universal-ai-skills-library

Use when aggregating local files, directories, GitHub repositories/issues/PRs, documentation pages, PDFs, arXiv/DOI/PMID sources, YouTube transcripts, stdin, or clipboard text into a single LLM-ready XML context file using the locally installed jimmc414/onefilellm CLI. Use for context packaging, source bundling, repo-to-text conversion, and multi-source research ingestion.

Configure and audit the local universal AI skills setup across Codex, ChatGPT, Claude, Claude Code, Claude Cowork, Cursor, Gemini, OpenCode, OpenSkills, Hermes Agent, OpenClaw, Cline, Continue, GitHub Copilot, Kiro, OpenHands, hosted provider compatibility surfaces, plugin manifests, optional MCP bridges, and global instruction files. Use when the user asks to organize, consolidate, optimize, rename, or repair the cross-AI skill router configuration.

MUST read when a task needs persistent services, Docker, fixed IPs, background jobs, heavy compute, reusable environments, or always-on infrastructure beyond the current AI sandbox. Covers local desktop, managed cloud computer, and third-party cloud options, including hosted provider compatibility where relevant.

Hosted project-UI compatibility adapter for deploying skills through a provider gRPC-web API. Packages skills as zips, uploads/deletes/syncs per-project skill sets, and curates domain-relevant skills using LLM analysis. Use only when filesystem skills must be visible in a hosted project UI sidebar or synchronized across hosted projects.

Universal hosted-provider API adapter guide. Use the skill-router provider-api CLI for compatible project/task/file/webhook/agent APIs, with explicit endpoint and key configuration instead of provider-specific defaults.

Generate high-density infographics with structured layout and style choices and bundled generation tooling. Use when the user asks to create an infographic, a visual summary, or a dense single-page information graphic.

Search and recommend Agent Skills from verified GitHub repositories. Use when users ask to find, discover, search for, or recommend skills/plugins for specific tasks, domains, or workflows.

Build generative UI apps with OpenUI and OpenUI Lang — the token-efficient open standard for LLM-generated interfaces. Use when mentioning OpenUI, @openuidev, generative UI, streaming UI from LLMs, component libraries for AI, or replacing json-render/A2UI. Covers scaffolding, defineComponent, system prompts, the Renderer, and debugging OpenUI Lang output.

Transforms workflow to use agent-friendly persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Configure and audit the local universal AI skills setup across Codex, ChatGPT, Claude, Claude Code, Claude Cowork, Cursor, Gemini, OpenCode, OpenSkills, Hermes Agent, Paperclip agents, OpenClaw, Cline, Continue, GitHub Copilot, Kiro, OpenHands, hosted provider compatibility surfaces, plugin manifests, optional MCP bridges, and global instruction files. Use when the user asks to organize, consolidate, optimize, rename, or repair the cross-AI skill router configuration.

Analyze websites and domains using SimilarWeb traffic data. Get traffic metrics, engagement stats, global rankings, traffic sources, and geographic distribution for comprehensive website research.

Guide for creating or updating portable AI skills via specialized knowledge, workflows, scripts, references, or tool integrations. For any skill modification or improvement request, read this skill first and follow its update workflow.

Deep dual-model debugging of AI skills using reasoning model and fast synthesis model. Use when asked to debug a skill, find bugs in a skill, review a skill for issues, fix a broken skill, or audit a skill's quality. Also use when a skill is not working correctly or producing unexpected results.

Search the installed skill library to find and fully activate the most relevant skills for any user task. Use when the user asks to find a skill, search for skills, says "find the best skill for this", "which skill should I use", "search skills", or when the assistant needs to identify which installed skills are most applicable to a complex or unfamiliar task before execution. Also use proactively when facing a task outside core capabilities to discover specialized workflows, scripts, and domain expertise from the skill library.

Sync and install skills from a GitHub skills repository into a local or global AI skill root. Use when the user asks to install skills, update skills, sync skills from GitHub, load a skill library, or ensure cross-AI skill roots are up to date.

The definitive end-to-end pipeline for creating the highest quality portable AI skills. Orchestrates six individual skills in sequence — each run fully, separately, and in its entirety — to produce elite, production-grade skills. Use when the user explicitly requests the full pipeline, says "ultimate skill", "ultimate skill creator", "ultimate skill creation", "best skill", "best skill creator", "full pipeline", "full skill pipeline", or specifically asks for maximum quality skill creation with all optimization stages. For simple skill creation without the full pipeline, use skill-creator instead.

Crawl entire websites using Cloudflare Browser Rendering /crawl API. Initiates async crawl jobs, polls for completion, and saves results as markdown files. Useful for ingesting documentation sites, knowledge bases, or any web content into your project context. Requires CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN environment variables.

Compress or convert generated images for delivery, preview, and social upload. Use when the user asks to compress an image, optimize image size, convert to webp, or reduce file size after generation.

Use when working with unclecode/crawl4ai or the local Crawl4AI stack: installing, updating, setting up, diagnosing, or using the `crwl` CLI for LLM-ready web crawling, scraping, Markdown extraction, JSON extraction, deep crawling, browser profiles, CDP browser control, screenshots/PDF/MHTML export, or Python `AsyncWebCrawler` workflows. Prefer this for deterministic local web-to-Markdown and crawler workflows. Do not use for generic web search when the host AI has native search.

Use when working with firecrawl/firecrawl or the installed Firecrawl CLI: installing, updating, logging in, checking status, searching the web through Firecrawl, scraping pages, interacting with pages, crawling sites, mapping URLs, parsing files, running Firecrawl agent jobs, using Firecrawl SDK/API examples, or configuring optional firecrawl-mcp for an MCP client. Prefer this for Firecrawl hosted API and CLI workflows. Do not use for generic web search when the host AI has native search, or for local Crawl4AI workflows.

Harden the Docker daemon by configuring daemon.json with user namespace remapping, TLS authentication, rootless mode, and CIS benchmark controls.

Use when working with supreme-gg-gg/instagram-cli or Instagram from the terminal: logging in or checking auth, listing or searching inbox threads, sending Instagram direct messages, reading messages, replying, unsending, downloading message media, viewing feed/stories/notifications/profile TUI screens, configuring the Instagram CLI, or diagnosing the local `instagram-cli` install. Prefer this for agent one-turn Instagram workflows that need JSON output. Do not use for generic social-media copywriting or unrelated Instagram marketing strategy.

Use when working with Google NotebookLM through jacob-bd/notebooklm-mcp-cli: listing or creating notebooks, adding sources, querying notebooks, generating audio or studio artifacts, revising slides, downloading artifacts, sharing notebooks, syncing Drive sources, running cross-notebook queries, configuring the NotebookLM MCP server, or diagnosing NotebookLM CLI authentication. Prefer this over generic Google or MCP skills when the task is specifically about NotebookLM.

Run mandatory pre-PR quality checks for .NET projects before creating a pull request. Use before creating any PR, or when the user says "prepare for PR", "pre-PR checks", or "quality gate".

Printing Press CLI for Printing Press Golden. Purpose-built fixture for golden generation coverage.

Find and reduce code duplication, clean up redundant code, detect code clones, reduce codebase size, DRY violations, copy-paste detection. Use when the user asks about duplicate code, code cleanup, reducing code size, DRY principles, or finding copy-pasted code.

Technical SEO auditor and fixer. Runs Lighthouse/PageSpeed audits on websites or local dev servers, analyzes SEO/performance/accessibility scores, and automatically implements fixes for meta tags, structured data, Core Web Vitals, and accessibility issues.

Use when working with sferik/x-cli or the X API from the command line: authorizing X accounts, listing accounts, posting or replying, reading timelines, searching posts or users, streaming X events, managing follows, mutes, blocks, lists, direct messages, trends, places, or diagnosing the local `x` CLI install. Do not use for generic algebra variable "x" or unrelated command-line work.

Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.

Generate a comprehensive, AI-optimized summary of the current AI session. Use when the user asks to summarize this chat, create a session summary, generate a handoff document, capture what was done, or save progress for continuation in a new chat or another AI client.

Use when working with unclecode/crawl4ai or the local Crawl4AI stack: installing, updating, setting up, diagnosing, or using the `crwl` CLI for LLM-ready web crawling, scraping, Markdown extraction, JSON extraction, deep crawling, browser profiles, CDP browser control, screenshots/PDF/MHTML export, or Python `AsyncWebCrawler` workflows. Prefer this for deterministic local web-to-Markdown and crawler workflows. Do not use for generic web search when the host AI has native search.

Comprehensive file organization suite. Use for cleaning up messy folders, arranging the desktop, finding duplicates, renaming files intelligently, and categorizing files by type or date. Includes safety features like dry-run mode and undo capabilities.

Use when working with supreme-gg-gg/instagram-cli or Instagram from the terminal: logging in or checking auth, listing or searching inbox threads, sending Instagram direct messages, reading messages, replying, unsending, downloading message media, viewing feed/stories/notifications/profile TUI screens, configuring the Instagram CLI, or diagnosing the local `instagram-cli` install. Prefer this for agent one-turn Instagram workflows that need JSON output. Do not use for generic social-media copywriting or unrelated Instagram marketing strategy.

Use when aggregating local files, directories, GitHub repositories/issues/PRs, documentation pages, PDFs, arXiv/DOI/PMID sources, YouTube transcripts, stdin, or clipboard text into a single LLM-ready XML context file using the locally installed jimmc414/onefilellm CLI. Use for context packaging, source bundling, repo-to-text conversion, and multi-source research ingestion.

Create beautiful printable foldable greeting cards (birthday, thank you, etc.) as PDFs. Use when the user asks to make, design, or create a printable card, greeting card, birthday card, or foldable card for someone.

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

This skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "extract database information through injection", "detect SQL injection flaws", or "exploit database query vulnerabilities". It provides comprehensive techniques for identifying, exploiting, and understanding SQL injection attack vectors across different database systems.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Manage this repository as the user's universal AI setup hub for OpenSkills, source repo inventory, bootstrap scripts, skill audits, and cross-agent operating rules.

Use this whenever the user mentions Universal AI Skills, skill-router, router, route to a skill, unknown skill names, or wants the best skill selected automatically. This skill routes through the full `skill-router` corpus instead of relying on the native client skill list.