1.2K skills · sorted by relevance
Build Handsontable demo pages for visual regression tests, which compare screenshots for appearance changes. It guides feature routes, URL-driven display states, sample data, and decisions about testing the same feature across framework wrappers.
Create and update Handsontable guide pages with consistent page metadata, headings, framework-specific examples, and sidebar entries. Follow the documentation site's writing conventions and generate JavaScript examples from TypeScript sources where required.
Find facts, relevant examples, and prior wording in work history to support a writing draft. Use source evidence to separate completed work from plans and opinions, verify quotations, and remove sensitive details from public drafts unless disclosure is authorized.
Find repeated tasks in recorded activity or starred examples, then describe their steps, exceptions, and human decisions. Assess a small automation candidate using captured evidence, available tools, permissions, and clear completion criteria.
Assess Web3 vulnerability findings before submission by checking scope, reproducibility, prerequisites, and attack costs. Organize the root cause, measurable impact, working proof of concept, and proposed fix into an Immunefi report, with examples for comparison.
Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.
Create, update, or review Bifrost feature documentation for Mintlify using MDX, a format combining Markdown and components. Research the interface and backend, validate configuration examples, and organize pages with screenshot placeholders and navigation entries.
Guides Java SDK development in Apache Beam, from finding relevant modules to building code, running focused tests, and trying examples. Also explains how to publish modified modules locally and build SDK containers.
Write, review, and edit developer documentation for SDKs, libraries, and frameworks. Organize guides, API references, and code examples around readers’ tasks, checking technical claims against source code and official documentation while following the destination site’s conventions.
Answer Python questions and write code using examples fetched from pythonsheets.com. Find patterns for syntax, asynchronous tasks, networking, databases, machine learning, and distributed computing, or use topic-based questions to prepare for Python interviews.
Turn existing source code into reusable learning materials. This skill identifies architectural patterns and implementation techniques, then organizes them into a SKILL.md with structured metadata, explanatory code templates, practical examples, and validation steps.
Use concrete JSON and Markdown examples to structure Sergo tool caches, strategy histories, improvement tasks, and reports. The templates show which fields to record and how to organize findings for review.
Design deliberately flawed examples that develop error-detection skills and deepen understanding. Use when students make characteristic errors and need practice spotting mistakes.
The English summary is being prepared. Showing the original description.
Design the transition from worked examples to independent problem-solving using expertise-reversal principles. Use when students follow examples but cannot solve problems alone.
The English summary is being prepared. Showing the original description.
Use when a Java change needs independent Behavior-Driven Development guidance from trusted behavior facts through concrete examples and observable scenarios, with focused clarification when behavior is pending or ambiguous. This should trigger for requests such as Apply BDD; Facilitate behavior examples; Discover scenarios with Given When Then; Review these examples for shared domain language; Complete BDD discovery as a self-contained interaction. Part of Plinth Toolkit
The English summary is being prepared. Showing the original description.
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
The English summary is being prepared. Showing the original description.
Design the transition from worked examples to independent problem-solving using expertise-reversal principles. Use when students follow examples but cannot solve problems alone.
The English summary is being prepared. Showing the original description.
Design deliberately flawed examples that develop error-detection skills and deepen understanding. Use when students make characteristic errors and need practice spotting mistakes.
The English summary is being prepared. Showing the original description.
Synchronize and verify code examples in documentation. Use when function signatures change, API interfaces update, imports shift, or documentation snippets become outdated and need correction.
The English summary is being prepared. Showing the original description.
Generates code examples for PHP documentation. Creates minimal, copy-paste ready examples with expected output.
The English summary is being prepared. Showing the original description.
Turn notes, transcripts, or research into polished articles, guides, tutorials, and newsletters. Use supplied writing examples or brand guidance to maintain a consistent voice, organize a clear argument, and support factual claims with provided evidence.
Draft articles, guides, and newsletters in a voice drawn from supplied examples or brand guidance. Turn notes and research into structured prose, or revise existing drafts for clearer pacing, stronger evidence, and consistent style.
Build question answering and document retrieval workflows with DSPy by defining inputs, outputs, and reusable components. Use training examples and evaluation metrics to automatically optimize prompts and compare results before and after optimization.
Build specialized agents for Claude Code plugins that handle tasks involving multiple steps. Define when each agent should run, its responsibilities, available tools, and expected output, then validate its configuration and test its behavior.