Skip to content
Research Agent Skillsby Kalaris Labs
Install

The prompts every skill is tested on.

1,395 prompts across 283 skills. Each skill gets realistic requests it should handle, plus near misses (549 in total) that belong to another skill. The routing benchmark checks that the right skill is picked and the wrong one stays out. Suites for adapted skills were generated from SKILL.md and are marked pending review in the repository.

1,395 of 1,395
  1. should trigger13c-metabolic-flux

    “Can I get fluxes from my 13C glucose labeling data? I have MIDs for a few amino acids.”

    expects Does not fit immediately. Asks for or lists the missing inputs: the atom-mapped carbon network and its source, tracer positional isotopomer and purity, fragment carbon assignments, correction history, measurement uncertainty, and flux units or bounds. Checks steady-state evidence and offers the input template.

  2. should trigger13c-metabolic-flux

    “I'm working in E. coli on [1,2-13C]glucose and [U-13C]glucose parallel cultures, with corrected MDVs for alanine, serine and glutamate in dataset.json and model.json. Please run the contract check, then fit PPP vs glycolysis split with multistart and give me profile intervals. The fit residual is small but I want to know if the oxidative PPP flux is actually pinned down.”

    expects Runs the contract and feasibility check, then fits with multiple starts and profiles the PPP and glycolysis reactions. States that a small residual does not establish identifiability, reports profile brackets at grid resolution and local rank, and flags flat directions. Records hashes, versions and provenance, and does not invent atom maps or errors.

  3. should trigger13c-metabolic-flux

    “We fed cells labeled substrate and measured how labeling in TCA intermediates changes over 0, 30, 60, 120 seconds. Can we average the timepoints and estimate pathway rates with your flux tool?”

    expects Says that time-course labeling needs nonstationary (INST) MFA with pool sizes and initial labeling, and that averaging timepoints into this steady-state solver is invalid. Recommends a specialized INST-MFA engine, or checks whether isotopic steady state was reached at a late timepoint.

  4. “Run flux balance analysis on my genome-scale SBML model of yeast to maximize biomass, then do a knockout screen with COBRApy.”

    expects Recognizes this as COBRA-style flux balance analysis with a biomass objective and no isotope-labeling data, so it is not a 13C-MFA task. Uses a COBRA/FBA approach instead.

  5. “I have raw GC-MS chromatograms from my labeled samples. Please integrate the peaks and correct for natural isotope abundance.”

    expects Recognizes that raw peak integration and natural-abundance correction are preprocessing steps outside this skill, so it does not run the flux fit. Points to a validated MS preprocessing tool.

  6. should triggerabstract-and-title

    “Cut my 320-word abstract to 250 words for PLOS ONE and suggest three better titles.”

    expects Five-move abstract within limit with numbers kept; 5+ title candidates judged against criteria

  7. “Write the methods section describing our ELISA protocol.”

    expects Skill not used

  8. should triggeracademic-plotting

    “I need a figure for the overview section of my paper. Here's the method text: 'Our framework has a Retriever that fetches documents, a Reranker that scores them, and a Generator that writes the answer. If the Generator's confidence is low, it sends a query back to the Retriever.' Can you make the diagram?”

    expects Extracts the three components (Retriever, Reranker, Generator) and the feedback loop from the text. Picks the diagram workflow using Gemini, chooses a visual style and palette, and writes a 6-section prompt with exact labels and a dashed feedback arrow. Saves a script at figures/gen_fig_<name>.py that reads GEMINI_API_KEY from the environment, runs 3 attempts, and saves the best as a PNG.

  9. should triggeracademic-plotting

    “Plot results.csv (columns: step, method, val_loss, with 3 seeds each) as training curves for our ICML submission. 'ours' should stand out, and I need it to fit in a single column. Also the fonts look wrong when I include the PDF in LaTeX.”

    expects Uses matplotlib to make a line plot with mean and confidence bands across seeds, with 'ours' in a distinct color and an Okabe-Ito colorblind-safe palette. Sizes the figure to the ICML single-column width of 3.25 in, using a serif/Times font or usetex to fix the font problem. Exports PDF plus 300 DPI PNG and saves the script at figures/gen_fig_<name>.py.

  10. should triggeracademic-plotting

    “Here are my numbers: GPT-4 gets 86.4 on MMLU and 67.0 on HumanEval, our model gets 88.1 and 71.2, Llama-3 gets 79.3 and 62.1. What's the best way to show this in the paper, and can you draw it?”

    expects Recognizes 3 methods across 2 benchmarks and automatically chooses a grouped bar chart via matplotlib. Highlights our model with a distinct color, adds value labels, and exports PDF and PNG with a script saved under figures/.

  11. “I have a multi-panel figure for a Nature submission showing microscopy intensity with error bars and some missing data points. Can you audit it for color contrast, check whether the uncertainty display is honest, and plan the journal export (TIFF, 600 dpi)?”

    expects Should hand this to the scientific-visualization skill. It covers the figure audit, uncertainty and missing-data display, contrast review, and journal export planning for a non-ML-conference setting. It does not involve Gemini diagrams or ML-paper chart templates.

  12. should triggeracm-sigconf

    “Set up my CHI 2026 submission in acmart with anonymous review mode and CCS concepts.”

    expects acmart sigconf,review,anonymous setup, CCSXML, Description alt text, anonymization checklist

  13. near missacm-sigconf

    “Format my paper for IEEE Transactions.”

    expects Skill not used (ieee-transactions applies)

  14. should triggeradaptyv

    “How do I submit a few sequences to a cloud lab to see if they bind my target? I'm using the Python SDK.”

    expects Uses the Adaptyv Foundry SDK or API. Notes the SDK must be installed from GitHub, not PyPI. Reads ADAPTYV_API_KEY from the environment or a .env file and never hardcodes it. Chooses a screening or affinity experiment with the bli or spr method and a target. Creates the experiment in Draft, adds sequences, then submits. Warns that submission leads to a quote and costs money, so asks before confirming it.

  15. should triggeradaptyv

    “I have binders.fasta with 48 designed nanobody sequences. I want KD values against my target using SPR, and I want the quote auto-accepted so nothing waits on me. My script has `from adaptyv_sdk import FoundryClient` and it's returning a 401. Can you fix the script and set up a webhook so I get notified on status changes?”

    expects Diagnoses the 401 as a missing or invalid bearer token. Loads ADAPTYV_API_KEY from env or .env via python-dotenv instead of hardcoding it. Builds an affinity experiment with the spr method from the FASTA sequences, in the simple or rich seq format with valid amino acids. Passes webhook_url, which fires on each status transition. Flags that auto-accepting the quote commits spend and confirms with the user first. Mentions x-request-id and the ~21 day turnaround.

  16. should triggeradaptyv

    “I've designed 200 miniprotein binders computationally and want real wet-lab data on which ones actually express and how stable they are. Is there an automated lab service with an API where I can send the sequences and get melting temperatures and yields back, and how would I script that and poll for results?”

    expects Recommends the Adaptyv Bio Foundry cloud lab API or SDK. Uses thermostability (Tm) and expression experiment types, which need no target. Describes the lifecycle from Draft through QuoteSent to Done, and the results_status field (none, partial, all). Shows polling or webhooks, with auth from the ADAPTYV_API_KEY environment variable. Labels earlier computational predictions as hypotheses, not results.

  17. near missadaptyv

    “Run Boltz and AlphaFold on my antibody–antigen complex through Tamarind's API and compare the predicted structures.”

    expects Does not use the adaptyv skill. Uses the tamarind skill, since this is computational structure prediction on the Tamarind platform and not wet-lab experiment submission.

  18. near missadaptyv

    “Use ESM3 to generate variants of my protein sequence conditioned on a structure prompt, and score them with the language model's log-likelihood.”

    expects Does not use the adaptyv skill. Uses the esm skill for ESM3 generative design and scoring. No lab submission is involved.

  19. should triggeraeon

    “How do I train a fast classifier on my accelerometer windows? Shape is (500, 3, 128).”

    expects Recommends an aeon classifier such as MiniRocketClassifier or Arsenal, and confirms the data uses the (n_cases, n_channels, n_timepoints) layout. Shows a fit/predict example with a held-out split and an accuracy metric, and checks that the installed aeon is 1.x.

  20. should triggeraeon

    “I have ECG recordings in ecg_train.csv, with 1 row per beat, 140 columns for the samples and a final column for the label (normal or abnormal). I tried sklearn's RandomForest on the raw values and got about 70% accuracy. I'd like to try elastic-distance methods, and I got `ImportError: cannot import name 'ROCKETClassifier' from 'aeon.classification.convolution_based'`. Can you fix the import and compare 1-NN with DTW against a ROCKET-family model, using cross-validation?”

    expects Explains that the class names differ in aeon 1.x (e.g. RocketClassifier or MiniRocketClassifier), and checks the installed version and the real import path instead of guessing. Reshapes the CSV to (n_cases, 1, 140), compares KNeighborsTimeSeriesClassifier with DTW against a ROCKET-family model using stratified CV with fixed seeds, reports only metrics it actually computed, and notes the runtime of the DTW run.

  21. should triggeraeon

    “I have a year of minute-level vibration readings from a turbine. I need to flag the odd stretches and also work out where the machine switched operating regimes. There are no labels. What approach would you take?”

    expects Proposes unsupervised time series methods without labels: anomaly detection (e.g. matrix-profile or distance-based detectors, to find discords) and segmentation or change-point detection for the regime switches. Notes that these aeon modules are experimental, discusses windowing and normalization, and asks about or states assumptions on sampling and missing values. Validates by visual inspection or any available maintenance logs.

  22. near missaeon

    “I have 3 years of daily hospital admissions in a CSV. Give me a zero-shot 30-day forecast with prediction intervals, without training a model.”

    expects Routes to the timesfm-forecasting skill, since the request is for a zero-shot foundation-model forecast with intervals and no custom training. It does not use aeon's trained forecasters.

  23. near missaeon

    “I have a tabular dataset of patient lab values with 40 features. Tune a gradient boosting classifier with GridSearchCV and report the ROC-AUC from 5-fold cross-validation.”

    expects Uses scikit-learn for tabular classification with a Pipeline, GridSearchCV and cross-validated ROC-AUC. The data is not time series, so the aeon skill is not needed.

  24. should triggeralphagenome

    “What's the AlphaGenome AVI score for chr22:36201698:A>C?”

    expects Uses the Atlas lookup (scripts/atlas_query.py avi) on the GRCh38 SNV, reports avi_raw, Phred/quantile and top SHAP feature with the interpretation (splice, regulatory or conservation-driven), checks REF against the reference, and gives the portal link. Notes research-use-only.

  25. should triggeralphagenome

    “I have a VCF, fine_map_credible_set.vcf, with 40 SNVs from a lipid GWAS locus (hg38, intronic/intergenic). I want to know which are likely to alter enhancer activity in liver. Can you rank them and show me which tracks in HepG2 or liver drive the effect? I have an API key set in my environment, and I'm getting 'ValueError: API key not valid' on one machine.”

    expects Runs a small subset first, then ranks the SNVs with Atlas AVI (rank, don't threshold), reads top_feature attributions before the number, pulls track-level scores filtered to liver/HepG2 ontology (e.g. UBERON liver CURIE) reporting raw and quantile scores with scorer, track, gene. Explains the invalid-key error is a bad/missing key in the environment (not permissions), advises never putting the key on a command line, and attaches portal links per variant.

  26. should triggeralphagenome

    “I've got a noncoding variant in a mouse mm10-lifted region and also a 3 bp deletion in human that I suspect disrupt a promoter. How can I predict what happens to expression and chromatin accessibility computationally with DeepMind's sequence-to-function model, comparing reference and mutant tracks?”

    expects Explains the Atlas is human GRCh38 SNV-only, so indels and mouse variants need the on-demand model (score_variants.py or predict_variant). Recommends a suitable window (1 Mb default or smaller), specifying ontology CURIEs, REF-vs-ALT track plots and scoring with recommended scorers, normalising coordinates (1-based variants, build check), and reporting raw plus quantile scores while stating that no effect is a valid result.

  27. near missalphagenome

    “Is rs113993960 in CFTR pathogenic according to ClinVar, and does it meet ACMG criteria for a likely pathogenic classification?”

    expects Does not use AlphaGenome; points to a variant-evidence/ClinVar lookup skill for assertions and ACMG framing, since AlphaGenome is only one evidence line and not a clinical tool.

  28. near missalphagenome

    “I have GRCh37 coordinates for a list of SNPs and need to lift them over to hg38 and normalise the indels before anything else.”

    expects Handles coordinate conversion and normalisation with a genomic-coordinates tool, not AlphaGenome scoring.

  29. “I have linearity data for my HPLC assay, r² is 0.999. Is that enough to say the calibration is linear?”

    expects Says r² is not evidence of linearity. Recommends a lack-of-fit F test against pure error, residual pattern and back-calculated error by level (e.g. via check_response with replicates). Notes that acceptance criteria must be stated beforehand and that the script reports but does not conclude.

  30. “We're moving our LC-MS/MS plasma PK assay from our lab to a CRO. I have run results in runs_batch3.csv with QC columns (level, nominal, measured) and I need to check whether batch 3 meets the guideline for a chromatographic assay, including the rule that each QC level has enough passing samples. Also, what's the right way to check incurred sample reanalysis?”

    expects Uses the bioanalytical run check with modality set to chromatographic (not LBA). Applies ±15%/±20% at LLOQ, and at least 2/3 of all QCs plus at least 50% at each level. ISR: ±20% for at least 2/3 of repeats. Does not import the LBA total-error criterion, and leaves the accept/reject decision to the analyst and QA.

  31. “Our QC lab is replacing an old HPLC method for an impurity with a faster UHPLC one. We ran 24 samples on both. A t-test gave p = 0.4 so my manager says they're the same. I'd like to defend the switch to auditors. How should I do this properly?”

    expects Explains that p > 0.05 does not demonstrate equivalence. Recommends TOST against a margin stated before looking at the data, plus Deming or Passing-Bablok regression instead of OLS for the method comparison. Notes the margin must be justified and that the result is reported, not a declaration of validation.

  32. “What does USP <1225> say exactly about the acceptance limits for accuracy of an assay? Please quote the text of the chapter for me.”

    expects Declines to quote or reconstruct the paywalled USP text and does not invent thresholds. Points to obtaining an authorised copy. This is a copyright-boundary request, not something the skill should fulfil.

  33. “Fit a four-parameter logistic curve to my ELISA standards in Python and plot the curve with confidence bands for a figure in my paper.”

    expects Does general curve fitting and plotting (scipy/matplotlib). It is not a validation, protocol or acceptance-criteria task, so the validation skill is not needed.

  34. should triggeranndata

    “How do I read a .h5ad file in backed mode so it doesn't load into RAM?”

    expects Shows ad.read_h5ad(path, backed='r') (or 'r+'), explains X stays on disk while obs/var load in memory, and notes that subsetting or in-memory operations need .to_memory() or a copy. Does not use deprecated ad.read.

  35. should triggeranndata

    “I have three batches saved as batch1.h5ad, batch2.h5ad and batch3.h5ad with different gene panels. I ran `adata1.concatenate(adata2, adata3)` and got a FutureWarning, and the result is missing a lot of genes. How do I combine them properly, keep track of which batch each cell came from, and keep the union of genes?”

    expects Replaces the deprecated .concatenate() with ad.concat([...], join='outer', label='batch', keys=[...]), explains inner vs outer join and that outer fills missing genes (with 0/NaN, fill_value), mentions merge strategy for var and checking obs_names uniqueness (index_unique). Suggests checking the result on a small subset first.

  36. should triggeranndata

    “I've got a cell-by-gene count matrix in a CSV, a separate table of cell metadata (donor, tissue, sequencing run), and a gene annotation table. I want to bundle everything into one object that I can slice by cell or gene and save as a single file for collaborators in the scverse ecosystem. How should I set that up?”

    expects Recommends building an AnnData with X (sparse if appropriate), obs and var as DataFrames whose indices are aligned to the matrix rows/columns, checks index alignment and orientation (cells as rows), and writes with write_h5ad (optionally with compression). Mentions converting strings to categoricals and verifying shapes before writing.

  37. near missanndata

    “I have a filtered h5ad of PBMCs. Run QC, normalize, find highly variable genes, compute PCA/UMAP, cluster with Leiden, and find marker genes per cluster.”

    expects Recognizes this as a standard analysis workflow and uses the scanpy skill (sc.pp, sc.tl, sc.pl), not the anndata data-format skill.

  38. near missanndata

    “Pull all human lung cells from the CELLxGENE Census for a COPD vs. healthy comparison and give me the cell counts per cell type and donor.”

    expects Recognizes this as a population-scale Census query and uses cellxgene-census (open_soma, obs queries with value_filter), not the anndata skill.

  39. should triggerapa7

    “Convert my reference list to APA 7th edition and fix the heading levels in my thesis.”

    expects APA 7 reference patterns, DOIs as URLs, 5 heading levels

  40. near missapa7

    “Format my bibliography in IEEE numbered style.”

    expects Skill not used