accuracy-improvement-loop

A workflow for investigating why a machine-learning model performs poorly and choosing targeted ways to improve it. It examines errors, training behaviour, data leakage, model attention, and separate parts of combined models.

In plain words
What is it for?
Use it to investigate overfitting, underfitting, suspicious results, misleading image features, data-split problems, and weak components in model combinations.
Why use it?
It replaces random attempts to improve accuracy with diagnosis based on evidence from the data, training process, and wrong predictions.

Skill for Claude CodeCodex

Part of the mlcraft plugin — 23 skills, 1 command, 1 agent shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mxslr/mlcraft/accuracy-improvement-loop
Any agent
npx skills add mxslr/mlcraft --skill accuracy-improvement-loop
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft

Made for: Claude Code, Codex.

Or install mlcraft, the plugin that ships this one along with the rest of its 23 skills, 1 command, 1 agent.

Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 867 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00112 $0.00867
Opus 5 $0.00056 $0.00434
Sonnet 5 $0.00022 $0.00173
Haiku 4.5 $0.00011 $0.00087

Measured 3d ago against content hash 667a37b086fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accuracy-improvement-loop 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 3d 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.

skills/accuracy-improvement-loop/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accuracy-Improvement Loop

Do NOT throw random tricks at the model. Diagnose, research the gap, combine principled fixes, verify. This is the loop a professional runs to push toward (and recognize) the ceiling.

Step 1 - Diagnose the bottleneck (evidence, not guesses)

  • Re-audit leakage FIRST (data-rigor-and-leakage). A suspicious jump/drop is often a split problem. Fixing leakage may lower the number - that is success, because it was fake.
  • Learning curves: train loss down but val loss up means overfitting; both flat or low means underfitting or a data problem; unstable means an LR, batch, or BatchNorm issue.
  • Error analysis: inspect the confusion matrix and the actual misclassified samples. What do the errors have in common?
  • Saliency check (Grad-CAM): is the model attending to the signal or to an artifact (background, labels, muscle/border, watermark, spurious correlation)? Fix the data/preprocessing if so.
  • Per-branch/per-model check: in fusion/ensembles, is one component dragging the rest down?

Step 2 - Research the specific gap

Invoke literature-review / paper-researcher targeted at the diagnosed problem (e.g., "small-lesion whole-image classification", "fusion gradient dilution", "class imbalance long-tail"), not the generic task. Extract techniques that address this failure mode.

Step 3 - Synthesize a principled combination

Combine the best-evidenced techniques that target the bottleneck - this is how you "beat existing work": a grounded combination, not one silver bullet. Common high-impact levers (pick by diagnosis):

  • Data/signal: higher input resolution, better ROI/region focus, artifact removal, cleaner labels, stronger domain-appropriate augmentation, more/balanced data (incl. synthesis only if justified).
  • Architecture: stronger/more-suitable backbone for this dataset (not just the trendiest); attention (CBAM/self-attention); multi-scale features; multi-view/multi-input; feature-fusion done right - gated fusion + deep supervision / auxiliary per-branch losses to beat gradient dilution when a weak branch drags a fusion.
  • Training: discriminative LR, better schedule, regularization retuned to the diagnosis, longer training, EMA/SWA, self-distillation, patch-pretraining then whole-image.
  • Inference/aggregation: TTA, calibrated thresholds, ensembles (soft-voting / weighted-by-val / stacking) - output-level fusion is often the cheapest real gain.
  • Weakly-supervised localization (e.g., GMIC-style) when lesions/objects are tiny in a large input - often both more accurate and gives free saliency.

Read the full file on GitHub · 37 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. 3d ago First seen · 37 lines · 112 tokens per session scan A 667a37b086fe

Subscribe to this mod's changes

accuracy-improvement-loop is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 867 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

torch-performance-optimization

Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions. Use when adding or changing Torch CPU kernels, Tensor/NumPy bridges, Torch backend routing, tensor layouts, allocations, threading, profiling, memory-format candidates, or Torch performance benchmarks.

albumentations-team/albucore · 60 tokens

ml-for-aec

Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.

Abhinavbwj/Claude-skills-for-Computational-Designers · 39 tokens

yolo-export

Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, OpenVINO, LiteRT, NCNN, ExecuTorch, and NPUs (RKNN, QNN, Hailo, Ascend, IMX, Axelera, DeepX), FP16/INT8 quantization, benchmarking, and non-Python runtimes.…

ultralytics/skills · 114 tokens

yolo-training

Use when training, fine-tuning, or validating Ultralytics YOLO models in Platform, cloud GPUs, or local code — model.train(), yolo train/val, remote metric streaming, epochs, batch, imgsz, devices, augmentation, multi-GPU, resumes, results, and fixing OOM, NaN loss, low mAP, or overfitting. For hyperparameter search…

ultralytics/skills · 95 tokens

yolo-datasets

Use when uploading, annotating, building, converting, analyzing, or debugging datasets in Ultralytics Platform or local YOLO — Platform dataset management and Smart Annotation, data.yaml, YOLO label .txt formats, COCO/DOTA/mask conversion, auto-labeling, splits, validation, and errors like "no labels found" or mAP…

ultralytics/skills · 97 tokens

yolo-models

Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable…

ultralytics/skills · 128 tokens