2.1K skills · sorted by relevance
Build a product strategy across nine connected areas, including vision, target markets, customer value, growth, and competitive advantages. Clarify priorities, work to exclude, success metrics, and assumptions, then propose small experiments to test the strategy.
Turn product or feature ideas into a concise product requirements document that helps teams decide what to build first. Connect target customers, customer value, success measures, and release scope, or review an existing document for gaps.
Review and simplify code while preserving its behavior. Check readability, reuse, and efficiency, assess whether tests and comments add value, and verify applied changes with the project's configured checks before review.
Diagnose declines in Google Ads conversions, conversion value, and leads by comparing periods, traffic, device breakdowns, impression share, and account changes. Use live account data through the Google Ads MCP Server or receive queries and diagnostic guidance for manual execution.
Turn product documentation into sales materials with a conversational story, charcoal sketch artwork, and talking points. The workflow connects product value to a narrative and matching visual for pitches, presentations, and sales scripts.
Manage shared iii configuration with JSON Schema, a definition of allowed value structures. Covers validated settings, automatic change notifications, YAML edits, temporary overrides, and default initialization that preserves existing values.
Build Vue 3 interfaces from JSON specifications, including AI-generated layouts. The skill covers component registration, named content areas, synchronized form values, conditional visibility, validation, actions, and connections to external state management.
Create reusable Helm charts, packages of Kubernetes deployment templates and settings. The skill guides environment configuration, dependency management, shared templates, and release procedures so applications can be deployed across environments with fewer template changes.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Configure Convex deployment environment variables for secrets such as API keys, read them from application actions, and check the configured values while keeping secrets out of source code and Git.
Handle merged cells before filling Excel templates with openpyxl, a Python library for spreadsheets. This skill shows how to inspect merged ranges, unmerge the required areas, write values, and save the workbook without merged-cell write errors.
Audits arithmetic code for mixed units, decimal precision mistakes, and scaling errors. Adds comments identifying each value’s units and produces a summary of findings, unit definitions, and files reviewed.
Draft an Amazon-style press release before development to clarify a product's customer value. Using Working Backwards, a method that starts with the intended customer outcome, organize the problem, benefits, and launch promise so stakeholders can assess the idea.
Build or update a Figma design system to match a codebase. Organize reusable design values, light and dark themes, component variants, and documentation, then check component structure, appearance, and bindings to those values.
Combine selected data from multiple Excel sheets, clean numeric values, and extract the highest entries for a chosen metric. Create a ranked Excel report with highlighted columns, borders, column widths, and number formats for easier comparison.
Extract coefficients associated with a chosen label across Excel sheets and check them against a standard value. Create a comparison workbook showing each value, its source sheet, and red highlighting for rows that fail the check.
Extract numbers from text values containing a specified unit, remove unusable rows, and visualize the distribution. Create a histogram with mean and median markers, plus a dashboard showing frequencies, proportions, and cumulative percentages.
Diagnose and fix MSBuild property problems, including overwritten settings, ineffective conditions, and environment-dependent paths. Review defaults, list appending, and evaluation order so project files and shared build settings retain the intended values.
Develop user-visible improvements for cc-wf-studio, verify their basis in the code, and assess their value. Record qualifying proposals as locked GitHub issues, creating a queue of concrete ideas for later implementation without changing code.
Extract statistical values from research PDFs for meta-analysis, which combines results across studies. Track each value’s source and confidence, prioritize review, and manage human corrections and final approval in a shared data structure.
Build and estimate economic models that represent underlying choices and incentives. Get guidance on demand, dynamic choice, and auction models, select estimation methods, and diagnose numerical problems such as failed convergence or sensitivity to starting values.
Build reproducible empirical analyses in R, from data cleaning to statistical modeling and publication tables and figures. Covers economics, epidemiology, and machine learning approaches to causal inference, which estimates effects of interventions.
Build a reproducible Stata analysis from data cleaning through modeling, diagnostic checks, and robustness tests. Generate runnable .do files, regression tables, and figures for empirical papers, with additional workflows for epidemiology and machine learning approaches to causal inference.
Collect user-provided API keys and other credentials through a form and save them to a specified dotenv configuration file. Request multiple variables together without exposing their values in chat, command arguments, or output visible to the agent.