Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.
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.
npx skills add Galaxy-Dawn/claude-scholar --skill kaggle-learnergit clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholarWrote 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.
[](https://agentmods.dev/skills/galaxy-dawn/claude-scholar/kaggle-learner)<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/kaggle-learner"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/kaggle-learner/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.
<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/kaggle-learner"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/kaggle-learner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.01118 |
| Opus 5 | $0.00034 | $0.00559 |
| Sonnet 5 | $0.00014 | $0.00224 |
| Haiku 4.5 | $0.00007 | $0.00112 |
Grade A, and why
kaggle-learner 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaggle Learner
Extract and apply knowledge from Kaggle competition winning solutions. This skill provides access to a continuously updated knowledge base of techniques, code patterns, and best practices from top Kaggle competitors.
Overview
Kaggle competitions are at the forefront of practical machine learning. Winning solutions often innovate with novel techniques, clever feature engineering, and optimized pipelines. This skill captures that knowledge and makes it accessible for your projects.
When to Use
Use this skill when:
- Studying for a Kaggle competition
- Looking for proven techniques in a specific domain (NLP, CV, etc.)
- Need code templates for common ML tasks
- Want to learn from competition winners
Knowledge Categories
| Category | Focus | Directory |
|---|---|---|
| NLP | Text classification, NER, translation, LLM applications | references/knowledge/nlp/ |
| CV | Image classification, detection, segmentation, generation | references/knowledge/cv/ |
| Time Series | Forecasting, anomaly detection, sequence modeling | references/knowledge/time-series/ |
| Tabular | Feature engineering, traditional ML, structured data | references/knowledge/tabular/ |
| Multimodal | Cross-modal tasks, vision-language models | references/knowledge/multimodal/ |
文件组织结构：每个竞赛一个独立的 markdown 文件，按 domain 分类到对应目录。
示例：
time-series/birdclef-plus-2025.mdnlp/aimo-2-2025.md
Quick Reference
To learn from a competition:
- Provide the Kaggle competition URL
- The kaggle-miner agent will extract the winning solution
- Knowledge is automatically added to the relevant category
- 前排方案详细技术分析 (Front-runner Detailed Technical Analysis) is automatically included
To browse existing knowledge:
- 浏览相关 domain 目录：
references/knowledge/[domain]/ - 每个竞赛一个独立文件，包含：
- Competition Brief (竞赛简介)
- 前排方案详细技术分析 (前排方案详细技术分析) ⭐
- Code Templates (代码模板)
- Best Practices (最佳实践)
Self-Evolving
This skill automatically updates its knowledge base when the kaggle-miner agent processes new competitions. The more you use it, the smarter it becomes.
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/knowledge/.archive/cv.md 248 B
- references/knowledge/.archive/multimodal.md 256 B
- references/knowledge/.archive/nlp.md 111 KB
- references/knowledge/.archive/tabular.md 24 KB
- references/knowledge/.archive/time-series.md 334 KB
- references/knowledge/nlp/aimo-2-2025.md 38 KB
- references/knowledge/nlp/arc-prize-2025.md 51 KB
- references/knowledge/nlp/eedi-2024.md 7.6 KB
- references/knowledge/nlp/konwinski-prize-2025-6th-place-study.md 9.9 KB
- references/knowledge/nlp/konwinski-prize-2025-comparison.md 35 KB
- references/knowledge/nlp/konwinski-prize-2025.md 20 KB
- references/knowledge/nlp/map-2024.md 14 KB
- references/knowledge/tabular/amp-parkinsons-2021.md 17 KB
- references/knowledge/time-series/birdclef-2023.md 51 KB
- references/knowledge/time-series/birdclef-2024.md 156 KB
- references/knowledge/time-series/birdclef-plus-2025.md 67 KB
- references/knowledge/time-series/detect-behavior-sensor-2025.md 59 KB
- references/knowledge/time-series/detect-sleep-states-2023.md 56 KB
- references/knowledge/time-series/hms-2024.md 58 KB
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.
- 10d ago First seen · 109 lines · 69 tokens per session scan A 555c52d08991
kaggle-learner is a skill published in the GitHub repository Galaxy-Dawn/claude-scholar (5,407 stars, last pushed 13d ago), licensed MIT. It adds 69 tokens to every session and 1,118 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.
Other skills, from other repositories
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.
knowledge-layer
High-level deployment wrapper over RepoBrain core with graph-first knowledge injection and all-file support. Exposes refreshfilesystem and askfilesystem for building and querying the knowledge graph.
education-data-context
Interpretation guidance for Urban Institute Portal datasets. Coded values (-1/-2/-3), year definitions, grade encoding, suppression, licensing, cross-source joins. Use when interpreting Portal data before analysis. Routes to source-specific skills.
education-data-query
Downloads education datasets from configured mirror sources (parquet/CSV) with local Polars filtering. Use when writing fetch scripts or retrieving CCD, IPEDS, CRDC, SAIPE data. Load after education-data-explorer — retrieval here, not discovery.
prompt-pilot
Rewrite a rough, vague prompt into a precise, context-enriched prompt. Explores the codebase read-only and weaves real file paths and symbols into the rewritten prompt — never implements the task itself. Use when the user asks to optimize, enrich, or improve a prompt before running it.
rlhf
Understanding Reinforcement Learning from Human Feedback (RLHF) for aligning language models. Use when learning about preference data, reward modeling, policy optimization, or direct alignment algorithms like DPO.