Skills

A

alterlab-imaging-data-commons

alterlab-ieu / alterlab-academic-skills

Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for AI/ML training or cancer imaging research. Part of the AlterLab Academic Skills suite.

A

alterlab-interpro

alterlab-ieu / alterlab-academic-skills

Query the EMBL-EBI InterPro REST API for protein family, domain, and functional-site annotations integrated from member databases (Pfam, PANTHER, PRINTS, SMART, SUPERFAMILY, CDD, ProSite, NCBIfam, and others). Use when predicting protein function, analyzing or comparing domain architecture, classifying a protein by family or homologous superfamily, resolving a Pfam/InterPro accession, or mapping a protein's signatures to GO terms. Not for raw UniProt entry/FASTA retrieval or AlphaFold 3D structures. Part of the AlterLab Academic Skills suite.

A

alterlab-lamindb

alterlab-ieu / alterlab-academic-skills

Manage, annotate, and trace biological data with LaminDB, an open-source FAIR data framework that makes datasets queryable, versioned, and reproducible. Use when registering or querying biological datasets (scRNA-seq, spatial, flow cytometry), validating and curating data against ontologies (genes, cell types, diseases, tissues), tracking data lineage and computational workflows, building data lakehouses, or wiring integrations with Nextflow, Snakemake, W&B, or MLflow. Part of the AlterLab Academic Skills suite.

A

alterlab-metabolomics-wb

alterlab-ieu / alterlab-academic-skills

Access the NIH Metabolomics Workbench via its REST API (4,500+ public studies), querying metabolites, RefMet standardized nomenclature, MS/NMR data, m/z mass searches, and study metadata. Use when retrieving public metabolomics study data, standardizing metabolite names with RefMet, running m/z lookups, or doing biomarker discovery. Part of the AlterLab Academic Skills suite.

A

alterlab-molfeat

alterlab-ieu / alterlab-academic-skills

Featurizes molecules for machine learning with molfeat — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, pharmacophore and shape descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, CheMeleon) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.

A

alterlab-networkx

alterlab-ieu / alterlab-academic-skills

Creates, analyzes, and visualizes complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing topologies — applicable to social, biological, transportation, citation, and any pairwise-relationship networks. This is classical graph analytics, not deep learning — for training graph neural networks (GCN/message passing, node/edge/graph classification on Cora-style data) use alterlab-torch-geometric instead. Part of the AlterLab Academic Skills suite.

A

alterlab-neuropixels

alterlab-ieu / alterlab-academic-skills

Analyze Neuropixels 1.0/2.0 extracellular electrophysiology with SpikeInterface — load SpikeGLX/Open Ephys recordings, preprocess and motion-correct, run Kilosort4 spike sorting, compute quality metrics, apply Allen/IBL curation, and do AI-assisted visual inspection. Use when working with neural recordings, spike sorting, or extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation. Part of the AlterLab Academic Skills suite.

A

alterlab-pathml

alterlab-ieu / alterlab-academic-skills

Run full computational-pathology workflows with PathML — whole-slide-image (WSI) analysis across 160+ slide formats, multiplexed immunofluorescence (CODEX, Vectra, MERFISH), nucleus segmentation/classification (HoVer-Net, HACTNet), tissue- and cell-graph construction, HDF5 dataset management, and deep-learning model training on pathology data. Use when the user builds end-to-end deep-learning pathology pipelines, analyzes multiplexed or spatial-proteomics slides, or segments nuclei. For lightweight H&E slide preprocessing, tissue masking, or plain Random/Grid/Score tile extraction prefer alterlab-histolab instead. Part of the AlterLab Academic Skills suite.

A

alterlab-pennylane

alterlab-ieu / alterlab-academic-skills

Trains and differentiates quantum circuits with PennyLane, a hardware-agnostic quantum machine-learning framework with automatic differentiation and PyTorch/JAX integration. Use when training quantum circuits via gradients (parameter-shift, backprop, adjoint), building hybrid quantum-classical models or quantum neural networks, or running differentiable variational algorithms (VQE, QAOA). For IBM Quantum hardware and Qiskit Runtime prefer alterlab-qiskit; for Google Quantum AI or NISQ circuits prefer alterlab-cirq; for open-system Lindblad/master-equation dynamics prefer alterlab-qutip. Part of the AlterLab Academic Skills suite.

A

alterlab-pymc

alterlab-ieu / alterlab-academic-skills

Bayesian modeling and probabilistic programming with PyMC 6 and ArviZ 1.x — hierarchical models, MCMC (NUTS via PyMC, nutpie, NumPyro, or BlackJAX), variational inference, PSIS-LOO model comparison, and prior/posterior predictive checks. Use when fitting Bayesian or hierarchical models, estimating posteriors and credible intervals, diagnosing divergences, R-hat, or ESS, running probabilistic inference, or comparing models with LOO (WAIC was removed from ArviZ 1.x). Part of the AlterLab Academic Skills suite.

A

alterlab-pysam

alterlab-ieu / alterlab-academic-skills

Read and write genomic alignment and variant files in Python with pysam (htslib bindings) — SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, plus region extraction and per-base coverage/pileup. Use when scripting NGS data-processing pipelines that parse, filter, index, or compute coverage over BAM/CRAM/VCF files. Part of the AlterLab Academic Skills suite.

A

alterlab-rdkit

alterlab-ieu / alterlab-academic-skills

Provides the RDKit cheminformatics toolkit for low-level, fine-grained molecular primitives — SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure/SMARTS search, 2D/3D coordinate generation, similarity, and reaction handling. Use when custom sanitization, specialized fingerprint or descriptor algorithms, reaction enumeration, or conformer generation demand direct API control; for a high-level pandas-friendly wrapper over RDKit prefer alterlab-datamol, and for turning molecules into ML feature vectors prefer alterlab-molfeat. Part of the AlterLab Academic Skills suite.

A

alterlab-scanpy

alterlab-ieu / alterlab-academic-skills

Run the standard single-cell RNA-seq analysis pipeline with Scanpy on AnnData — QC filtering, normalization, dimensionality reduction (PCA, UMAP, t-SNE), Leiden/Louvain clustering, marker/differential expression, PAGA trajectories, and plotting. Use when analyzing scRNA-seq data through clustering, cell-type annotation, DE, or pseudotime workflows; for building or reading the .h5ad data structure itself (layers, obs/var, concatenation, backed mode) prefer alterlab-anndata instead, and for RNA velocity from spliced/unspliced counts prefer alterlab-scvelo instead. Part of the AlterLab Academic Skills suite.

A

alterlab-scvelo

alterlab-ieu / alterlab-academic-skills

Run RNA velocity analysis with scVelo on single-cell RNA-seq data — estimate cell-state transitions from spliced/unspliced mRNA dynamics, infer trajectory direction, compute latent time, and identify driver genes. Use when adding directionality to trajectories or studying differentiation dynamics from spliced/unspliced layers (velocyto/STARsolo output); for the general QC, clustering, UMAP, and differential-expression analysis pipeline prefer alterlab-scanpy instead, and for .h5ad data-structure I/O and layer wrangling prefer alterlab-anndata instead. Part of the AlterLab Academic Skills suite.

A

alterlab-stable-baselines3

alterlab-ieu / alterlab-academic-skills

Trains single-agent reinforcement learning agents with Stable-Baselines3 — PPO, SAC, DQN, TD3, DDPG, and A2C behind a scikit-learn-like API. Use for standard single-agent RL experiments, quick prototyping, well-documented algorithm implementations on Gymnasium environments, or adding callbacks and evaluation. For high-throughput parallel training, multi-agent systems, or custom vectorized environments prefer alterlab-pufferlib. Part of the AlterLab Academic Skills suite.

A

alterlab-string-db

alterlab-ieu / alterlab-academic-skills

Query the STRING API for protein-protein interactions (59M proteins, 20B+ interactions across 12,500+ organisms), building interaction networks, discovering functional partners, and running GO/KEGG/Pfam enrichment on protein lists. Use when constructing a protein-protein interaction network, expanding from seed proteins to functional partners, or running PPI-based enrichment for systems biology; for curated metabolic pathway maps and reactions prefer alterlab-kegg, and for protein sequences, annotations, or accession ID mapping prefer alterlab-uniprot instead. Part of the AlterLab Academic Skills suite.

A

alterlab-timesfm

alterlab-ieu / alterlab-academic-skills

Forecasts time series zero-shot with Google's TimesFM foundation models — TimesFM 2.5 (200M, Apache-2.0 weights; ForecastConfig API, XReg covariates) and TimesFM 3.0 (~330M, multivariate with native past/future covariates; non-commercial weights) — producing point forecasts and quantile prediction intervals from CSV/DataFrame/array inputs, with a preflight system checker for RAM/GPU. Use when forecasting univariate or multivariate series (sales, sensors, energy, vitals, weather) without training a custom model, batch-forecasting many series, or flagging anomalies against forecast intervals. Part of the AlterLab Academic Skills suite.

A

alterlab-torchdrug

alterlab-ieu / alterlab-academic-skills

Builds PyTorch-native graph neural networks with TorchDrug for molecules and proteins, exposing custom GNN architectures, task/dataset abstractions, molecular generation, retrosynthesis planning, and knowledge-graph reasoning. Use when a project specifically needs TorchDrug's datasets and tasks — GearNet protein-structure models, center-identification/synthon-completion retrosynthesis, or Hetionet knowledge-graph baselines. TorchDrug has had no release since 0.2.1 (July 2023) and needs Python < 3.11, so for new custom GNN work prefer alterlab-torch-geometric, and for ready-made featurizers, MoleculeNet benchmarks, and pre-trained models prefer alterlab-deepchem. Part of the AlterLab Academic Skills suite.

A

alterlab-transformers

alterlab-ieu / alterlab-academic-skills

Loads, runs, and fine-tunes pretrained models with Hugging Face Transformers v5 (PyTorch-only) — pipeline() inference for chat-model text generation, text classification, NER, zero-shot, speech recognition, image classification, object detection, and image-text-to-text VLMs; AutoModel/AutoTokenizer loading with dtype, device_map and bitsandbytes quantization; generate() decoding control; and Trainer fine-tuning with optional PEFT/LoRA. Use when running inference with a Hugging Face Hub checkpoint, fine-tuning BERT/ModernBERT/Qwen-style models on a custom labelled dataset, controlling generation (sampling, beam search, streaming, chat templates), or porting v4 code (torch_dtype, removed summarization/translation/QA pipelines, TF/Flax) to v5. Part of the AlterLab Academic Skills suite.

A

alterlab-umap

alterlab-ieu / alterlab-academic-skills

Nonlinear dimensionality reduction with UMAP — fast manifold learning for 2D/3D visualization, clustering preprocessing (e.g., HDBSCAN), and supervised or parametric UMAP. Use when projecting high-dimensional data to low dimensions for visualization, embedding generation, or as a preprocessing step before clustering. Part of the AlterLab Academic Skills suite.

A

alterlab-uniprot

alterlab-ieu / alterlab-academic-skills

Provide direct REST API access to UniProt (Swiss-Prot/TrEMBL) for protein sequence searches, FASTA retrieval, functional annotations (GO terms, domains), and cross-database ID mapping. Use when looking up a protein entry, fetching a protein FASTA sequence, or mapping accessions between databases over raw HTTP/REST; for EXPERIMENTAL 3D structures prefer alterlab-pdb, for AI-PREDICTED 3D structures prefer alterlab-alphafold-db, for protein-protein interaction networks prefer alterlab-string-db, and for Python workflows spanning many databases prefer alterlab-bioservices instead. Part of the AlterLab Academic Skills suite.

A

alterlab-usfiscaldata

alterlab-ieu / alterlab-academic-skills

Queries the U.S. Treasury Fiscal Data API across 50+ datasets and roughly 180 data tables (no API key required) for federal financial data on national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics. Part of the AlterLab Academic Skills suite.

A

alterlab-uspto

alterlab-ieu / alterlab-academic-skills

Access USPTO patent and trademark data through the Open Data Portal (ODP) APIs — Patent File Wrapper search, examination history (the PEDS successor), continuity, assignments, office actions, PTAB decisions — and trademark status via TSDR. Use when searching patents or trademarks, conducting prior art searches, retrieving patent examination or assignment records, or doing intellectual property (IP) analysis. Part of the AlterLab Academic Skills suite.

A

alterlab-zinc-db

alterlab-ieu / alterlab-academic-skills

Access the ZINC database of 230M+ commercially available (purchasable) compounds, searching by ZINC ID or SMILES, running similarity searches, and downloading 3D-ready structures. Use when assembling a compound library for virtual screening, finding purchasable analogs, or obtaining docking-ready 3D structures for drug discovery. Part of the AlterLab Academic Skills suite.

A

analytics-tracking

kimny1143 / claude-code-template

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.

Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking plan from scratch, auditing existing analytics for gaps or errors, debugging missing events, or setting up GTM. Trigger keywords: GA4 setup, Google Tag Manager, GTM, event tracking, analytics implementation, conversion tracking, tracking plan, event taxonomy, custom dimensions, UTM tracking, analytics audit, missing events, tracking broken. NOT for analyzing marketing campaign data — use campaign-analytics for that. NOT for BI dashboards — use product-analytics for in-product event analysis.

A

aso-analysis

appfollow / appfollow-ai-toolkit

Analyze ASO performance for an app or collection — tracked-keyword positions and (gate-iv-gated) trends, category-rank trend, keyword opportunities with competitor context, an interactive add-keyword loop (the only write path), and honest metadata suggestions. Emits a structured findings.json plus a self-contained HTML report. Trigger on "ASO report", "keyword rankings", "keyword opportunities", "how do we rank for <keyword>", "suggest keywords to add".

A

autodiscovery

allenai / asta-plugins

Create, configure, and monitor AutoDiscovery runs — either via the hosted service (`asta autodiscovery`) or via the local CLI (`asta-autodiscovery`). Use when the user asks about their runs, experiments, discoveries, wants to check status, or wants to start a new discovery run.

A

azure-data-tables-java

sickn33 / agentic-awesome-skills

Build table storage applications using the Azure Tables SDK for Java. Works with both Azure Table Storage and Cosmos DB Table API.

B

bingx-trade-review

bingx-api / api-ai-skills

Use when the user asks for BingX perpetual futures trade review, performance analysis, PnL summary, win rate, trade journal, recent trading performance, trade tags, reflections, or weekly PnL. It fetches trade history from bingx-swap-account, computes statistics, generates local charts, and supports custom tags and review notes.

C

campaign-roi-calculator

archive-dot-com / creator-marketing-skills

Calculate influencer campaign ROI and build a leadership-ready narrative summary from raw performance data. This skill should be used when calculating ROI for a creator campaign, building a campaign performance report for leadership, turning raw influencer metrics into an executive summary, computing CPM CPE ROAS and EMV for a creator program, summarizing campaign spend versus revenue for a stakeholder meeting, proving influencer marketing ROI to a CMO or VP, creating a campaign wrap report with financial metrics, or comparing influencer channel efficiency against paid social. For setting KPI targets before a campaign launches, see performance-benchmark-setter. For tracking creator posting compliance, see creator-posting-compliance-tracker. For full end-of-campaign reporting with qualitative analysis, see post-campaign-creator-scorecard. For building UTM links to enable attribution, see utm-parameter-builder.

C

causal-inference-mixtape

brycewang-stanford / auto-empirical-research-skills

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.

C

cdata-cli-python

cdatasoftware / cli-skills

Use when writing Python application code that connects to a data source through a CData driver — after the connection and SQL have been validated with the cdata-cli discovery skill. Covers mapping the language to the CData Python Connector edition, downloading the connector wheel from CData's Python repository, activating its license, and connecting via DB-API 2.0 (cdata.<source>.connect). This is the Python build-phase companion to cdata-cli; invoke it whenever the target application language is Python (Salesforce, Snowflake, Jira, Gmail, etc.).

C

chart-implementation

motormetrics / motormetrics

Create interactive charts for car registration and COE data visualization using Recharts. Use when adding new chart types, fixing chart bugs, or implementing data visualizations.

C

cloud-azure-sql

partme-ai / full-stack-skills

Provides comprehensive guidance for Azure SQL Database including database creation, configuration, security, and Azure SQL management. Use when the user asks about Azure SQL, needs to create Azure SQL databases, configure Azure SQL, or manage Azure database services.

C

cloud-huawei-rds

partme-ai / full-stack-skills

Provides comprehensive guidance for Huawei Cloud RDS including database creation, configuration, backups, and RDS management. Use when the user asks about Huawei Cloud RDS, needs to create RDS databases, configure RDS, or manage Huawei Cloud database services.

C

community-kpi-dashboard

gtmagents / gtm-agents

Measurement system tracking engagement, health, and business impact of

C

create-knowledgebase

bolna-ai / skills

Create, list, inspect, and delete Bolna knowledge bases from PDF files or URLs, including multilingual retrieval settings, chunking, overlap, similarity top k, processing status, rag_id and vector_id usage. Use when a voice agent needs RAG over FAQs, policies, product docs, or web pages.

C

creative-analyzer

dengineproblem / agents-monorepo

Expert in Facebook Ads creative analysis. Use for evaluating creative performance, Risk Score, A/B testing, and improvement recommendations.

C

crypto-price

evgyur / crypto-price

Router skill for crypto token price + candlestick chart generation via Hyperliquid/CoinGecko.

D

data-profiler

majesticlabs-dev / majestic-marketplace

Generate data profiles with column stats, correlations, and missing patterns for DataFrames. Use for EDA and data discovery.

D

database-architecture

troykelly / claude-skills

MANDATORY when designing schemas, writing migrations, creating indexes, or making architectural database decisions - enforces PostgreSQL 18 best practices including AIO, UUIDv7, temporal constraints, and modern indexing strategies

D

dataset-curation

fcakyon / phd-skills

Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like \"dataset bias\"、\"stratified sample\"、\"class imbalance\"、\"data distribution\"、\"fairness analysis\", or \"ethical review\".

D

dby-api

zizhanovo / doubaoya-community

Doubaoya (doubaoya/本鸭) new-media data package: use DOUBAOYA_API_KEY to fetch live data for online fact-checking. Data only: body copy goes to dby-write, banned-word checks to dby-banned-words, formatting and drafts to dby-publish; ask dby when unsure. Finished images (image generation/editing/assets/key visuals) go to dby-image; this package only provides **reference data** for covers and titles. Triggers: Xiaohongshu: search/crawl/posts/creation/topics/titles/covers/rankings/lists/trending/daily/weekly/weekly ranking/TOP/popular notes/viral notes/note lookup; WeChat Official Account: data/crawler/titles/covers/rankings/lists/viral posts/dark horses/benchmarks; Douyin: search/data/comments/realtime search/comprehensive search; WeChat Channels: AI/daily/viral/topics; viral: articles/titles/covers/structure/imitation/review/rankings/topics/note discovery; topics: breakdown/inspiration/materials/angles/signals; covers: inspiration/reference/formulas/design/topics; titles: inspiration/optimisation/formulas/generation; account profile/account checkup/account health/account post list; benchmarks: analysis/posts/recommendations/matrix/accounts/write after; competitors: accounts/diagnosis/tracking/post review; going global: topics/viral/daily/traffic trends; notes: benchmark/breakdown/generation/topics; content: creation/inspiration/going global; cross-platform: topics/analysis/trending searches; hot topics: scan/lists, today's hot topics/comprehensive hot topics/chase hot topics/ride hot topics/leveraged topics/find topics/midline topics/short-video topics/all-network trending searches/trending keywords/all-network trending lists/aggregated trending lists/trending TOP10/daily list/today's viral/this week's viral/recent viral/all-platform viral/low-follower viral/ordinary-creator viral/search Douyin viral; low-follower high-likes/dark horse notes/dark horse accounts/top accounts/popular accounts/similar accounts/benchmark accounts/secondary-account playbook/cold-start benchmarks/account launch reference/Official Account diagnosis/batch diagnosis/throttled/readership dropped/weekly trends/last 30 days posts/latest posts/most liked/steady growth/growth list/readership growth/growth-rate ranking/traffic direction/heat index/chase traffic/chase updates/topic research/see trending content in a niche; high-CTR titles/make titles; check sources/citation sources/online search/online verification/Doubao search/social media sentiment/sentiment monitoring/user needs/comment analysis/comment trends/read comments/scrape comment sections; parse links/link parsing/post details/scrape articles/scrape Douyin posts/write Xiaohongshu in the same style/find benchmark notes/popular articles/batch crawl Official Accounts/watch Official Accounts/subscribe to Official Accounts/what an Official Account posted; AI WeChat Channels/Xiaohongshu Douyin Official Accounts/culture & tourism/short dramas/niche daily reports/what is being pushed every day/realtime data

D

degenerate-input-filtering

jaechang-hits / sciagent-skills

Filter degenerate, uninformative inputs before statistical tests: single-sequence alignments, empty files, constant features, zero-variance inputs, all-NaN columns. See nan-safe-correlation for NaN-aware correlation; statistical-analysis for test guidance.

D

develop-contribution

vincenzoimp / academic-research-skills

Use when creating a new contribution (analysis, experiment, dataset, software, reproduction) or regularizing a draft folder into badge compliance with its LaTeX report.

D

django-orm-query-optimization

lvtd-llc / skills

Optimize Django ORM query loading by fixing N+1 queries, duplicate related-object queries, over-fetching, serializer/template query loops, and inappropriate select_related, prefetch_related, only, or defer usage. Use when a Django page, API, admin view, template, serializer, or queryset issues too many queries or loads more model data than needed.

D

drugbank-database-access

jaechang-hits / sciagent-skills

Parse local DrugBank XML for drug info, interactions, targets, and properties. Search by ID/name/CAS, extract DDIs with severity, map targets/enzymes/transporters, compute SMILES similarity. Primary via local XML; REST API rate-limited (3k/month dev). For live bioactivity use chembl-database-bioactivity; for compound properties use pubchem-compound-search.

D

duckdb

tondevrel / scientific-agent-skills

An analytical in-process SQL database management system. Designed for fast analytical queries (OLAP). Highly interoperable with Python's data ecosystem (Pandas, NumPy, Arrow, Polars). Supports querying files (CSV, Parquet, JSON) directly without an ingestion step. Use for complex SQL queries on Pandas/Polars data, querying large Parquet/CSV files directly, joining data from different sources, analytical pipelines, local datasets too big for Excel, intermediate data storage and feature engineering for ML.

F

feedback-analysis

appfollow / appfollow-ai-toolkit

Analyze app or collection feedback over a window — KPIs with prev-window deltas, rating/volume/sentiment trends, anomaly callouts, and ranked top bugs and feature requests — then emit a structured findings.json plus a self-contained HTML report. Read-only (never writes). Trigger on “feedback report”, “how are our reviews”, “what are users complaining about”, “review trends for <app>”, or “what are our testers saying” (Google Play testing feedback).

Model Fine-tuning Service. LLM LoRA/QLoRA fine-tuning. 7B/13B model fine-tuning. Stable Diffusion LoRA training. Leveraging 20GB VRAM advantage. Trigger words: 微调, fine-tune, LoRA, 训练模型.

F

frame-data-chart-nyt

nexu-io / html-video

NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).

G

gempy

steadfastasart / geoscience-skills

3D structural geological modeling using implicit methods. Create geological models with faults, folds, and unconformities from surface points and orientations. Use when the agent needs to: (1) Build 3D geological models from surface contacts and orientations, (2) Model faults, unconformities, or intrusions, (3) Compute and visualize subsurface geology, (4) Export models to VTK or numpy arrays, (5) Generate gravity forward models, (6) Create cross-sections or 3D visualizations.

G

geo-visualizer

dkyazzentwatwa / chatgpt-skills

Create interactive maps with markers, heatmaps, routes, and choropleth layers. Use when visualizing geographic data, plotting locations, or creating map-based reports.

G

grafana-billing

nodnarbnitram / claude-code-extensions

Query Prometheus and Loki billing metrics from Grafana. Use when discussing observability costs, active series, ingestion rates, storage usage, or cardinality analysis.

G

grove-account-deletion

autumnsgrove / lattice

Delete a Grove tenant account via wrangler D1 commands. Use when the user wants to remove a test account, clean up after a walkthrough, or fully delete a user's data. Handles D1 CASCADE cleanup, R2 media purge, and Heartwood session invalidation.

H

helix-admin-mcp

helixdb / skills

Inspect customer database keys and perform explicitly requested, confirmation-gated Helix Cloud tenant or database-key mutations through the hosted Admin MCP server. Use only for create/delete tenant and create/revoke database-key operations. Never expose operational keys, bypass durable confirmation, or expand into excluded Cloud lifecycle surfaces.

H

histolab-wsi-processing

jaechang-hits / sciagent-skills

WSI processing for digital pathology. Tissue detection, tile extraction (random, grid, score-based), filter pipelines for H&E/IHC. For dataset prep, tile-based DL, slide QC. Use pathml for multiplexed imaging.

H

homer-motif-analysis

jaechang-hits / sciagent-skills

De novo and known TF motif enrichment in ChIP-seq/ATAC-seq peaks via HOMER. findMotifsGenome.pl finds over-represented patterns vs background; annotatePeaks.pl assigns context (TSS distance, gene, repeat). Use after MACS3 to identify enriched TFs, annotate peaks with nearest genes, and validate ChIP-seq via the target motif.

H

hypogenic-hypothesis-generation

jaechang-hits / sciagent-skills

LLM-driven hypothesis generation/testing on tabular data. Three methods: HypoGeniC (data-driven), HypoRefine (literature+data), Union. Iterative refinement, Redis caching, multi-hypothesis inference. Manual: hypothesis-generation; ideation: scientific-brainstorming.