Skip to content

feat: update research skills part 8 #54

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
markusha77 merged 3 commits into from
Mar 25, 2026
Merged

feat: update research skills part 8 #54

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ec9cf1c
feat: update research skills part 8 (20 folders)
SixiangH Mar 16, 2026
89e4267
Fix typo in Föhn wind patterns description
sixiang-svg Mar 21, 2026
78e5d5f
Fix typo in performance-optimized code snippet
sixiang-svg Mar 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions skills/Research/scientific-brainstorming/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,12 @@
---
category: Research
id: scientific-brainstorming
name: Scientific Brainstorming
description: Research ideation partner. Generate hypotheses, explore interdisciplinary connections, challenge assumptions, develop methodologies, identify research gaps, for creative scientific problem-solving.
description: Research ideation partner for generating hypotheses, exploring interdisciplinary connections, and identifying research gaps.
category: Research
requires: []
examples:
- Help me brainstorm novel research hypotheses for this dataset.
- Identify potential research gaps in the field of quantum biology.
---

# Scientific Brainstorming
Expand Down Expand Up @@ -167,7 +171,7 @@ Help crystallize insights and create concrete paths forward.

## Resources

### references/brainstorming_methods.md
### references

Contains detailed descriptions of structured brainstorming methodologies that can be consulted when standard techniques need supplementation:
- SCAMPER framework (Substitute, Combine, Adapt, Modify, Put to another use, Eliminate, Reverse)
Expand Down
28 changes: 19 additions & 9 deletions skills/Research/scientific-critical-thinking/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,21 +1,31 @@
---
category: Research
id: scientific-critical-thinking
name: Scientific Critical Thinking
description: Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
allowed-tools: [Read, Write, Edit, Bash]
description: Evaluate research rigor by assessing methodology, experimental design, and statistical validity of scientific claims.
category: Research
requires: []
examples:
- Assess the methodology of this research paper for potential bias.
- Evaluate the statistical validity of the claims made in this study.
---

# Scientific Critical Thinking

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
## Instruction
- Audit the research methodology by assessing the appropriateness of the experimental design and selected variables.
- Evaluate the statistical validity of claims, checking for p-hacking, insufficient sample sizes, or improper test selection.
- Identify potential sources of bias, including selection bias, observer bias, or systemic confounding factors.
- Utilize evidence quality frameworks such as GRADE or Cochrane Risk of Bias (ROB) to categorize the strength of scientific evidence.
- Scrutinize the connection between data and conclusions to ensure claims do not exceed the scope of the findings.
- Recommend rigorous validation steps or control experiments to address identified weaknesses in the study.

## When to Use

- You need help with scientific critical thinking.
- You want a clear, actionable next step.
- When reviewing scientific manuscripts or grant proposals for technical and logical rigor.
- When evaluating the reliability of published research findings or news regarding scientific breakthroughs.
- When self-auditing a research project to identify potential methodological flaws before submission.

## Output

- Summary of goals and plan
- Key tips and precautions
- A critical assessment report highlighting methodological strengths and specific areas of concern.
- Quantitative or qualitative ratings of evidence quality based on standardized research frameworks.
- Actionable recommendations for improving study design or performing sensitivity analysis.
18 changes: 8 additions & 10 deletions skills/Research/scientific-writing/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,16 +1,14 @@
---
category: Research
id: scientific-writing
name: Scientific Writing
description: Academic research assistant for literature reviews, paper analysis, and scholarly writing.
Academic research assistant for literature reviews, paper analysis, and scholarly writing.
Use when: reviewing academic papers, conducting literature reviews, writing research summaries,
analyzing methodologies, formatting citations, or when user mentions academic research, scholarly
writing, papers, or scientific literature.
license: MIT
metadata:
author: awesome-llm-apps
version: "1.0.0"
description: Academic research assistant for literature reviews, paper analysis, and structuring scholarly writing.
category: Research
author: awesome-llm-apps
version: 1.0.0
requires: []
examples:
- Help me structure the introduction section of my research paper.
- Format my citations in APA style for this literature review.
---

# Academic Researcher
Expand Down
195 changes: 6 additions & 189 deletions skills/Research/scikit-bio/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,12 @@
---
category: Research
id: scikit-bio
name: scikit-bio
description: Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
description: Toolkit for bioinformatics analyses including sequence manipulation, phylogenetic trees, and microbiome diversity metrics.
category: Research
requires: []
examples:
- Calculate alpha and beta diversity metrics for this microbiome dataset.
- Perform a PCoA ordination analysis on my distance matrix using scikit-bio.
---

# scikit-bio
Expand Down Expand Up @@ -39,26 +43,6 @@ Work with biological sequences using specialized classes for DNA, RNA, and prote
- Calculate distances (Hamming, k-mer based)
- Handle sequence quality scores and metadata

**Common patterns:**
```python
import skbio

# Read sequences from file
seq = skbio.DNA.read('input.fasta')

# Sequence operations
rc = seq.reverse_complement()
rna = seq.transcribe()
protein = rna.translate()

# Find motifs
motif_positions = seq.find_with_regex('ATG[ACGT]{3}')

# Check for properties
has_degens = seq.has_degenerates()
seq_no_gaps = seq.degap()
```

**Important notes:**
- Use `DNA`, `RNA`, `Protein` classes for grammared sequences with validation
- Use `Sequence` class for generic sequences without alphabet restrictions
Expand All @@ -76,22 +60,6 @@ Perform pairwise and multiple sequence alignments using dynamic programming algo
- CIGAR string conversion
- Multiple sequence alignment storage and manipulation with `TabularMSA`

**Common patterns:**
```python
from skbio.alignment import local_pairwise_align_ssw, TabularMSA

# Pairwise alignment
alignment = local_pairwise_align_ssw(seq1, seq2)

# Access aligned sequences
msa = alignment.aligned_sequences

# Read multiple alignment from file
msa = TabularMSA.read('alignment.fasta', constructor=skbio.DNA)

# Calculate consensus
consensus = msa.consensus()
```

**Important notes:**
- Use `local_pairwise_align_ssw` for local alignments (faster, SSW-based)
Expand All @@ -110,30 +78,6 @@ Construct, manipulate, and analyze phylogenetic trees representing evolutionary
- ASCII visualization
- Newick format I/O

**Common patterns:**
```python
from skbio import TreeNode
from skbio.tree import nj

# Read tree from file
tree = TreeNode.read('tree.nwk')

# Construct tree from distance matrix
tree = nj(distance_matrix)

# Tree operations
subtree = tree.shear(['taxon1', 'taxon2', 'taxon3'])
tips = [node for node in tree.tips()]
lca = tree.lowest_common_ancestor(['taxon1', 'taxon2'])

# Calculate distances
patristic_dist = tree.find('taxon1').distance(tree.find('taxon2'))
cophenetic_matrix = tree.cophenetic_matrix()

# Compare trees
rf_distance = tree.robinson_foulds(other_tree)
```

**Important notes:**
- Use `nj()` for neighbor joining (classic phylogenetic method)
- Use `upgma()` for UPGMA (assumes molecular clock)
Expand All @@ -151,25 +95,6 @@ Calculate alpha and beta diversity metrics for microbial ecology and community a
- Rarefaction and subsampling
- Integration with ordination and statistical tests

**Common patterns:**
```python
from skbio.diversity import alpha_diversity, beta_diversity
import skbio

# Alpha diversity
alpha = alpha_diversity('shannon', counts_matrix, ids=sample_ids)
faith_pd = alpha_diversity('faith_pd', counts_matrix, ids=sample_ids,
tree=tree, otu_ids=feature_ids)

# Beta diversity
bc_dm = beta_diversity('braycurtis', counts_matrix, ids=sample_ids)
unifrac_dm = beta_diversity('unweighted_unifrac', counts_matrix,
ids=sample_ids, tree=tree, otu_ids=feature_ids)

# Get available metrics
from skbio.diversity import get_alpha_diversity_metrics
print(get_alpha_diversity_metrics())
```

**Important notes:**
- Counts must be integers representing abundances, not relative frequencies
Expand All @@ -188,23 +113,6 @@ Reduce high-dimensional biological data to visualizable lower-dimensional spaces
- RDA (Redundancy Analysis) for linear relationships
- Biplot projection for feature interpretation

**Common patterns:**
```python
from skbio.stats.ordination import pcoa, cca

# PCoA from distance matrix
pcoa_results = pcoa(distance_matrix)
pc1 = pcoa_results.samples['PC1']
pc2 = pcoa_results.samples['PC2']

# CCA with environmental variables
cca_results = cca(species_matrix, environmental_matrix)

# Save/load ordination results
pcoa_results.write('ordination.txt')
results = skbio.OrdinationResults.read('ordination.txt')
```

**Important notes:**
- PCoA works with any distance/dissimilarity matrix
- CCA reveals environmental drivers of community composition
Expand All @@ -222,22 +130,6 @@ Perform hypothesis tests specific to ecological and biological data.
- Mantel test: correlation between distance matrices
- Bioenv: find environmental variables correlated with distances

**Common patterns:**
```python
from skbio.stats.distance import permanova, anosim, mantel

# Test if groups differ significantly
permanova_results = permanova(distance_matrix, grouping, permutations=999)
print(f"p-value: {permanova_results['p-value']}")

# ANOSIM test
anosim_results = anosim(distance_matrix, grouping, permutations=999)

# Mantel test between two distance matrices
mantel_results = mantel(dm1, dm2, method='pearson', permutations=999)
print(f"Correlation: {mantel_results[0]}, p-value: {mantel_results[1]}")
```

**Important notes:**
- Permutation tests provide non-parametric significance testing
- Use 999+ permutations for robust p-values
Expand All @@ -257,26 +149,6 @@ Read and write 19+ biological file formats with automatic format detection.
- Analysis: BLAST+6/7, GFF3, Ordination results
- Metadata: TSV/CSV with validation

**Common patterns:**
```python
import skbio

# Read with automatic format detection
seq = skbio.DNA.read('file.fasta', format='fasta')
tree = skbio.TreeNode.read('tree.nwk')

# Write to file
seq.write('output.fasta', format='fasta')

# Generator for large files (memory efficient)
for seq in skbio.io.read('large.fasta', format='fasta', constructor=skbio.DNA):
process(seq)

# Convert formats
seqs = list(skbio.io.read('input.fastq', format='fastq', constructor=skbio.DNA))
skbio.io.write(seqs, format='fasta', into='output.fasta')
```

**Important notes:**
- Use generators for large files to avoid memory issues
- Format can be auto-detected when `into` parameter specified
Expand All @@ -293,26 +165,6 @@ Create and manipulate distance/dissimilarity matrices with statistical methods.
- Integration with diversity, ordination, and statistical tests
- Read/write delimited text format

**Common patterns:**
```python
from skbio import DistanceMatrix
import numpy as np

# Create from array
data = np.array([[0, 1, 2], [1, 0, 3], [2, 3, 0]])
dm = DistanceMatrix(data, ids=['A', 'B', 'C'])

# Access distances
dist_ab = dm['A', 'B']
row_a = dm['A']

# Read from file
dm = DistanceMatrix.read('distances.txt')

# Use in downstream analyses
pcoa_results = pcoa(dm)
permanova_results = permanova(dm, grouping)
```

**Important notes:**
- DistanceMatrix enforces symmetry and zero diagonal
Expand All @@ -331,25 +183,7 @@ Work with feature tables (OTU/ASV tables) common in microbiome research.
- Sample/feature filtering and normalization
- Metadata integration

**Common patterns:**
```python
from skbio import Table

# Read BIOM table
table = Table.read('table.biom')

# Access data
sample_ids = table.ids(axis='sample')
feature_ids = table.ids(axis='observation')
counts = table.matrix_data

# Filter
filtered = table.filter(sample_ids_to_keep, axis='sample')

# Convert to/from pandas
df = table.to_dataframe()
table = Table.from_dataframe(df)
```

**Important notes:**
- BIOM tables are standard in QIIME 2 workflows
Expand All @@ -367,23 +201,6 @@ Work with protein language model embeddings for downstream analysis.
- Generate ordination objects for visualization
- Export to numpy/pandas for ML workflows

**Common patterns:**
```python
from skbio.embedding import ProteinEmbedding, ProteinVector

# Create embedding from array
embedding = ProteinEmbedding(embedding_array, sequence_ids)

# Convert to distance matrix for analysis
dm = embedding.to_distances(metric='euclidean')

# PCoA visualization of embedding space
pcoa_results = embedding.to_ordination(metric='euclidean', method='pcoa')

# Export for machine learning
array = embedding.to_array()
df = embedding.to_dataframe()
```

**Important notes:**
- Embeddings bridge protein language models with traditional bioinformatics
Expand Down
Loading
Loading