AI & ML

holobiomicslab Skill

Use when when you have preprocessed molecular graph data (node and edge tensors representing atoms and bonds) and need to train a regression model to predict a continuous molecular property (e.g., LC retention time).

holobiomicslab Skill

Use when your goal is to assess whether a pretrained NMR2Struct model trained on molecules ≤19 heavy atoms can generalize to larger, more complex molecules, or whether accuracy degrades significantly.

holobiomicslab Skill

Use when you have trained a new machine learning model for chemical formula or adduct assignment from MS/MS spectra and need to assess whether it offers genuine performance gains over established baselines. Use it specifically when you have access to ground-truth annotations (e.

holobiomicslab Skill

Use when you have constraint-based metabolic models with integrated multi-omics constraints (transcriptomics via Reaction Activity Scores, extracellular flux ratios via YSI bioanalyzer or LC-MS, nutrient availability bounds), and you need to determine whether differential enzyme expression.

holobiomicslab Skill

Use when you have intracellular metabolomics abundance data (measured metabolite concentrations) from multiple biological replicates collected from two or more cell lines or conditions, and you need to create a normalized, cell-line-level metabolite dataset before computing Reaction Propensity.

holobiomicslab Skill

Use when you have a 1D 1H NMR spectrum represented as chemical shift vs. intensity values, a corresponding list of detected peak positions, and you need to assign metabolite identities to those peaks.

holobiomicslab Skill

Use when after generating cross-spectrum negative examples via precursor m/z windowing and before training a rescore model (e.g., Siamese architecture in FIDDLE v2.0.0).

holobiomicslab Skill

Use when after standardizing link scores (strain correlation and IOKR) across all potential GCF-MF pairs in a metabologenomics dataset, perform significance testing to determine whether validated links show statistically distinguishable score distributions from the background.

holobiomicslab Skill

Use when you have raw molecular datasets (e.g., METLIN-CCS, CCSBase) with SMILES strings, 3D coordinates, adduct information, and ground-truth collision cross section labels, and you need to format them for GNN training and held-out test evaluation with consistent standardization.

holobiomicslab Skill

Use when you have a trained deep learning model and want to quantify prediction uncertainty for each input pair or decision point. Use this when you need to identify low-confidence predictions (high IQR) and filter them out to reduce error in specific score ranges (e.

holobiomicslab Skill

Use when after RAMClustR clustering and do.findmain molecular weight inference have been completed on XCMS-detected metabolomics features.

holobiomicslab Skill

Use when you have raw or minimally processed FT-ICR MS peak tables in Formularity .

holobiomicslab Skill

Use when you have a trained regression model (e.g., a neural network or similar predictor) and a held-out test set with ground-truth continuous labels, and you need to measure whether the model's predictions match the true values.

holobiomicslab Skill

Use when you have a trained conformer-based peak-picking model (in ONNX format) and need to apply it to chromatographic or ion-mobility mass spectrometry data (TransitionGroup objects) to detect peak boundaries and apex positions, generating TransitionGroupFeature records for downstream analysis or.

holobiomicslab Skill

Use when when you have paired MS/MS spectra with known structural similarity labels (Tanimoto scores from molecular fingerprints) and need to predict structural similarity for new spectrum pairs faster than fingerprint-based methods, or when you want to assess model prediction confidence per.

holobiomicslab Skill

Use when you have preprocessed tandem mass spectrometry spectra converted into a bag-of-fragments representation (with fragments and neutral losses extracted and noise filtered) and your goal is to discover recurring fragmentation patterns or substructures across a large spectral dataset without.

holobiomicslab Skill

Use when you have computed raw or standardised correlation scores (or other link-ranking metrics) for all possible GCF-MF pairs in a dataset and want to verify that validated links (those with known strain co-occurrence or experimental confirmation) are significantly enriched at higher score values.

holobiomicslab Skill

Use when you have a sequence-to-structure prediction task where: (1) inputs are token sequences or embeddings representing molecular fragments or spectral data; (2) outputs are structured molecular representations (adjacency matrices for connectivity, formula vectors);

holobiomicslab Skill

Use when when you have raw MS/MS spectra in MGF or mzML/mzXML formats and need to feed them into Casanovo or similar transformer-based de novo sequencing models.

holobiomicslab Skill

Use when after training or loading a pre-trained deep learning model that produces high-dimensional embeddings (e.g., 200-dimensional vectors from MS2DeepScore). Use this skill when you have a set of spectra with known chemical class annotations (e.

holobiomicslab Skill

Use when you have a baseline GNN model trained on a molecular property prediction task (e.

holobiomicslab Skill

Use when you have raw or semi-processed MS/MS spectra in MSP format (e.g., from GNPS, Orbitrap instruments) and need to feed them into MSBERT or similar transformer-based embedding models for library matching, clustering, or similarity scoring.

holobiomicslab Skill

Use when you have MS/MS spectra with unknown precursor m/z values and need to assign the most likely chemical formula and adduct type (e.g., [M+H]+, [M+Na]+, [M+K]+) in a de novo setting where spectrum database matching is unavailable or undesirable.

holobiomicslab Skill

Use when when adopting a mass spectrometry data processing tool (e.g., LipidMatch) and needing to verify whether your specific instrument platform (vendor + model) and acquisition mode combination (targeted, ddMS2-topN, AIF, direct infusion, imaging) have been formally validated.

holobiomicslab Skill

Use when a deep learning model for molecular structure prediction (e.g., NMR2Struct) has been trained and evaluated on a limited molecular size range (e.

tools-only Bundle

Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.

tools-only Bundle

Interact with Google Chat - list spaces, send messages, read conversations, and manage DMs. Use when user asks to: send a message on Google Chat, read chat messages, list chat spaces, find a chat room, send a DM, or create a new chat space. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.

tools-only Bundle

Export RepoPrompt context for external LLM review (ChatGPT, Claude web, etc.). Use when you want to review code or plans with an external model. Triggers on /flow-next:export-context.

tools-only Bundle

Find and identify the CBasePlayerPawn_CommitSuicide function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or server.so to locate the CommitSuicide function by searching for the "bot_kill" command string, tracing to its handler, and identifying the CommitSuicide vfunc call in the kill loop.

tools-only Bundle

Generate and validate unique byte signatures for instructions containing a virtual-function offset using IDA Pro MCP. Use this skill when you need a signature for an instruction like call qword ptr [rax+538h], where the vfunc offset (0x538) must be explicitly fixed in the first instruction bytes. Triggers: vfunc offset signature, signature for vfunc offset, virtual function offset signature, call [reg+offset] signature

tools-only Bundle

Find and identify the CPhysBox_Use_PatchCaller patch in CS2 binary using IDA Pro MCP. This patch changes the third argument of the sub_XXXXXXXX call inside CPhysBox_Use from inputdata->pCaller to this (the CPhysBox entity pointer), so the caller is the physbox itself. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate and patch the caller argument. Trigger: CPhysBox_Use patch caller, CPhysBox_Use_PatchCaller, physbox use caller patch

tools-only Bundle

Write function analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after completing function identification and signature generation to persist the results in a standardized YAML format. For virtual functions with known vtable index, use write-vfunc-as-yaml instead.

tools-only Bundle

Find and identify the CBaseTrigger_PassesTriggerFilters virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or server.so to locate the PassesTriggerFilters function by first finding CBaseTrigger_StartTouch and extracting the first virtual call offset from its decompiled code.

tools-only Bundle

Overview of all benchmarks supported by mcpbr for evaluating MCP servers and AI agent capabilities across software engineering, code generation, math reasoning, knowledge, tool use, and security.

tools-only Bundle

Inbox management agent that removes obvious debris

tools-only Bundle

Write struct member offset analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after identifying a struct member offset and optionally generating a signature for it to persist the results in a standardized YAML format.