RedAct

Interact with research artifacts running in separate Docker containers via artifact-runner. Execute commands through HTTP API, read files, and verify artifact functionality.

Evaluate research artifacts running in separate Docker containers via artifact-runner. Access artifacts through HTTP API, execute commands, read files, and analyze PDFs.

Interact with artifact containers via HTTP API for paper evaluation tasks. Execute commands, read files, and list directories in remote artifact environments.

Evaluate research artifacts against NDSS badge criteria (Available, Functional, Reproduced) by checking DOI, documentation, exercisability, and reproducibility requirements.

Extract text, tables, and structured information from PDF documents using pdfplumber, PyPDF2, or pdftotext command-line tools.

Calculate protein dihedral angle (phi/psi) from atomic coordinates using the torsion formula. Use when computing backbone dihedral angles from atomic positions or validating protein geometry.

Analyze DNA/RNA/protein sequences: type determination, GC content calculation, reading frame translation, and longest ORF finding. Use when users ask about sequence translation, GC content, open reading frames, or residue counting.

Calculate Nusselt number for forced convection heat transfer. Use when computing dimensionless heat transfer coefficient, or analyzing convection heat transfer performance.

Pipe flow Reynolds number calculation and flow regime classification. Use when calculating Re from fluid properties and pipe parameters, or classifying flow as laminar/transitional/turbulent.

Gibbs free energy and equilibrium constant calculation from thermodynamics data. Use when calculating ΔG from ΔH, ΔS, and T, or computing equilibrium constants.

This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences across sessions using MCP memory server integration

Parse MSP (mass spectrometry) files and count spectral data: spectrum count, peak count per spectrum, and total peak count. Use when users ask about mass spectrometry data parsing, spectral counting, or MSP file analysis.

Find the most similar spectral pair from MSP files using CosineGreedy similarity. Use when comparing multiple mass spectra, computing pairwise similarity matrices, or identifying best matches in metabolomics.

Filter molecules using CommonAlertsFilters from medchem library. Detect structural alerts and problematic functional groups in molecules for drug discovery filtering.

Apply Lipinski Rule of Five (Ro5) to molecules: check MW, LogP, HBD, HBA. Use when users ask about drug-likeness, Lipinski rules, or oral bioavailability filters.

Calculate RMSD between two sets of 3D atomic coordinates. Use when computing root mean square deviation between reference and target structures, or structural alignment quality assessment.

Check if a SMARTS pattern matches a molecule using RDKit. Use when performing substructure matching on SMILES structures with SMARTS patterns, or checking functional groups in molecules.

Hardy-Weinberg equilibrium expected genotype counts and heterozygosity calculation. Use when computing expected genotype frequencies, expected heterozygosity, or observed heterozygosity from allele counts.

Constrained single-objective optimization using pymoo. Minimize objective functions subject to inequality constraints using ElementwiseProblem and NSGA-II or GA.

Multi-objective optimization using NSGA-II. Define custom problems, find Pareto front, minimize conflicting objectives. Use when solving optimization problems with 2-3 objectives, Pareto front analysis, or NSGA-II algorithm configuration.

Calculate Bloch vector components from spherical coordinates (theta, phi). Use when converting Bloch sphere angles to Cartesian coordinates, or working with quantum state geometry.

Compute quantum state expectation values for Pauli matrices from Bloch sphere coordinates. Use when working with quantum state analysis, Bloch sphere representation, or Pauli matrix expectation values.

Local sequence alignment scoring using Smith-Waterman algorithm with affine gaps. Use when computing DNA alignment scores with match/mismatch and gap penalties.

Count k-mers (subsequences of length k) in DNA sequences. Use when counting DNA k-mers, analyzing sequence composition, or computing k-mer frequency distributions.

Fit Cox proportional hazards model and compute concordance index using scikit-survival. Use when performing survival analysis, fitting Cox models, or evaluating survival predictions with concordance index.

Annotate VCF variants with their type (SNP, MNP, INS, DEL) based on REF and ALT allele lengths. Use when parsing VCF files and classifying variant types from sequence changes.

Parse VCF files and count variants by FILTER status. Use when users ask about VCF file parsing, variant counting, or PASS/FAIL filter statistics.

Compute the mass of the largest connected component in a binary STL where the 2-byte attribute field stores a material ID, using a Markdown density table.

Design, implement, and validate an adaptive cruise control (ACC) simulation with PID control, mode logic, segmented metrics, and reproducible I/O.

Detect BGP preference-cycle oscillations and valley-free route leaks, then assess which changes would resolve each issue.

Compute signed dihedral (torsion) angles from four 3D points and report degrees in [-180, 180] using a robust atan2 formulation.

Fill structured, fillable PDFs (e.g., court/government forms) by extracting fields, mapping user data, handling checkboxes/dates/amounts, and verifying the result.

Compute network metrics and intrusion flags from a PCAP and populate a metric,value CSV while preserving comments.

Compute GC content, translate a nucleotide sequence in a specified reading frame, and find the longest ORF across frames with robust verification.

Analyze nucleotide sequences: detect type, compute GC%, translate in a specified reading frame with '*' for stops, and find the longest ORF that starts at ATG and ends at an in-frame stop.

Classify DNA/RNA vs protein, compute GC%, translate in a specified frame with stop codons marked '*', and find the longest valid ORF across all three frames.

Estimate camera egomotion between sampled video frames and produce dynamic-object masks with CSR storage; validates outputs for downstream use.

Run deep-learning phase picking (SeisBench) and robustly associate picks into earthquakes with GaMMA, with ID alignment, timestamp, projection, and config sanity checks.

Compute distances from point events to the nearest relevant boundary within a parent polygon using GeoPandas projections, then select the extremal case (e.g., farthest).

Detrend macroeconomic time series with the HP filter (on log real values) and compute Pearson correlation, robust to mixed annual/quarterly Excel tables and CPI deflation.