cpuguy96

cpuguy96/StepCOVNet

Cursor rule Cursor

Session entry — route through AGENTS.md to one index only.

cpuguy96/StepCOVNet

Cursor rule Cursor

Schema versions and per-field rationale in design/plan docs.

cpuguy96/StepCOVNet

Cursor rule Cursor

Which Python executable to use — Windows venv (CPU) vs WSL (GPU).

cpuguy96/StepCOVNet

Cursor rule Cursor

Python code style — imports, third-party submodules, and docstrings.

cpuguy96/StepCOVNet

Cursor rule Cursor

Tests and coverage when changing src/, scripts/, or tests/.

cpuguy96/StepCOVNet

Cursor rule Cursor

Log EXP/NOTE and paper citations in docs/research/.

cpuguy96/StepCOVNet

Cursor rule Cursor

Visible console, TensorBoard with train jobs, logs/tmp captures, no repo-root tmp.

cpuguy96/StepCOVNet

Cursor rule Cursor

Refresh repo state before routing edits; portable paths, scratch hygiene, Windows git hygiene.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Audit and sync agent brain — read all rules from disk, reconcile skills/catalogs/routing. Triggers on refresh agent brain, refresh all rules, audit rules, or after steering promotion. Read-only audit script; agent writes doc updates.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Triggers on process mistakes and steering corrections; run steering-correction-promotion for artifact choice, context optimization, and JRN receipt. Journal alone is incomplete.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Deprecated alias — use autoresearch skill with profile ar-tide-overfit.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

One-prompt agent autoresearch loop for StepCOVNet: goal + time budget → orient, hypothesize, run, log, repeat until success or deadline. Use when the user says "run autoresearch", gives a research goal with a budget, or names a profile (e.g. ar-tide-overfit). Not for unattended Python planners (--hours / lattice).

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Diagnoses onset event F1, train/eval matching mismatches, confidence collapse, and threshold effects. Use when F1 is zero or low, conv1d collapse is suspected, or the user asks about Hungarian vs ordered assignment, matching tolerance, or debugonsetoverfit output.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Starts a research session and logs EXP and NOTE entries with timestamps. Use when beginning research work, logging experiments, or writing discussion notes. Promote findings to PAPEROUTLINE only when drafting the paper.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

On user steering corrections or remember-this, pick the smallest durable artifact (skill section, scoped rule, or rare always-apply rule), slim AGENTS.md, optimize agent-brain context, then prepend JRN. Use instead of creating new alwaysApply rules by default.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Runs tide overfit ablations — confidence threshold sweep, loss-weight variants, and architecture changes on MERT. Use when investigating F1 plateau, loss weight tuning, threshold post-hoc, or archmedium vs archlarge on tide.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Runs tide single-song overfit smoke tests across conv1d, mel, and MERT frontends via WSL GPU. Use when the user mentions tide overfit, overfit suite, frontend ablation, smoke test on tide, or comparing preprocessing frontends.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Answers what to do now, what's next, where are we, project status, or orientation. When the user then says do it, go ahead, or start, execute the If you say do it steps from the last whats-next answer. Runs projectstatus.py and reads EXPERIMENTLOG § Current phase.

cpuguy96/StepCOVNet

Skill Claude CodeCodexCursor

Runs StepCOVNet GPU training and MERT extraction on Windows via WSL with TensorFlow CUDA libraries. Use for trainonset, overfit scripts, extractmertfeatures with cuda, or when TensorFlow sees zero GPUs in WSL.

cpuguy96/StepCOVNet

Instructions file CodexOpenCode

Instructions for cpuguy96/StepCOVNet, covering stepcovnet — agent entry, before commit / push and path conventions (portable).

cpuguy96/StepCOVNet

Agent

Human-maintained inventory of .cursor/rules and skills. Updated by the agent during agent-brain-refresh — not generated by a script.

cpuguy96/StepCOVNet

Agent

Status (2026-06-30): Tide gate PASS — scratch iter175 / champion v8. Do not start new tide iter runs unless reproducing. Next AR work: gate-10song-smoke (EXPERIMENTLOG.md § Current phase).

cpuguy96/StepCOVNet

Agent

When to read: Locating code, configs, scripts, or model artifacts. Routed from AGENTS.md.

cpuguy96/StepCOVNet

Agent

Iterative improvements to agent behavior, process, and conventions on this project. Not a substitute for EXPERIMENTLOG.md or DISCUSSIONNOTES.md — those hold research findings; this holds how we work better.