critical-read
Critically analyzes research papers by identifying assumptions, comparing methodologies, and highlighting weaknesses.
Install
mkdir -p .claude/skills/critical-read && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16727" && unzip -o skill.zip -d .claude/skills/critical-read && rm skill.zipInstalls to .claude/skills/critical-read
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
在paper-extractor已經產出規格表之後，針對一篇核心相關論文做批判性判斷——隱含假設、跟使用者VQ-VAE+潛在空間RX detection方法的具體比較、可借用之處、最大弱點。在主對話執行，因為使用者會想當場討論、追問、被挑戰想法。觸發詞：「幫我深讀這篇」、「這篇論文的假設合理嗎」、「跟我的方法比起來呢」。Key capabilities
- →Identify implicit assumptions in a paper
- →Compare paper methods to VQ-VAE+RX detection
- →Determine reusable parts from a paper
- →Identify the greatest weaknesses of a paper
- →Suggest citations to follow up on
- →Ask if the paper should be added to the literature database
How it works
The skill analyzes a core relevant paper, after a specification table has been produced, to critically evaluate its assumptions, compare its methods, identify reusable parts, and pinpoint weaknesses.
Inputs & outputs
When to use critical-read
- →Critiquing research papers
- →Validating paper assumptions
- →Comparing research methodologies
About this skill
Stage 1b：批判性深讀
這篇論文已判定為核心相關，且已有 Stage 1a 的規格表。請只針對下面這幾個需要判斷力的問題回答， 不要重複規格表已有的事實：
-
隱含假設：論文有什麼沒有明說但默認成立的假設？這些假設站得住腳嗎？
-
跟我方法的具體比較：
- 我目前的候選方法是 VQ-VAE 重建誤差 + 潛在空間 RX detection（現階段探索方向， 非定案方法）。這篇論文的方法在哪個環節跟我相似？哪個環節不同？
- 他們有沒有踩到我可能會踩的坑（光學影像特有的 hardware artifact、 coastal 區域的 spectral 干擾等）？
-
我能不能借用/延伸的具體部分是什麼？ 有沒有任何引用值得我去追？
-
這篇論文最大的弱點或未驗證假設是什麼？ （這個問題本身就是「假設殺手」的單篇版，先在這裡埋個種子， 等進入文獻庫六階段分析時，可以跟其他論文的假設一起比對）
回答完後，主動詢問使用者是否要正式收編進文獻庫，並提示累積到 5-8 篇核心相關論文時， 可以呼叫 lit-corpus-analysis 做整批分析。
When not to use it
- →When the paper has not been identified as core relevant
- →When a specification table from paper-extractor is not available
- →When the user does not want to discuss or be challenged on ideas
Limitations
- →The skill requires the paper to be core relevant.
- →The skill requires a specification table from paper-extractor.
- →The skill focuses on specific judgment-based questions.
How it compares
This skill provides a structured critical analysis of a paper, focusing on specific judgment-based questions, rather than just extracting facts.
Compared to similar skills
critical-read side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| critical-read (this skill) | 0 | 1mo | No flags | Intermediate |
| torchdrug | 3 | 8mo | Review | Advanced |
| string-database | 2 | 8mo | Review | Intermediate |
| transformer-lens-interpretability | 2 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
torchdrug
davila7
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
string-database
davila7
Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.
transformer-lens-interpretability
davila7
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
denario
davila7
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
tooluniverse
jimmc414
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets/PubChem/UniProt/PDB/ChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.
tooluniverse-binder-discovery
mims-harvard
Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches. Creates actionable reports with candidate compounds, ADMET profiles, and synthesis feasibility. Use when users ask to find small molecules for a target, identify novel binders, perform virtual screening, or need hit-to-lead compound identification.