1.4K skills · sorted by relevance
Develop solution ideas through repeated rounds of research, cross-domain borrowing, recombination, and evaluation. Receive ranked candidates with feasibility and novelty scores, supporting and opposing arguments, and a record of where each idea came from and how it changed.
Prepare an Apache bRPC release with tracked progress, version updates, release candidate checks, and draft release notes and emails. The workflow leaves signing, publishing, and other external release actions to the release manager.
Screen companies across markets within a chosen industry and narrow the list to three investment candidates. Compare financial health, lasting competitive advantages, valuations, and risks, while recording why other companies were excluded.
Review what Superset agents did while you were away by checking workspaces, tasks, and recent terminal output. Receive a concise digest of completed work, review requests, ongoing activity, and blockers, with the next actions listed first.
Inspect repository code or code changes for plausible security vulnerabilities. The skill records candidate issues with affected locations, attacker-controlled inputs, failing safeguards, and possible impact, preserving the evidence needed for later validation.
Uses a known or suspected vulnerability to find related code through Trailmark's graph of calls, types, and implementations. Produces ranked review targets with reasons and limitations for follow-up security analysis.
Turn security findings into candidate code fixes with review results and summaries. Depending on the input, use independent source review or a pipeline with execution checks, then provide diffs for a person to review and apply.
Screen public equity candidates and prioritize further research using company sources, market data, and supplied notes. Organize promising names, watchlist items, evidence gaps, and rejection risks into a concise review or standalone HTML report.
Prioritizes candidate genes from GWAS, studies linking genetic variants to traits. Combines locus predictions, gene expression evidence, and rare variant support into ranked results with source attribution, confidence labels, reproducible files, and optional figures.
Examines code or code changes for plausible security vulnerabilities by tracing attacker-controlled input to dangerous operations or failed safeguards. Records candidate issues with affected locations, supporting evidence, potential impact, and controls that need further validation.
Screen an existing compound library against a protein target with Boltz. Rank candidates by binding confidence or lead optimization score, download predicted structures, and review solubility, permeability, and lipophilicity results alongside the ranked hits.
Screen supplied proteins, peptides, antibodies, or nanobodies against a target with Boltz. Prepares inputs, obtains a cost estimate for approval, downloads results, and ranks candidates by binding confidence, a score for predicted binding reliability.
Generate new small molecules intended to bind a target protein with Boltz. The workflow covers cost estimation, job submission, result downloads, and ranking candidates by binding confidence or a score for improving promising molecules.
Turn .NET runtime addresses in Android crash reports into function names, source files, and line numbers. The skill extracts build identifiers, downloads matching debug symbols, and uses llvm-symbolizer to produce a readable backtrace.
Design amino acid sequences from a protein backbone stored in a PDB file using ProteinMPNN. Generate multiple candidates, redesign selected chains while preserving specified residues, and vary sampling settings to prepare sequences for downstream structure prediction.
Design amino acid sequences from a protein backbone using SolubleMPNN, a model trained on soluble protein structures. Generate candidates with a solubility bias for redesigning aggregation-prone proteins or preparing an E. coli expression screen.
Validate a Kiln release candidate with standard code checks and selected tests against live APIs. Diagnose failures, inspect outdated model selections and coverage gaps, and produce a report with recommended actions without changing code or tests.
Review a codebase for design friction and compare refactoring candidates in an HTML report with before-and-after diagrams. Then explore a chosen candidate through questions about constraints, module design, and testing.
Develop identification arguments in econometrics: establish whether observed data uniquely determine a target parameter, state assumptions and rank conditions, and write formal propositions. When uniqueness fails, characterize the range of parameter values consistent with the data.
Turn a financial economics research idea into a structured, 12-part empirical proposal. It outlines hypotheses, matching data sources, methods for testing causal effects, illustrative results tables, and robustness checks, while examining the study’s contribution.
Plan robustness checks for finance and economics papers to assess whether findings hold under different samples, variable definitions, and modeling choices. Get method-specific checklists, test priorities, and a template for presenting results.
Run empirical and causal analyses in Python with StatsPAI, from stating assumptions to estimating effects and checking how results change under alternative choices. Produce diagnostic figures, regression tables, and replication bundles for economics, public health, or machine learning studies.
Find STATA code examples for empirical accounting research from published replication files. Adapt regression, matching, event study, and table export syntax to your variables, with citations to the papers behind each example.
Review a JavaScript SDK release plan or final candidate against the previous release. Check compatibility, packaging, regressions, and Changesets version records, then recommend shipping or blocking with supporting evidence and a separate assessment of documentation coverage.