Search: "networks"

Processes, cleans, compares, and searches tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral similarity, library matching, score matrices, and molecular-similarity networks. Use pyopenms instead for LC-MS feature detection or proteomics pipelines.

Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.

Creates, analyzes, and visualizes complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks (random, scale-free, small-world), reading/writing graph file formats, or drawing network topologies. Common applications include social, biological, transportation, and citation networks.

Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

A modular framework for building performant networks, pushing the boundary of today in order to build the apps of tomorrow.

Use this skill when an agency operator wants the partner roster for a brand split by relationship status, plus the active partners who have gone quiet so they can be chased or reactivated. The output is a read-only worklist; the outreach itself happens outside this skill. How a partner's relationship status is read depends on the network. Some advertiser networks report it through the API. Awin does not: its advertiser API returns only already-joined publishers with no relationship-status field, so every Awin row maps to unknown and neither the roster split nor the dormant worklist can be derived from the API. Awin's roster and per-partner relationship status are read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Who's gone quiet on Acme?", "Acme's partner roster health", "Which partners have gone dormant on [brand]?", "Build a reactivation list for Acme", "Show me Acme's roster by status".

Premium pack. Use this to prepare a full quarterly business review for a brand across its affiliate networks: quarter-over-quarter performance, top and declining partners, reversal and pending exposure, and a narrative with recommended actions. Trigger on: "prep the QBR for Acme", "quarterly business review for this brand", "build the Q3 review deck notes".

Use this skill to spot week-over-week anomalies across an agency's portfolio of brands and networks — revenue drops, reversal spikes, dead links, publishers that fell out of the top 10. Designed to run on a schedule via Claude's own scheduling so the agency learns about problems before clients do. Trigger on: "Are there any problems with the affiliate programmes this week?", "Anomaly check", "Anything weird in the affiliate data?".

Use this skill when the user wants a health check of their configured affiliate networks — auth, reachability, supported operations. Trigger on: "is my affiliate setup working", "check my affiliate networks", "are all my networks responding", "network health".

Use this skill when the user asks how much they have earned across their configured affiliate networks, or wants a consolidated period summary. Trigger on: "show my affiliate earnings", "what did I earn last month?", "earnings report", "how much have I made?".

Use this skill when an agency operator wants the list of partner applications waiting on a decision for a brand: who has applied to the programme and is sitting in the pending queue. The output is a read-only queue; the approve or decline happens in the network dashboard. How the queue is read depends on the network. Some advertiser networks expose application status through the API. Awin does not: its advertiser API returns only joined publishers with no application status, so Awin's pending queue is read from the operator's own authenticated Awin session (new UI, app.awin.com) through Claude-in-Chrome, read-only. Awin Classic (ui.awin.com) accounts have no equivalent and are detected and stopped. Trigger on: "Which partner applications are pending on Acme?", "Acme's application queue", "Who's waiting for approval on [brand]?", "Show me pending partners for Acme".

Use this skill when an agency operator asks for a performance report for a single brand across one or more advertiser-side affiliate networks: per-publisher rollup, status split, and period-over-period delta. This is also the one reporting workflow behind the cadence deliverables an account manager ships: the daily snapshot, the weekly client note, the month-close report, and the quarterly business review (QBR). Match the output profile to the cadence the user asks for. Trigger on: "How is Acme performing this quarter?", "Show me the programme report for [brand]", "[brand] performance last month", "Which publishers are driving Acme's revenue?", "Acme's weekly report", "How did Acme do this week?", "Acme's month-end report", "Prepare Acme's QBR", "Build the Q2 review for [brand]".