StepCOVNet: Skill for Claude Code

.cursor/skills/onset-event-eval-matching/SKILL.md

onset-event-eval-matching is a skill for Claude Code, Cursor from cpuguy96/StepCOVNet. It costs 66 tokens per session (593 once invoked), scanned A, original, Apache-2.0.

A diagnostic guide for onset-event evaluation in StepCOVNet, a machine-learning system that detects events at specific times. It focuses on F1, a score that balances missed detections and false alarms, and on how predicted events are matched to real ones.

In plain words
What is it for?
Use it to investigate zero or low F1, confidence values collapsing, matching tolerances, threshold choices, or Hungarian matching versus ordered pairing.
Why use it?
It helps explain cases where the model appears to predict reasonable times but receives a very low or zero score. The main issue it checks is whether training and evaluation match events in the same way.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is cpuguy96/StepCOVNet's own configuration. It tells Claude Code and Cursor how to work on StepCOVNet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything StepCOVNet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cpuguy96/StepCOVNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cpuguy96/StepCOVNet/master/.cursor/skills/onset-event-eval-matching/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cpuguy96/StepCOVNet

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for onset-event-eval-matching

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/onset-event-eval-matching/github.svg)](https://agentmods.dev/skills/cpuguy96/stepcovnet/onset-event-eval-matching)
Your own site
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/onset-event-eval-matching"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/onset-event-eval-matching/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for onset-event-eval-matching

Your own site · 80×15
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/onset-event-eval-matching"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/onset-event-eval-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 593 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.00593
Opus 5 $0.00033 $0.00296
Sonnet 5 $0.00013 $0.00119
Haiku 4.5 $0.00007 $0.00059

Measured 11d ago against content hash 5887d1866e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

onset-event-eval-matching scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/onset-event-eval-matching/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onset event eval and matching

Core rule

Training and eval must use the same assignment philosophy. Eval always uses Hungarian matching with tolerance; training uses assign_onset_pairs_l1 (Hungarian L1) in src/stepcovnet/onset_events/losses.py.

Ordered slot→GT pairing on tide (634 GT, 1024 uniform slots) can yield zero in-tolerance pairs → loss drives all confidences toward 0 → 0% F1 despite reasonable predicted times (see NOTE-20260606-13, EXP-07/08).

Diagnostics-first (F1=0 or suspicious)

Before changing epochs, architecture, or loss weights, run diagnostics via the WSL command template with:

scripts/debug_onset_overfit.py --checkpoint=models_wsl/overfit_tide/<frontend>/onset_event_model.keras

Check in output / diagnostics.py:

  • Max confidence and count above 0.5
  • Hungarian pairs within tolerance vs thresholded detections
  • TP / FP / FN breakdown (expect ~233/634 TP at ~30% F1 plateau)

Interpretation guide

Symptom Likely cause Next step
Max conf ~0.0002, 0% F1 Train/eval assignment mismatch or no learnable pairs Verify Hungarian train loss; read NOTE-13
Many pairs in tolerance, low F1 Threshold / post-hoc filtering tide-ablations threshold phase
~28–30% F1, high FP Query-slot formulation cap, not metric bug Formulation change; see EXP-10

Key code paths

Module Role
losses.py assign_onset_pairs_l1 — training assignment
metrics.py match_onsets_numpy — eval Hungarian matching
diagnostics.py Confidence sweeps, pair stats
scripts/debug_onset_overfit.py Checkpoint inspection CLI

Read the full file on GitHub · 47 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 47 lines · 66 tokens per session scan A 5887d1866e69

Subscribe to this mod's changes

onset-event-eval-matching is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 17d ago), licensed Apache-2.0. It adds 66 tokens to every session and 593 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

developing-with-streamlit

Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…

streamlit/streamlit · 128 tokens

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

perforatedai-complex-methods

Solutions for non-trivial PerforatedAI integration scenarios. Use when standard integration hits edge cases such as AMP (Automatic Mixed Precision) / GradScaler crashes in p mode, or other advanced setups not covered by the main perforatedai skill.

PerforatedAI/PerforatedAI · 58 tokens

depth-estimation

Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch).

SharpAI/DeepCamera · 22 tokens

HomeSafe-Bench

VLM indoor safety hazard detection benchmark inspired by HomeSafeBench (arXiv 2509.23690).

SharpAI/DeepCamera · 28 tokens

safe-debug

Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research…

lllllllama/RigorPilot-Skills · 88 tokens