616 skills · sorted by relevance
Build Python workflows that constrain language model output using text patterns and grammar rules. Generate structured JSON, restrict classifications to allowed labels, extract information, and combine reusable generation steps with loops and tool selection.
Check regulatory feeds for updates since the last review and filter them by relevance to your work. Receive a digest grouped by importance, with source labels, effective dates, and comment deadlines where applicable.
Structure client intake for a legal clinic using practice-specific questions. Produce a case summary with issues across legal areas, potential conflicts of interest, urgency, verification prompts, and deadline handoffs for student analysis and supervisor review.
Build evaluation suites for AI features with the Axiom AI SDK. Generate test files, scoring functions, test cases, and configurable parameters from descriptions and existing code to compare changes and monitor output quality in production.
Turn unstructured clinical encounter summaries into SOAP notes, a four-part format for medical records. Organize symptoms and findings, include diagnoses with ICD-10 classification codes, and document treatment steps, follow-up timing, and reasons to return for care.
Query EpiGraphDB for trait classifications, related literature, genetic evidence, and gene–drug relationships. Get concise summaries with limited result counts, or save the complete response when you need the underlying data.
Organize AI agent security findings using the ten OWASP ASI risk categories. Map issues such as leaked credentials or unauthorized tool calls to category IDs, and assign severity levels with suggested remediation timeframes.
Turn a product idea into a product requirements document through guided questions. Review existing system behavior and measurements as evidence, confirm how answers are recorded, and keep decisions separate from assumptions and unresolved items.
Identify whether a Matrix chat room is a request source or a task workspace, then create or reuse a project-specific task room. The skill also handles worker invitation details and preserves information about where requests originated.
Refactor C#/.NET code through renaming, extraction, consolidation, and other structural changes while preserving behavior. Check compatibility beyond code references, including public APIs and serialized names, then validate with builds and relevant tests.
Review test files or suites for missing checks, hidden exceptions, unreliable timing, shared state, and maintenance problems. Get a severity-ranked report with specific locations, explanations, and concrete suggestions for improving the tests.
Compare two or more dotnet new templates using their installed options, features, and supported frameworks. Get a focused comparison table and a recommendation that explains which template best fits the project you want to build.
Review C#/.NET code for about 50 inefficient API usage patterns across asynchronous work, memory, strings, collections, and I/O. Get exact occurrence counts, prioritized findings, and concrete fixes, with attention to frequently executed code.
Guide gh-aw release preparation and assess whether command-line changes break existing usage. The reference covers changesets, which record release changes, version previews, release steps, firewall log classification, and summaries of Go module usage.
Screen incoming nondisclosure agreements against a supplied playbook or default criteria. Receive a three-level classification, a summary of problematic clauses, suggested fixes, and recommended next steps for approval or legal review.
Find test inputs and filter bypass examples for web security checks, organized by vulnerability type. Includes URL classification patterns, discovery wordlists, and examples of combining findings to demonstrate concrete security impact.
Build a software quality assurance process with structured test cases, execution tracking, bug severity levels, and quality metrics. Includes templates for progress reports and team handoffs, plus prompts for agent-driven test execution.
Select open or explicitly named issues for triage, an initial assessment and classification, then distribute them to dedicated workers. It filters ineligible items, records selection reasons, and runs two sessions concurrently by default.
Select open pull requests for initial classification and distribute them to dedicated workers with a concurrency limit. Record why each request is included or excluded, without merging changes, assigning owners, or requesting reviewers.
Choose methods for differential equations with conditions specified at boundaries. The skill guides problem classification, shooting methods, finite differences, numerical solvers, and eigenvalue problems, with command examples for exploring solutions and checking numerical accuracy.
Build and train graph neural networks, models that learn from connected entities, using PyTorch Geometric. The skill covers classifying nodes or whole graphs, predicting missing connections, and modeling molecular properties or networks with multiple entity types.
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series models (ARIMA, SARIMAX, VAR) use statsmodels; for time series classification/clustering use aeon.
The English summary is being prepared. Showing the original description.
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting, underfitting, baseline, ablation study, critique my approach, review my model, is this a good idea, should I use, what's wrong with, evaluate my solution, challenge my assumptions, discuss my approach Engages in critical discussion with minimum 3 rounds of iterative refinement. Challenges both user proposals and own suggestions with fact-based critique. Demands evidence and baselines before accepting solutions.
The English summary is being prepared. Showing the original description.
Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.
The English summary is being prepared. Showing the original description.