Total 31,127 skills, AI & Machine Learning has 5038 skills
Showing 12 of 5038 skills
Create, audit, and maintain CLAUDE.md documentation files that configure Claude Code for projects. Use this skill when (1) initializing a new project with Claude Code configuration, (2) reviewing or improving existing CLAUDE.md files, (3) organizing project instructions using progressive disclosure patterns, (4) converting repeated instructions into permanent documentation, or (5) setting up agent_docs/ structures for larger codebases. Handles the WHAT/WHY/HOW framework, conciseness optimization, and file import patterns.
Local vision-language model for image analysis using SmolVLM-2B
Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X configured?', 'We should...', 'The fix is...', 'Options: 1...', 'Based on my understanding...', 'I believe X supports...'. Before deciding anything, spin up parallel subagents to WebSearch for current docs, community solutions, framework best practices, and GitHub issues. Your memory is stale — verify everything.
Updates model references across all skill files when new Claude models are released. Use when Anthropic releases new Claude models to keep skills current.
Designs album concepts, tracklist architecture, and thematic planning through 7 structured phases. Use when planning a new album or reworking an existing album concept.
Super Ralph Wiggum - autonomous iteration loops with templates, PRD support, progress tracking, and browser testing. This skill should be used when running Claude Code in autonomous loops for test coverage improvement, PRD-based feature development, documentation generation, dataset creation, lint fixing, code cleanup, or framework migrations. Combines the plugin's in-session loop mechanism with specialized templates and best practices from Geoffrey Huntley, Ryan Carson, and AI Hero.
Use when parameter values appear in multiple documents and consistency must be verified, especially for quantitative values that may differ due to measurement context or require reconciliation
MANDATORY before starting any task. Enforces the GPA execution loop that prevents tool call sprawl. G: GATHER phase combines discover queries + memory reads + file reads into one phase. P: Plan in text with zero tool calls. A: APPLY all writes/edits/verification in one phase. One call per tool type per phase — batch all same-type operations together. Covers dependency analysis, batch opportunities, scope estimation, and loop-back triggers.
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol)
Use when research direction needs assessment, critical knowledge gaps must be identified, or priorities must be recommended based on impact, dependencies, and effort (especially at project milestones or when scope questions arise)
Guide for creating and validating Claude Code plugin.json files. Use when creating plugins, validating plugin schemas, or troubleshooting plugin configuration.
Use this skill when the user asks to "create a finding", "record an insight", "what findings exist", "show findings", or wants to create or review evidence-backed analysis insights from crawl observations. Creates and queries curated findings with evidence chains.