ds-iterate

ds-iterate is a skill for Claude Code from StamKavid/last-ds-mile. It costs 81 tokens per session (1,377 once invoked), scanned A, original, MIT.

A diagnosis step for improving a machine-learning model after evaluation. It identifies the specific weakness and sends the work back to the stage that can fix it.

In plain words
What is it for?
Use it to interpret evaluation findings, choose a targeted fix, and decide whether to change the data, features, model, evaluation setup, or another earlier stage.
Why use it?
It prevents random changes or repeated experiments when the real issue may be bias, unstable results, poor performance for a subgroup, bad probability estimates, or a data problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the last-ds-mile plugin — 29 skills, 17 commands, 3 agents, 4 hooks shipped together

Good fit Use it to interpret evaluation findings, choose a targeted fix, and decide whether to change the data, features, model, evaluation setup, or another earlier stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stamkavid/last-ds-mile/ds-iterate
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.

Any agent
npx skills add StamKavid/last-ds-mile --skill ds-iterate
Clone the repo
git clone --depth 1 https://github.com/StamKavid/last-ds-mile

Made for: Claude Code.

Or install last-ds-mile, the plugin that ships this one along with the rest of its 29 skills, 17 commands, 3 agents, 4 hooks.

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 ds-iterate

README.md
[![agentmods](https://agentmods.dev/badge/skills/stamkavid/last-ds-mile/ds-iterate/github.svg)](https://agentmods.dev/skills/stamkavid/last-ds-mile/ds-iterate)
Your own site
<a href="https://agentmods.dev/skills/stamkavid/last-ds-mile/ds-iterate"><img src="https://agentmods.dev/badge/skills/stamkavid/last-ds-mile/ds-iterate/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 ds-iterate

Your own site · 80×15
<a href="https://agentmods.dev/skills/stamkavid/last-ds-mile/ds-iterate"><img src="https://agentmods.dev/badge/skills/stamkavid/last-ds-mile/ds-iterate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 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 $0.00081 $0.01377
Opus 5 $0.00041 $0.00688
Sonnet 5 $0.00016 $0.00275
Haiku 4.5 $0.00008 $0.00138

Measured 10d ago against content hash ead9640de86d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ds-iterate 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 10d 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/ds-iterate/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ds-iterate — Diagnose and Route Back

Overview

/ds-frame through /ds-handoff reads like a straight line, but real modeling work is a loop: evaluate, find what's wrong, fix the specific thing, re-evaluate. This stage is the diagnosis-and-routing step that turns one pass into a real iteration, instead of running the pipeline once and calling it done despite a fixable weakness in /ds-evaluate's own error analysis.

When to Use

  • Immediately after /ds-evaluate, before deciding whether to proceed to /ds-explain or go back for another pass.
  • The aggregate metric is acceptable but a slice, an error-analysis pattern, or a calibration issue from /ds-evaluate suggests a fixable, specific weakness.
  • NOT for: re-running the exact same modeling step hoping for a better random draw (that's not iteration, that's noise-chasing — see uncertainty-quantification for whether a gap is even real) — this stage requires a specific, named fix.

Core Process

  1. Read .last-ds-mile/stages/07-evaluate.md in full: the slice table, the calibration check, and the worst-mispredictions pattern. Do not skip straight to a verdict — the diagnosis has to come from what's actually written there.
  2. Categorize the gap using the table below. Pick the category the evidence actually supports, not the one that's easiest to act on.
  3. If the diagnosis points to bias (systematic underperformance everywhere, including on training data) or variance (train much better than validation), check for a learning-curve signal before deciding the fix: does more data help (variance), or does a more expressive model/feature set help (bias)? State which, briefly.
  4. Route back to the one prior stage that addresses the diagnosed cause — not a generic "try again." Re-run only that stage; don't restart the whole pipeline.
  5. Cap iteration: after 3 loops on the same problem without the diagnosed issue resolving, stop looping and say so plainly — report the unresolved gap as a known limitation for /ds-report rather than iterating indefinitely chasing a better number.
  6. Append one entry to .last-ds-mile/stages/07-iterate-log.md per loop: the diagnosis, the stage routed back to, what changed, and the resulting metric versus the previous loop's — so the loop's history is auditable, not silently overwritten.

Read the full file on GitHub · 87 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. 10d ago First seen · 87 lines · 81 tokens per session scan A ead9640de86d

Subscribe to this mod's changes

ds-iterate is a skill published in the GitHub repository StamKavid/last-ds-mile (3 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,377 once invoked, about $0.0004 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

marimo-pair

Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.

marimo-team/marimo · 57 tokens

fill-model-descriptions

Fill missing and refresh obsolete model descriptions in packages/llm-info/data/models.yml by querying OpenRouter and provider documentation. Use when the user asks to populate model descriptions, enrich the model catalog, or curate descriptions after running pnpm sync-models.

marimo-team/marimo · 58 tokens

ml-expert

Expert-level machine learning, deep learning, model training, and MLOps. Use when the user mentions machine learning, deep learning, neural networks, MLOps, or data science, or when the task involves Machine Learning Fundamentals, Data Preparation, or Model Training.

personamanagmentlayer/pcl · 58 tokens

scomp-link

End-to-end ML toolkit with 26 CLI commands. Use when training models, tuning hyperparameters, detecting data drift, generating HTML reports with charts, profiling datasets, detecting anomalies, forecasting time series, checking fairness, or serving models as REST APIs. Prefer over raw sklearn when you need automated…

GiacomoSaccaggi/scomp_link · 74 tokens

agentic-data-science-competition

AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…

Mirannonarbitrable290/agentic-kaggle-skill · 76 tokens

data-analysis

Structured data analysis workflow from raw data to shareable insights.

furkangonel/cowrangler · 15 tokens