literature-review

literature-review is a skill for Claude Code from mxslr/mlcraft. It costs 89 tokens per session (470 once invoked), scanned A, original, MIT.

A research workflow for choosing machine-learning methods by studying papers, benchmarks, data splits, and reported results. It also checks whether high scores may be caused by data leakage, where test information accidentally reaches training.

In plain words
What is it for?
Use it when starting an ML project, comparing methods, estimating realistic performance, and preparing an evidence-based summary of the field.
Why use it?
It helps prevent choosing a method based on inflated or incomparable accuracy claims.

Skill for Claude Code

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

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

Good fit Use it when starting an ML project, comparing methods, estimating realistic performance, and preparing an evidence-based summary of the field.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mxslr/mlcraft/literature-review
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 mxslr/mlcraft --skill literature-review
Clone the repo
git clone --depth 1 https://github.com/mxslr/mlcraft

Made for: Claude Code.

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

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 literature-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mxslr/mlcraft/literature-review/github.svg)](https://agentmods.dev/skills/mxslr/mlcraft/literature-review)
Your own site
<a href="https://agentmods.dev/skills/mxslr/mlcraft/literature-review"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/literature-review/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 literature-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mxslr/mlcraft/literature-review"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/literature-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 470 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 $0.00089 $0.00470
Opus 5 $0.00044 $0.00235
Sonnet 5 $0.00018 $0.00094
Haiku 4.5 $0.00009 $0.00047

Measured 10d ago against content hash aacd337a568c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

literature-review 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/literature-review/SKILL.md · 30 lines

What it actually says

Literature Review (research-first, skeptical)

Never pick a method from memory or hype. Ground it in evidence.

Do this

  1. Delegate breadth to the paper-researcher agent when available; otherwise run diverse WebSearch yourself (by task, by dataset + "state of the art", by method family, by "patient-level" / "leakage").
  2. Read the top 2-5 sources. For each, record: method, dataset + split, headline metric, how the split was done.

Appraise every number adversarially

A high number is a hypothesis to disprove, not a target:

  • Whole-input vs ROI/patch? ROI-crop (lesion already cropped) is a different, easier problem than whole-image. Numbers are not comparable.
  • Split integrity? A random per-sample split with multiple samples per subject causes leakage and inflated scores. Demand group/patient/temporal or the official split.
  • Test size & metric? A tiny test set or thresholded accuracy is unstable. Prefer AUC / mAP / F1 with confidence intervals.
  • Comparable? Only the official benchmark split can be compared across papers.

Output an evidence brief

  • SOTA table with columns: method, dataset/split, metric, credibility note.
  • Realistic ceiling: best rigorous, leakage-free, comparable number - the honest target.
  • Ranked techniques worth combining, each with evidence + caveat.
  • Traps to avoid.
  • Sources as markdown links.

Red flags = distrust, don't chase

99%+ on a hard whole-image medical/vision benchmark almost always means ROI-only or leakage. Say so plainly. The professional move is knowing which numbers are fake.

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 · 30 lines · 89 tokens per session scan A aacd337a568c

Subscribe to this mod's changes

literature-review is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 470 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

reinforcement-learning

Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…

Aznatkoiny/zAI-Skills · 86 tokens

cpp-reinforcement-learning

C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…

Aznatkoiny/zAI-Skills · 83 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

decompose-to-pipeline

Decompose a complex vision-and-reasoning requirement into the cheapest measurable pipeline. TRIGGER when: user asks to monitor/alert, analyze footage over time, combine perception with aggregation/reporting, determine whether something is feasible to detect (including sensor limits or smoldering), or replace repeated…

Borda/vision-delivery · 124 tokens

shumo-paper

A step-by-step helper for solving China’s national undergraduate mathematical modeling contest problems and writing the accompanying paper. It covers analyzing the question, choosing and testing models, processing data, solving problems, and improving the paper.

thinker137/shumo-paper-skill · 147 tokens

init-physics-intern

Scaffold a PhysicsIntern research workspace in the current folder.

huggingface/physics-intern-claude-plugin · 18 tokens