Loading...
Loading...
Found 1,832 Skills
Debug TensorFlow and Keras issues systematically. This skill helps diagnose and resolve machine learning problems including tensor shape mismatches, GPU/CUDA detection failures, out-of-memory errors, NaN/Inf values in loss functions, vanishing/exploding gradients, SavedModel loading errors, and data pipeline bottlenecks. Provides tf.debugging assertions, TensorBoard profiling, eager execution debugging, and version compatibility guidance.
Refactor Scikit-learn and machine learning code to improve maintainability, reproducibility, and adherence to best practices. This skill transforms working ML code into production-ready pipelines that prevent data leakage and ensure reproducible results. It addresses preprocessing outside pipelines, missing random_state parameters, improper cross-validation, and custom transformers not following sklearn API conventions. Implements proper Pipeline and ColumnTransformer patterns, systematic hyperparameter tuning, and appropriate evaluation metrics.
Debug ASP.NET Core and .NET applications with systematic diagnostic approaches. This skill covers troubleshooting dependency injection container errors, middleware pipeline issues, Entity Framework Core query problems, configuration binding failures, authentication/authorization issues, and startup failures. Includes Visual Studio and VS Code debugging, dotnet-trace, dotnet-dump, dotnet-counters tools, Serilog configuration, Application Insights integration, and four-phase debugging methodology.
Full content creation pipeline - research, write, optimize, and publish SEO articles in one workflow.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Talk to a senior product advisor who thinks in Ivan Zamesin's Next Move Theory / Advanced Jobs To Be Done methodology (distinct from generic Christensen JTBD). A conversational, multi-turn skill — ask any product, strategy, segmentation, value, pricing, growth, retention, positioning, B2B, research, or methodology question and get an answer grounded in the canon, not in LLM training. It explains concepts, diagnoses real product situations, pressure-tests hypotheses like a skeptical senior PM, teaches the methodology, and routes heavyweight artifact requests to the right producer skill in the pipeline (nmt-market-research → nmt-craft-value-proposition → nmt-product-requirements / nmt-craft-go-to-market). Use whenever the user wants advice, a second opinion, a methodology explanation, a diagnosis of "what should I do about X", or to think through a product decision — especially on /nmt-chat. Plain language first, methodology terms in parentheses; defaults to English.
Use when adding or changing a Bagisto import — an Importer class, a file source, the importers registry, the queued import pipeline, or a stuck or failing import job. Trigger phrases include "import", "importer", "data transfer", "CSV", "XLSX", "XML", "bulk upload", "import batch", "queued import", "validate rows".
Evidence-grounded advisory pipeline for "how should this work?" questions about any real system — codebase, database, CRM/ERP, SaaS, API, data pipeline, infra. Three-stage multi-agent method; STUDY the business and the live system with parallel readers returning structured citable findings (read-only, evidence saved to disk), DESIGN with independent designers given deliberately different value systems, VERIFY with an adversarial reviewer that attacks every design against the live schema, code, and usage data before anything is recommended. Use whenever the user asks for advice or a recommendation that must be grounded in how their system actually works — "how should X convert/map/migrate/sync to Y", "study my business and advise", "what's the right way to integrate/restructure/redesign this", "should we copy or link this data", "is this conversion/mapping correct, and if not what should it be", reviewing a planned schema or integration change, or any "give me advice" about a system mechanism. Trigger even when the user never says "advice" but wants a defensible recommendation about an existing system. Do NOT use for quick opinion questions with no system to study, single-file refactors, status updates, or pure greenfield design with no existing system as ground truth (use brainstorming instead).
Like sp-grill-with-doc (domain-aware grilling, glossary sharpening, inline CONTEXT.md/ADR capture) BUT continues into the superpowers planning pipeline by handing off to sp-writing-plans at the end. Use ONLY when the user wants both the grilling AND a written implementation plan produced afterward; if they want grilling/docs alone, use sp-grill-with-doc instead. The superpowers plugin is needed two hops downstream, by sp-writing-plans' own execution skills, not by this Skill.
Compare a target (spec, product vision, competitor, RFP, or "to-be" design) against a system as actually built, and produce an evidence-first fit-gap — a capability matrix plus a step-by-step user-journey comparison, verified against the LIVE system (schema + code, not docs) and rolled up into decisions. Stack-agnostic (web apps, APIs, ERPs, low-code/CRM, pipelines, infra). Use whenever the user wants to compare a spec/vision/competitor to an existing system, asks "how far are we from X" or "what would it take to support Y", runs a gap analysis or COTS/package/vendor evaluation, or scopes a migration / re-platform / feature-parity effort. Trigger on fit-gap, gap analysis, capability comparison, as-is vs to-be, system comparison, feature parity, migration assessment — even when the user never says "fit-gap". Do NOT use for: reviewing a single diff/PR, a generic code review/audit with no target to compare against, or comparing two prose documents for wording.
Turborepo CI pipelines with remote caching and affected detection
Upstash serverless Redis -- REST-based client, auto-serialization, pipelines, rate limiting, QStash, edge compatibility, global replication