agentskills.codes
TD

tda-experiment

by stephendorCodingSource

Standardizes the creation of TDA experiment modules.

Data AnalysisMachine LearningPython

Install

mkdir -p .claude/skills/tda-experiment && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15834" && unzip -o skill.zip -d .claude/skills/tda-experiment && rm skill.zip

Installs to .claude/skills/tda-experiment

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.

Scaffold a new TDA experiment module in the correct domain package
66 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Ask the user for domain, experiment name, topological method, and hypothesis
  • →Determine the correct target directory for the experiment file
  • →Read existing experiment files to understand established patterns
  • →Create a new experiment file following a template structure
  • →Create a corresponding test stub with at least one smoke test
  • →Report back the created files, research question, and next steps

How it works

The skill gathers user input, determines file locations, references existing patterns, generates experiment and test files based on templates, and reports the outcome.

Inputs & outputs

You give it
User input for domain, experiment name, topological method, and hypothesis
You get back
New experiment file and corresponding test stub, with a report of created files and research question

When to use tda-experiment

  • →Scaffold new financial experiment
  • →Create topology research module
  • →Setup new TDA test file

About this skill

Skill: tda-experiment

Scaffold a new TDA experiment for this research project.

Your task

  1. Ask the user for:

    • Which domain: financial_tda, poverty_tda, or trajectory_tda
    • A short experiment name (snake_case, e.g. sector_crisis_2024)
    • What topological method to use (Rips, Alpha, Mapper, Morse-Smale, etc.)
    • What the hypothesis or research question is

  2. Determine the correct target directory:

    • financial_tda/experiments/<name>.py for financial experiments
    • trajectory_tda/scripts/<name>.py for trajectory scripts
    • poverty_tda/analysis/<name>.py for poverty analysis

  3. Read one or two existing experiment files in that domain to understand the established patterns, imports, and structure.

  4. Create the new experiment file following this template structure:

    • Module docstring with: research question, method, expected output, references
    • Typed configuration dataclass or constants section
    • load_data() function calling domain data/ modules
    • compute_topology() function calling domain topology/ modules
    • analyse() function implementing the specific analysis
    • main() function orchestrating the pipeline with logging
    • if __name__ == "__main__": block

  5. Create a corresponding test stub in tests/<domain>/test_<name>.py with:

    • At least one smoke test
    • Appropriate markers (@pytest.mark.slow if needed, @pytest.mark.integration if data-dependent)

  6. Report back: the files created, the research question captured in the docstring, and what to run next.

Key conventions to follow

  • All public functions need Google-style docstrings and type hints
  • Use pathlib.Path for all file paths
  • Use logging not print()
  • Save results to results/<domain>/ or outputs/<domain>/
  • Expose all tunable parameters (thresholds, window sizes, n_permutations) as function arguments with defaults
  • Permutation nulls: default n_permutations=1000
  • Bootstrap CI: default n_bootstrap=1000

When not to use it

  • →When the goal is not to scaffold a new TDA experiment module
  • →When the goal is not to follow specific domain packages
  • →When the goal is not to create test stubs

Limitations

  • →The skill requires user input for domain, experiment name, topological method, and hypothesis
  • →The skill creates test stubs with at least one smoke test
  • →The skill follows specific naming conventions for files and functions

How it compares

This skill automates the creation of TDA experiment modules and test stubs following specific conventions, ensuring consistency and adherence to project standards, unlike manual file creation.

Compared to similar skills

tda-experiment side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
tda-experiment (this skill)04moNo flagsIntermediate
llava79moReviewAdvanced
cocoindex610moReviewIntermediate
ai-multimodal96moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by stephendor

View all by stephendor →

tda-paper-dissemination-pack

stephendor

Use only after a TDL paper section or result set is stable — to convert it into public-facing web pages, talks, posters, slide decks, graphical abstracts, or explainer material.

00

You might also like

llava

zechenzhangAGI

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

7117

cocoindex

cocoindex-io

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge graphs, creating search indexes, or processing data streams with incremental updates.

6116

ai-multimodal

mrgoonie

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

9108

rag-implementation

wshobson

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

10101

rdkit

K-Dense-AI

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

856

pyhealth

davila7

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

351

Search skills

Search the agent skills registry