism actually engage, is the measurement still valid, what did it silently break. Use for /tml:review, "I made training faster, check it", "review this diff before I merge", "why did throughput improve but…
Skill Claude CodeCodex
Design the next round of experiments — scope one goal, classify every hyperparameter as scientific, nuisance or fixed, build the studies, choose search spaces and a sampler, and allocate the trial budget. Use for /tml:round, "what experiment should I run next", "how do I test whether X helps", "design a sweep for…
Plugin Claude Code
ws — whetstone: sharpen the thinking before the work. One user-only skill: /ws:grill runs a relentless, round-based interview over the design tree of a plan, decision or idea, asking the whole settled frontier at a time with a recommendation attached to every question, and closing only when nothing is left silently…
Skill Claude CodeCodex
A relentless, round-based interview that stress-tests a plan, design or decision against its own design tree until nothing is left silently assumed.