diff --git a/skills/Research/scientific-brainstorming/SKILL.md b/skills/Research/scientific-brainstorming/SKILL.md index 8cfb89ec..d388606c 100644 --- a/skills/Research/scientific-brainstorming/SKILL.md +++ b/skills/Research/scientific-brainstorming/SKILL.md @@ -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 @@ -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) diff --git a/skills/Research/scientific-critical-thinking/SKILL.md b/skills/Research/scientific-critical-thinking/SKILL.md index ee390ccf..170c2549 100644 --- a/skills/Research/scientific-critical-thinking/SKILL.md +++ b/skills/Research/scientific-critical-thinking/SKILL.md @@ -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. \ No newline at end of file diff --git a/skills/Research/scientific-writing/SKILL.md b/skills/Research/scientific-writing/SKILL.md index 0956fd56..474e501e 100644 --- a/skills/Research/scientific-writing/SKILL.md +++ b/skills/Research/scientific-writing/SKILL.md @@ -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 diff --git a/skills/Research/scikit-bio/SKILL.md b/skills/Research/scikit-bio/SKILL.md index d05c3833..3dbabccb 100644 --- a/skills/Research/scikit-bio/SKILL.md +++ b/skills/Research/scikit-bio/SKILL.md @@ -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 @@ -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 @@ -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) @@ -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) @@ -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 @@ -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 @@ -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 @@ -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 @@ -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 @@ -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 @@ -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 diff --git a/skills/Research/scikit-hep-analysis/SKILL.md b/skills/Research/scikit-hep-analysis/SKILL.md index 448fbad4..fab5a127 100644 --- a/skills/Research/scikit-hep-analysis/SKILL.md +++ b/skills/Research/scikit-hep-analysis/SKILL.md @@ -1,20 +1,32 @@ --- id: scikit-hep-analysis name: Scikit-HEP Analysis -description: Step-by-step guidance for scikit-hep. +description: Step-by-step guidance for high-energy physics analysis workflows using the Scikit-HEP library. category: Research +requires: [] +examples: + - Help me set up a Scikit-HEP workflow for my particle physics data. + - What are the best practices for using Scikit-HEP in data analysis? --- # Scikit-HEP Analysis Support scikit-hep workflows with clear steps and best practices. -## When to Use +## Instruction +- Utilize the Scikit-HEP ecosystem tools, specifically `uproot` and `awkward-array`, to access and manipulate large-scale physics datasets in ROOT format. +- Perform high-performance data processing on jagged (non-rectilinear) arrays commonly found in particle collision events. +- Implement histogramming and visualization using `boost-histogram` or `mplhep` to generate publication-quality physics plots. +- Execute statistical fitting and parameter estimation tasks using wrappers for `iminuit` or `zfit`. +- Conduct decay chain analysis and kinematic calculations for particle identification and event reconstruction. +- Follow best practices for memory management when processing multi-terabyte HEP datasets on distributed systems. -- You need help with scikit-hep analysis. -- You want a clear, actionable next step. +## When to Use +- When performing data analysis for high-energy physics experiments (e.g., LHC, Belle II) using the Python scientific stack. +- When needing to read or write ROOT files without a full ROOT installation. +- When visualizing and fitting complex particle physics histograms and distributions. ## Output - -- Summary of goals and plan -- Key tips and precautions +- Summarized HEP analysis plans including data loading strategies and selection cuts. +- Annotated physics plots (e.g., invariant mass distributions) with statistical fit results. +- Performance-optimized Python code snippets for HEP data manipulation. diff --git a/skills/Research/scope-logic-analyzer/SKILL.md b/skills/Research/scope-logic-analyzer/SKILL.md index 0dc5ecec..ed1825a5 100644 --- a/skills/Research/scope-logic-analyzer/SKILL.md +++ b/skills/Research/scope-logic-analyzer/SKILL.md @@ -1,15 +1,12 @@ --- id: scope-logic-analyzer name: Scope Logic Analyzer -description: Test equipment integration for signal analysis (oscilloscope and logic analyzer). +description: Test equipment integration for automated measurements and protocol decoding using oscilloscopes and logic analyzers. category: Research -allowed-tools: - - Bash - - Read - - Write - - Edit - - Glob - - Grep +requires: [] +examples: + - Automate a rise time measurement for CH1 on my oscilloscope. + - How do I set up an I2C protocol decoder on my logic analyzer? --- # Oscilloscope/Logic Analyzer Skill @@ -18,6 +15,24 @@ allowed-tools: This skill provides test equipment integration for signal analysis, enabling automated measurements, protocol decoding, and timing verification using oscilloscopes and logic analyzers. +## Instruction +- Configure oscilloscope parameters including channel scaling, trigger levels, and time-base settings via automated SCPI commands. +- Execute automated signal integrity measurements such as rise/fall times, jitter analysis, and eye diagram generation. +- Set up logic analyzer captures, defining sample rates, capture depths, and trigger conditions for digital bus analysis. +- Implement protocol decoding for standard interfaces including I2C, SPI, UART, and CAN/LIN. +- Perform timing validation for hardware bring-up, focusing on setup/hold time verification and propagation delays. +- Export waveform data and capture logs for documentation and remote debugging of hardware issues. + +## When to Use +- When automating repetitive signal measurements during hardware validation or EMI pre-compliance testing. +- When debugging complex serial communication protocols or verifying real-time timing performance in embedded systems. +- When needing to correlate analog waveforms with digital logic states during system-level troubleshooting. + +## Output +- Automated measurement reports including signal timing and amplitude statistics. +- Decoded protocol logs and timing diagrams highlighting bus events or errors. +- Technical advice on equipment configuration and optimal probe placement for high-fidelity signal capture. + ## Capabilities ### Oscilloscope Operations @@ -77,9 +92,9 @@ This skill provides test equipment integration for signal analysis, enabling aut ## Target Processes -- `signal-integrity-testing.js` - Signal quality validation -- `hardware-bring-up.js` - Initial signal verification -- `real-time-performance-validation.js` - Timing validation +Signal quality validation +Initial signal verification +Timing validation ## Dependencies @@ -97,39 +112,3 @@ This skill is invoked when tasks require: - Hardware validation - EMI pre-compliance testing -## Measurement Examples - -### Rise Time Measurement -```python -scope.channel[1].enabled = True -scope.channel[1].scale = 1.0 # V/div -scope.trigger.source = "CH1" -scope.trigger.level = 1.65 # V -scope.trigger.slope = "RISE" - -measurement = scope.measure.rise_time("CH1") -print(f"Rise time: {measurement * 1e9:.2f} ns") -``` - -### Logic Analyzer Capture -```python -analyzer.set_sample_rate(24e6) # 24 MHz -analyzer.set_capture_depth(10e6) # 10M samples -analyzer.add_decoder("i2c", sda=0, scl=1) -analyzer.trigger.add_condition("i2c_start") -analyzer.start_capture() -``` - -## Configuration - -```yaml -equipment: - oscilloscope: - type: keysight | tektronix | rigol - connection: visa | usb | ethernet - address: "TCPIP::192.168.1.100::INSTR" - logic_analyzer: - type: saleae | sigrok - sample_rate: 24MHz - channels: 8 -``` diff --git a/skills/Research/scvi-tools/SKILL.md b/skills/Research/scvi-tools/SKILL.md index 34da3218..d3d50ddb 100644 --- a/skills/Research/scvi-tools/SKILL.md +++ b/skills/Research/scvi-tools/SKILL.md @@ -1,8 +1,12 @@ --- -category: Research id: scvi-tools name: scvi-tools -description: Step-by-step guidance for scvi-tools. +description: Variational inference framework for probabilistic modeling of single-cell genomics data modalities. +category: Research +requires: [] +examples: + - Perform batch correction on my single-cell RNA-seq data using scVI. + - Annotate cell types in my dataset using a semi-supervised scANVI model. --- # scvi-tools @@ -23,6 +27,19 @@ Use this skill when: - Working with specialized single-cell modalities (methylation, cytometry, RNA velocity) - Building custom probabilistic models for single-cell analysis +## Instruction +- Register the single-cell dataset using `setup_anndata`, ensuring all relevant covariates (batch, donor, cell-cycle) are correctly identified. +- Initialize and train probabilistic models such as scVI for batch correction and integration of single-cell RNA-seq data. +- Utilize semi-supervised models like scANVI for automated cell type annotation and transfer learning across datasets. +- Perform multimodal analysis using models like TotalVI for combined RNA and surface protein (CITE-seq) data. +- Execute differential expression analysis using the model's posterior distributions for robust, uncertainty-aware statistical testing. +- Optimize training performance by enabling GPU acceleration and monitoring convergence via training history logs. + +## Output +- Trained scvi-tools models and associated latent representations (embeddings). +- Summarized integration reports highlighting batch correction success and identified cell clusters. +- Actionable differential expression results and cell-type annotation labels with confidence scores. + ## Core Capabilities scvi-tools provides models organized by data modality: @@ -65,41 +82,19 @@ Additional specialized analysis tools. See `references/models-specialized.md` fo All scvi-tools models follow a consistent API pattern: -```python -# 1. Load and preprocess data (AnnData format) -import scvi -import scanpy as sc - -adata = scvi.data.heart_cell_atlas_subsampled() -sc.pp.filter_genes(adata, min_counts=3) -sc.pp.highly_variable_genes(adata, n_top_genes=1200) - -# 2. Register data with model (specify layers, covariates) -scvi.model.SCVI.setup_anndata( - adata, - layer="counts", # Use raw counts, not log-normalized - batch_key="batch", - categorical_covariate_keys=["donor"], - continuous_covariate_keys=["percent_mito"] -) - -# 3. Create and train model -model = scvi.model.SCVI(adata) -model.train() - -# 4. Extract latent representations and normalized values -latent = model.get_latent_representation() -normalized = model.get_normalized_expression(library_size=1e4) - -# 5. Store in AnnData for downstream analysis -adata.obsm["X_scVI"] = latent -adata.layers["scvi_normalized"] = normalized - -# 6. Downstream analysis with scanpy -sc.pp.neighbors(adata, use_rep="X_scVI") -sc.tl.umap(adata) -sc.tl.leiden(adata) -``` + +1. Load and preprocess data (AnnData format) + +2. Register data with model (specify layers, covariates) + +3. Create and train model + +4. Extract latent representations and normalized values + +5. Store in AnnData for downstream analysis + +6. Downstream analysis with scanpy + **Key Design Principles:** - **Raw counts required**: Models expect unnormalized count data for optimal performance @@ -111,44 +106,15 @@ sc.tl.leiden(adata) ## Common Analysis Tasks ### Differential Expression -Probabilistic DE analysis using the learned generative models: - -```python -de_results = model.differential_expression( - groupby="cell_type", - group1="TypeA", - group2="TypeB", - mode="change", # Use composite hypothesis testing - delta=0.25 # Minimum effect size threshold -) -``` - -See `references/differential-expression.md` for detailed methodology and interpretation. +Probabilistic DE analysis using the learned generative models ### Model Persistence -Save and load trained models: +Save and load trained models -```python -# Save model -model.save("./model_directory", overwrite=True) - -# Load model -model = scvi.model.SCVI.load("./model_directory", adata=adata) -``` ### Batch Correction and Integration Integrate datasets across batches or studies: -```python -# Register batch information -scvi.model.SCVI.setup_anndata(adata, batch_key="study") - -# Model automatically learns batch-corrected representations -model = scvi.model.SCVI(adata) -model.train() -latent = model.get_latent_representation() # Batch-corrected -``` - ## Theoretical Foundations scvi-tools is built on: @@ -157,23 +123,6 @@ scvi-tools is built on: - **Amortized inference**: Shared neural networks for efficient learning across cells - **Probabilistic modeling**: Principled uncertainty quantification and statistical testing -See `references/theoretical-foundations.md` for detailed background on the mathematical framework. - -## Additional Resources - -- **Workflows**: `references/workflows.md` contains common workflows, best practices, hyperparameter tuning, and GPU optimization -- **Model References**: Detailed documentation for each model category in the `references/` directory -- **Official Documentation**: https://docs.scvi-tools.org/en/stable/ -- **Tutorials**: https://docs.scvi-tools.org/en/stable/tutorials/index.html -- **API Reference**: https://docs.scvi-tools.org/en/stable/api/index.html - -## Installation - -```bash -uv pip install scvi-tools -# For GPU support -uv pip install scvi-tools[cuda] -``` ## Best Practices diff --git a/skills/Research/segment-combiner/SKILL.md b/skills/Research/segment-combiner/SKILL.md index 7bea9f31..ef2e68ca 100644 --- a/skills/Research/segment-combiner/SKILL.md +++ b/skills/Research/segment-combiner/SKILL.md @@ -1,10 +1,13 @@ --- -category: Research id: segment-combiner name: Segment Combiner -description: Combine multiple segment detection results into a unified list. +description: Combine multiple segment JSON files into a single unified segments file for video processing workflows. +category: Research +requires: [] +examples: + - Combine segments from my two video detection files into one. + - Merge these JSON segments and calculate the total duration. --- - # Segment Combiner Combines multiple segment JSON files into a single unified segments file for video processing. @@ -15,13 +18,15 @@ Combines multiple segment JSON files into a single unified segments file for vid - Consolidating detection results - Preparing unified input for video-processor -## Usage +## Instruction +- Load multiple JSON segment files generated by previous video or audio detection steps. +- Parse the `segments` array from each input file to extract start times, end times, and durations. +- Consolidate detection results by merging overlapping or adjacent segments to create a unified timeline. +- Calculate the aggregate metrics for the combined segments, including total segment count and total duration in seconds. +- Validate the combined segment list to ensure chronological order and resolve any conflicting timestamps. +- Export the unified segment data into a single JSON file ready for downstream video processing or editing tools. -```bash -python3 /root/.claude/skills/segment-combiner/scripts/combine_segments.py \ - --segments /path/to/segments1.json /path/to/segments2.json \ - --output /path/to/all_segments.json -``` +## Usage ### Parameters diff --git a/skills/Research/seo-cannibalization-detector/SKILL.md b/skills/Research/seo-cannibalization-detector/SKILL.md index 1ebe4eff..7f970c7c 100644 --- a/skills/Research/seo-cannibalization-detector/SKILL.md +++ b/skills/Research/seo-cannibalization-detector/SKILL.md @@ -1,12 +1,12 @@ --- -category: Research id: seo-cannibalization-detector name: SEO Cannibalization Detector -description: Analyzes multiple provided pages to identify keyword overlap and potential cannibalization issues. Suggests differentiation strategies. Use PROACTIVELY when reviewing similar content. - potential cannibalization issues. Suggests differentiation strategies. Use - PROACTIVELY when reviewing similar content. -metadata: - model: haiku +description: Identify keyword overlap and potential cannibalization issues across multiple pages to suggest differentiation and consolidation strategies. +category: Research +requires: [] +examples: + - Check if these three URLs are competing for the same keywords. + - Analyze these pages for SEO cannibalization and suggest a resolution strategy. --- ## Use this skill when diff --git a/skills/Research/seo-keyword-strategist/SKILL.md b/skills/Research/seo-keyword-strategist/SKILL.md index 87035ac0..4a0ef428 100644 --- a/skills/Research/seo-keyword-strategist/SKILL.md +++ b/skills/Research/seo-keyword-strategist/SKILL.md @@ -1,12 +1,12 @@ --- -category: Research id: seo-keyword-strategist name: SEO Keyword Strategist -description: Analyzes keyword usage in provided content, calculates density, suggests semantic variations and LSI keywords based on the topic. Prevents over-optimization. Use PROACTIVELY for content optimization. - suggests semantic variations and LSI keywords based on the topic. Prevents - over-optimization. Use PROACTIVELY for content optimization. -metadata: - model: haiku +description: Analyze keyword density in content and suggest semantic variations, LSI keywords, and entity mappings for topical authority. +category: Research +requires: [] +examples: + - Suggest LSI keywords and analyze density for this blog post. + - Map entities and related concepts to improve my content's topical authority. --- ## Use this skill when diff --git a/skills/Research/setting-up-experiment-tracking/SKILL.md b/skills/Research/setting-up-experiment-tracking/SKILL.md index 9d08ad01..90760568 100644 --- a/skills/Research/setting-up-experiment-tracking/SKILL.md +++ b/skills/Research/setting-up-experiment-tracking/SKILL.md @@ -1,9 +1,12 @@ --- -category: Research id: setting-up-experiment-tracking name: Setting Up Experiment Tracking -description: This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs. - This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs. +description: Automate machine learning experiment tracking setup using tools like MLflow or Weights & Biases (W&B) for reproducibility. +category: Research +requires: [] +examples: + - Setup experiment tracking with MLflow for my current project. + - How do I integrate Weights & Biases into my PyTorch training loop? --- ## Overview @@ -25,6 +28,11 @@ This skill activates when you need to: - Quickly set up MLflow or Weights & Biases for experiment management. - Automate the process of logging parameters, metrics, and artifacts. +## Output +- Environment setup logs and confirmation of the initialized tracking tool. +- Reusable Python code templates for logging experiment parameters, metrics, and models. +- A summarized tracking plan with recommendations for consistent metadata and artifact management. + ## Examples ### Example 1: Starting a New Project with MLflow diff --git a/skills/Research/simpy/SKILL.md b/skills/Research/simpy/SKILL.md index 48ef3d66..94afa566 100644 --- a/skills/Research/simpy/SKILL.md +++ b/skills/Research/simpy/SKILL.md @@ -1,8 +1,12 @@ --- -category: Research id: simpy name: Simpy -description: Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time. +description: Process-based discrete-event simulation framework in Python for modeling systems with shared resources and time-based events. +category: Research +requires: [] +examples: + - Model a manufacturing production line using SimPy discrete-event simulation. + - Simulate a hospital emergency room to analyze patient waiting times. --- # SimPy - Discrete-Event Simulation @@ -35,50 +39,19 @@ Use the SimPy skill when: - Independent processes without resource sharing - Pure mathematical optimization (consider SciPy optimize) -## Quick Start - -### Basic Simulation Structure - -```python -import simpy - -def process(env, name): - """A simple process that waits and prints.""" - print(f'{name} starting at {env.now}') - yield env.timeout(5) - print(f'{name} finishing at {env.now}') - -# Create environment -env = simpy.Environment() - -# Start processes -env.process(process(env, 'Process 1')) -env.process(process(env, 'Process 2')) +## Instruction +- Identify the core components of the system to be simulated, including entities, processes, and shared resources (e.g., servers, machines). +- Construct the simulation model using Python generator functions to define entity behaviors and event-driven logic. +- Implement resource management by utilizing SimPy objects like `Resource`, `Container`, or `Store` to handle contention. +- Configure data collection hooks to monitor system metrics such as queue lengths, waiting times, and total throughput. +- Execute the simulation over a defined time horizon, ensuring reproducibility through controlled random seeding. +- Analyze and visualize simulation logs to identify system bottlenecks and evaluate process optimization strategies. -# Run simulation -env.run(until=10) -``` +## Output +- Executable Python simulation code with defined process logic and resource constraints. +- Quantitative performance reports detailing average wait times, resource utilization, and throughput. +- Visual summaries of simulation results and actionable recommendations for system improvements. -### Resource Usage Pattern - -```python -import simpy - -def customer(env, name, resource): - """Customer requests resource, uses it, then releases.""" - with resource.request() as req: - yield req # Wait for resource - print(f'{name} got resource at {env.now}') - yield env.timeout(3) # Use resource - print(f'{name} released resource at {env.now}') - -env = simpy.Environment() -server = simpy.Resource(env, capacity=1) - -env.process(customer(env, 'Customer 1', server)) -env.process(customer(env, 'Customer 2', server)) -env.run() -``` ## Core Concepts @@ -86,61 +59,19 @@ env.run() The simulation environment manages time and schedules events. -```python -import simpy - -# Standard environment (runs as fast as possible) -env = simpy.Environment(initial_time=0) - -# Real-time environment (synchronized with wall-clock) -import simpy.rt -env_rt = simpy.rt.RealtimeEnvironment(factor=1.0) - -# Run simulation -env.run(until=100) # Run until time 100 -env.run() # Run until no events remain -``` ### 2. Processes Processes are defined using Python generator functions (functions with `yield` statements). -```python -def my_process(env, param1, param2): - """Process that yields events to pause execution.""" - print(f'Starting at {env.now}') - - # Wait for time to pass - yield env.timeout(5) - - print(f'Resumed at {env.now}') - - # Wait for another event - yield env.timeout(3) - - print(f'Done at {env.now}') - return 'result' - -# Start the process -env.process(my_process(env, 'value1', 'value2')) -``` ### 3. Events Events are the fundamental mechanism for process synchronization. Processes yield events and resume when those events are triggered. -**Common event types:** -- `env.timeout(delay)` - Wait for time to pass -- `resource.request()` - Request a resource -- `env.event()` - Create a custom event -- `env.process(func())` - Process as an event -- `event1 & event2` - Wait for all events (AllOf) -- `event1 | event2` - Wait for any event (AnyOf) ## Resources -SimPy provides several resource types for different scenarios. For comprehensive details, see `references/resources.md`. - ### Resource Types Summary | Resource Type | Use Case | @@ -153,108 +84,16 @@ SimPy provides several resource types for different scenarios. For comprehensive | FilterStore | Selective item retrieval | | PriorityStore | Priority-ordered items | -### Quick Reference - -```python -import simpy - -env = simpy.Environment() - -# Basic resource (e.g., servers) -resource = simpy.Resource(env, capacity=2) - -# Priority resource -priority_resource = simpy.PriorityResource(env, capacity=1) - -# Container (e.g., fuel tank) -fuel_tank = simpy.Container(env, capacity=100, init=50) - -# Store (e.g., warehouse) -warehouse = simpy.Store(env, capacity=10) -``` ## Common Simulation Patterns ### Pattern 1: Customer-Server Queue -```python -import simpy -import random - -def customer(env, name, server): - arrival = env.now - with server.request() as req: - yield req - wait = env.now - arrival - print(f'{name} waited {wait:.2f}, served at {env.now}') - yield env.timeout(random.uniform(2, 4)) - -def customer_generator(env, server): - i = 0 - while True: - yield env.timeout(random.uniform(1, 3)) - i += 1 - env.process(customer(env, f'Customer {i}', server)) - -env = simpy.Environment() -server = simpy.Resource(env, capacity=2) -env.process(customer_generator(env, server)) -env.run(until=20) -``` ### Pattern 2: Producer-Consumer -```python -import simpy - -def producer(env, store): - item_id = 0 - while True: - yield env.timeout(2) - item = f'Item {item_id}' - yield store.put(item) - print(f'Produced {item} at {env.now}') - item_id += 1 - -def consumer(env, store): - while True: - item = yield store.get() - print(f'Consumed {item} at {env.now}') - yield env.timeout(3) - -env = simpy.Environment() -store = simpy.Store(env, capacity=10) -env.process(producer(env, store)) -env.process(consumer(env, store)) -env.run(until=20) -``` - ### Pattern 3: Parallel Task Execution -```python -import simpy - -def task(env, name, duration): - print(f'{name} starting at {env.now}') - yield env.timeout(duration) - print(f'{name} done at {env.now}') - return f'{name} result' - -def coordinator(env): - # Start tasks in parallel - task1 = env.process(task(env, 'Task 1', 5)) - task2 = env.process(task(env, 'Task 2', 3)) - task3 = env.process(task(env, 'Task 3', 4)) - - # Wait for all to complete - results = yield task1 & task2 & task3 - print(f'All done at {env.now}') - -env = simpy.Environment() -env.process(coordinator(env)) -env.run() -``` - ## Workflow Guide ### Step 1: Define the System @@ -269,51 +108,13 @@ Identify: Create generator functions for each process type: -```python -def entity_process(env, name, resources, parameters): - # Arrival logic - arrival_time = env.now - - # Request resources - with resource.request() as req: - yield req - - # Service logic - service_time = calculate_service_time(parameters) - yield env.timeout(service_time) - - # Departure logic - collect_statistics(env.now - arrival_time) -``` ### Step 3: Set Up Monitoring -Use monitoring utilities to collect data. See `references/monitoring.md` for comprehensive techniques. - -```python -from scripts.resource_monitor import ResourceMonitor - -# Create and monitor resource -resource = simpy.Resource(env, capacity=2) -monitor = ResourceMonitor(env, resource, "Server") - -# After simulation -monitor.report() -``` +Use monitoring utilities to collect data. ### Step 4: Run and Analyze -```python -# Run simulation -env.run(until=simulation_time) - -# Generate reports -monitor.report() -stats.report() - -# Export data for further analysis -monitor.export_csv('results.csv') -``` ## Advanced Features @@ -330,71 +131,14 @@ Processes can interact through events, process yields, and interrupts. See `refe Synchronize simulation with wall-clock time for hardware-in-the-loop or interactive applications. See `references/real-time.md`. -```python -import simpy.rt - -env = simpy.rt.RealtimeEnvironment(factor=1.0) # 1:1 time mapping -# factor=0.5 means 1 sim unit = 0.5 seconds (2x faster) -``` - ### Comprehensive Monitoring -Monitor processes, resources, and events. See `references/monitoring.md` for techniques including: +Monitor processes, resources, and events. - State variable tracking - Resource monkey-patching - Event tracing - Statistical collection -## Scripts and Templates - -### basic_simulation_template.py - -Complete template for building queue simulations with: -- Configurable parameters -- Statistics collection -- Customer generation -- Resource usage -- Report generation - -**Usage:** -```python -from scripts.basic_simulation_template import SimulationConfig, run_simulation - -config = SimulationConfig() -config.num_resources = 2 -config.sim_time = 100 -stats = run_simulation(config) -stats.report() -``` - -### resource_monitor.py - -Reusable monitoring utilities: -- `ResourceMonitor` - Track single resource -- `MultiResourceMonitor` - Monitor multiple resources -- `ContainerMonitor` - Track container levels -- Automatic statistics calculation -- CSV export functionality - -**Usage:** -```python -from scripts.resource_monitor import ResourceMonitor - -monitor = ResourceMonitor(env, resource, "My Resource") -# ... run simulation ... -monitor.report() -monitor.export_csv('data.csv') -``` - -## Reference Documentation - -Detailed guides for specific topics: - -- **`references/resources.md`** - All resource types with examples -- **`references/events.md`** - Event system and patterns -- **`references/process-interaction.md`** - Process synchronization -- **`references/monitoring.md`** - Data collection techniques -- **`references/real-time.md`** - Real-time simulation setup ## Best Practices diff --git a/skills/Research/solar-weather/SKILL.md b/skills/Research/solar-weather/SKILL.md index 3cbd8a32..62be303a 100644 --- a/skills/Research/solar-weather/SKILL.md +++ b/skills/Research/solar-weather/SKILL.md @@ -1,20 +1,32 @@ --- id: solar-weather name: Solar Weather -description: Step-by-step guidance for solar weather. +description: Step-by-step guidance and best practices for solar weather forecasting and monitoring workflows. category: Research +requires: [] +examples: + - Provide a step-by-step guide for solar weather forecasting. + - What are the best practices for monitoring solar flare activity? --- # Solar Weather Support solar weather workflows with clear steps and best practices. -## When to Use +## Instruction +- Retrieve current solar activity data, including sunspot counts, flare status, and coronal mass ejection (CME) events. +- Analyze real-time imagery from space observatories to identify emerging solar features and active regions. +- Forecast the impact of solar events on Earth's ionosphere and calculate predicted geomagnetic indices (e.g., Kp-index). +- Evaluate operational risks to satellite systems, GPS precision, and terrestrial power grid stability based on current activity. +- Provide step-by-step guidance for interpreting solar spectral data and X-ray flux measurements for scientific research. +- Establish a long-term monitoring workflow to track solar cycle trends and prepare for extreme space weather anomalies. -- You need help with solar weather. -- You want a clear, actionable next step. +## When to Use +- When needing real-time alerts or impact assessments for solar flares and geomagnetic storms. +- When performing research on the effects of space weather on modern communication and navigation infrastructure. +- When monitoring long-term solar variability for astrophysical research or planetary safety studies. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A comprehensive solar weather briefing with current activity status and Kp-index forecasts. +- Tactical recommendations for mitigating interference in GPS and high-frequency radio systems. +- Structured data summaries of solar event characteristics and their predicted Earth-arrival times. \ No newline at end of file diff --git a/skills/Research/spacex/SKILL.md b/skills/Research/spacex/SKILL.md index 1542eead..0a35f107 100644 --- a/skills/Research/spacex/SKILL.md +++ b/skills/Research/spacex/SKILL.md @@ -1,20 +1,32 @@ --- id: spacex name: SpaceX -description: Step-by-step guidance for spacex. +description: Step-by-step guidance for SpaceX launch tracking workflows and telemetry data analysis best practices. category: Research +requires: [] +examples: + - Help me set up a SpaceX launch tracking workflow. + - What are the best practices for analyzing SpaceX telemetry data? --- # SpaceX Support spacex workflows with clear steps and best practices. -## When to Use +## Instruction +- Identify target SpaceX missions by querying official manifest data and real-time launch schedules. +- Monitor live launch countdowns and aggregate status updates from mission control and ground support telemetry. +- Analyze flight data to track key milestones, including stage separation, fairing deployment, and orbital insertion. +- Evaluate booster recovery operations, specifically landing attempt status on droneships (OCISLY/JRTI) or land zones. +- Synthesize technical vehicle specifications (e.g., Falcon 9, Falcon Heavy, Starship) for mission-specific performance analysis. +- Utilize SpaceX data APIs to build automated launch dashboards or custom research alerts for upcoming missions. -- You need help with spacex. -- You want a clear, actionable next step. +## When to Use +- When tracking live mission progress or requiring detailed technical reports on past SpaceX launches. +- When researching reusable launch vehicle performance and historical booster reuse statistics. +- When needing to integrate real-time SpaceX mission data into automated tracking or notification systems. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A summarized mission timeline with launch milestones and vehicle recovery outcomes. +- Technical telemetry summaries covering velocity, altitude, and landing accuracy. +- Actionable summaries for integrating SpaceX manifest data into custom research applications. \ No newline at end of file diff --git a/skills/Research/starlink/SKILL.md b/skills/Research/starlink/SKILL.md index 71db99c1..07b63597 100644 --- a/skills/Research/starlink/SKILL.md +++ b/skills/Research/starlink/SKILL.md @@ -1,20 +1,31 @@ --- id: starlink name: Starlink -description: Step-by-step guidance for starlink. +description: Step-by-step guidance for monitoring Starlink satellite passes and analyzing network performance data. category: Research +requires: [] +examples: + - Provide a guide for monitoring Starlink satellite passes over my location. + - How can I analyze Starlink network performance and latency data? --- # Starlink Support starlink workflows with clear steps and best practices. +## Instruction +- Calculate upcoming Starlink satellite pass times and visibility windows for a specific geographical location. +- Analyze network telemetry data, focusing on downlink/uplink speeds, latency (ping), and packet loss metrics. +- Monitor constellation-wide status to identify regional service degradations or maintenance-related outages. +- Evaluate the impact of environmental factors (e.g., weather, obstructions) on the quality of the satellite internet connection. +- Provide optimization guidance for Dishy placement and router configuration to maximize throughput and minimize dropouts. +- Correlate local performance data with active satellite density to estimate regional network capacity. ## When to Use - -- You need help with starlink. -- You want a clear, actionable next step. +- When predicting satellite visibility for astronomical observation or field connectivity planning. +- When performing research on LEO (Low Earth Orbit) satellite constellation performance and latency. +- When troubleshooting user connectivity issues or evaluating Starlink as a primary/backup internet solution. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A localized pass schedule and visibility report for Starlink satellites. +- Comprehensive network performance summaries with latency and stability statistics. +- Actionable next steps for hardware alignment and system performance optimization. \ No newline at end of file diff --git a/skills/Research/starwars/SKILL.md b/skills/Research/starwars/SKILL.md index 824ceda2..3ef87790 100644 --- a/skills/Research/starwars/SKILL.md +++ b/skills/Research/starwars/SKILL.md @@ -1,20 +1,32 @@ --- id: starwars name: Star Wars -description: Step-by-step guidance for star wars. +description: Systematic guidance for Star Wars lore research, media database organization, and franchise-specific workflows. category: Research +requires: [] +examples: + - Guide me through Star Wars lore research regarding the High Republic. + - What are the best practices for organizing a Star Wars media database? --- # Star Wars Support star wars workflows with clear steps and best practices. -## When to Use +## Instruction +- Define the specific Star Wars research scope, such as eras (e.g., High Republic, Rise of the First Order) or specific character lineages. +- Query specialized lore databases to synthesize comprehensive summaries, distinguishing between Canon and Legends material. +- Organize media databases by cataloging films, television series, novels, and comics into chronological or thematic order. +- Analyze the political dynamics and history of major galactic factions like the Galactic Republic, the Empire, and the Jedi Order. +- Establish best practices for cross-referencing lore claims across primary visual media and secondary reference guidebooks. +- Develop structured workflows for managing creative fan-based research or professional franchise analysis projects. -- You need help with star wars. -- You want a clear, actionable next step. +## When to Use +- When conducting deep-dive lore research or resolving continuity questions within the Star Wars universe. +- When managing large digital collections of franchise-related media and documentation. +- When drafting thematic analyses or chronological summaries for fan projects or professional research. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A structured lore briefing with verified citations and historical context from the franchise. +- Chronological or thematic media manifests tailored to the user's research focus. +- Actionable summaries of galactic events, character arcs, or political transformations. \ No newline at end of file diff --git a/skills/Research/string-database/SKILL.md b/skills/Research/string-database/SKILL.md index 26a774dd..ce99333d 100644 --- a/skills/Research/string-database/SKILL.md +++ b/skills/Research/string-database/SKILL.md @@ -1,20 +1,32 @@ --- -category: Research id: string-database name: String Database -description: Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology. +description: Query STRING API for protein-protein interactions, network analysis, and functional enrichment across 5000+ species. +category: Research +requires: [] +examples: + - Search for protein-protein interactions for the human TP53 gene. + - Perform a functional enrichment analysis using the STRING database. --- # String Database Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology. -## When to Use +## Instruction +- Formulate STRING API queries to retrieve protein-protein interaction (PPI) networks for specific gene lists or protein identifiers. +- Filter interactions based on evidence channels, including experimental assays, text mining, and genomic co-expression scores. +- Perform functional enrichment analysis (e.g., GO terms, KEGG pathways) on the identified interaction clusters. +- Analyze the network topology to identify high-degree "hub" proteins and critical functional modules. +- Adjust confidence thresholds (low to highest) to balance the discovery of novel interactions with high-fidelity verification. +- Export interaction matrices and high-quality network visualizations for integration into systems biology research. -- You need help with string database. -- You want a clear, actionable next step. +## When to Use +- When researching functional and physical connections between proteins in over 5,000 species. +- When performing pathway enrichment analysis to identify biological processes associated with a set of candidate genes. +- When constructing molecular interaction networks for drug target discovery or biomarker identification. ## Output - -- Summary of goals and plan -- Key tips and precautions +- Detailed PPI network tables with associated evidence scores and annotations. +- Biological enrichment reports identifying significant pathways and functional groups. +- Visualizations of the protein interactome highlighting key functional modules and hub nodes. \ No newline at end of file diff --git a/skills/Research/swiss-geo/SKILL.md b/skills/Research/swiss-geo/SKILL.md index 39e050f1..a8857c98 100644 --- a/skills/Research/swiss-geo/SKILL.md +++ b/skills/Research/swiss-geo/SKILL.md @@ -1,20 +1,31 @@ --- id: swiss-geo name: Swiss Geo -description: Step-by-step guidance for swiss geo. +description: Step-by-step guidance for Swiss geographic data workflows and spatial analysis best practices. category: Research +requires: [] +examples: + - Show me the geographic boundaries for the Canton of Zurich. + - How do I fetch Swiss coordinate data for a specific address? --- # Swiss Geo Support swiss geo workflows with clear steps and best practices. +## Instruction +- Retrieve high-resolution Swiss geographic boundaries for cantons, communes, and official administrative districts. +- Perform coordinate transformations between the Swiss national grid (LV95/LV03) and international systems (WGS84). +- Access and analyze spatial datasets from official Swiss sources (e.g., swisstopo) for land use or topographical research. +- Map Swiss-specific addresses to precise geographic coordinates for logistics or urban development tasks. +- Create customized maps and spatial visualizations that adhere to Swiss official cartographic standards. +- Implement workflows for processing unique Swiss geospatial formats such as INTERLIS for data exchange. ## When to Use - -- You need help with swiss geo. -- You want a clear, actionable next step. +- When requiring precise boundary data or spatial metrics for Swiss cantonal and communal infrastructure. +- When performing mapping and coordinate conversion tasks within the Swiss national geodata framework. +- When analyzing topography, land cover, or elevation data in Switzerland using official geodata repositories. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A summarized spatial report containing Swiss boundary data or transformed coordinate sets. +- Custom cartographic visualizations of Swiss geographic and administrative features. +- Technical advice on accessing and utilizing official Swiss geodata layers for research. \ No newline at end of file diff --git a/skills/Research/swissweather/SKILL.md b/skills/Research/swissweather/SKILL.md index 3c408e3f..29efae00 100644 --- a/skills/Research/swissweather/SKILL.md +++ b/skills/Research/swissweather/SKILL.md @@ -1,20 +1,32 @@ --- id: swissweather name: SwissWeather -description: Step-by-step guidance for swissweather. +description: Step-by-step guidance for fetching Swiss weather data and using local forecasting services. category: Research +requires: [] +examples: + - What is the 5-day weather forecast for Geneva? + - Get the current temperature and wind speed in Zermatt using SwissWeather. --- # SwissWeather Support swissweather workflows with clear steps and best practices. -## When to Use +## Instruction +- Fetch current weather conditions and multi-day forecasts for Swiss cities, valleys, and high-altitude alpine regions. +- Analyze specialized Swiss meteorological phenomena, including Föhn wind patterns, snow stability, and avalanche risk levels. +- Utilize the Swiss national weather network (MeteoSwiss) to identify microclimate variations across the Alps. +- Evaluate the impact of upcoming weather events on Swiss transport infrastructure, alpine agriculture, and outdoor activities. +- Provide step-by-step guidance for accessing local weather station telemetry and high-resolution precipitation radar. +- Establish a monitoring workflow for extreme Swiss weather events like heavy snowfall, flooding, or localized storms. -- You need help with swissweather. -- You want a clear, actionable next step. +## When to Use +- When needing precise local weather forecasts and specialized alpine metrics for Switzerland. +- When monitoring safety-critical weather conditions such as avalanche risk or high-wind events in Swiss cantons. +- When integrating official Swiss meteorological data into operational logistics or environmental research. ## Output - -- Summary of goals and plan -- Key tips and precautions +- A localized Swiss weather briefing with forecasts, current metrics, and active warnings. +- Technical summaries of alpine-specific weather indicators like snow depth and wind trajectories. +- Actionable steps for interpreting Swiss meteorological radar and station networks. diff --git a/skills/Research/tavily-web/SKILL.md b/skills/Research/tavily-web/SKILL.md index 72994d9a..2153ff74 100644 --- a/skills/Research/tavily-web/SKILL.md +++ b/skills/Research/tavily-web/SKILL.md @@ -1,8 +1,12 @@ --- -category: Research id: tavily-web name: Tavily Web -description: Web search, content extraction, crawling, and research capabilities using Tavily API. +description: Web search, content extraction, crawling, and real-time research capabilities using the Tavily API. +category: Research +requires: [] +examples: + - Search the web for recent research papers on room-temperature superconductors. + - Crawl this URL and extract the main content as structured markdown. --- # tavily-web @@ -15,10 +19,7 @@ Web search, content extraction, crawling, and research capabilities using Tavily - When extracting content from URLs - When crawling websites -## Installation -```bash -npx skills add -g BenedictKing/tavily-web -``` + ## Step-by-Step Guide 1. Install the skill using the command above