ai-agent-skills-library

Designs, improves, converts, debugs, and operationalizes prompts, system instructions, agent definitions, and reusable AI-agent behavior. Works autonomously by default: reads the project, infers intent, and produces a finished prompt with stated assumptions in one pass; runs a guided one-question-at-a-time interactive mode on request. Use when the user is writing or refining a prompt, a system prompt, GPT/agent instructions, an AGENTS.md or CLAUDE.md, a Cursor rule, or asks to make a prompt better, convert a prompt between platforms, debug poor prompt output, or cut a prompt's token usage. Triggers on: 'write a prompt', 'improve this prompt', 'prompt for', 'system prompt', 'agent instructions', 'convert this prompt', 'why is this prompt failing', 'reduce tokens', 'prompt engineering'.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms).

To access Anthropic's official brand identity and style resources, use this skill.

To access Anthropic's official brand identity and style resources, use this skill.

These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to install/search/generate skills, or needs to set up Context7 for their AI coding agent.

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

You are a frontend designer-engineer, not a layout generator.

Use this skill when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the Anthropic SDK", "query Pinecone", or any time the user asks you to write code against an external service and you need current API reference. Fetch the docs with chub before answering, rather than relying on training knowledge.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.

To write internal communications, use this skill for:

To write internal communications, use this skill for:

Write internal communications such as status reports, leadership updates, 3P updates, newsletters, FAQs, incident reports, and project updates using repeatable internal formats.

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.

Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.

To create new CLI skills following Anthropic's official best practices with zero manual configuration. This skill automates brainstorming, template application, validation, and installation processes while maintaining progressive disclosure patterns and writing style standards.

A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.

This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact.

To build powerful frontend claude.ai artifacts, follow these steps:

To test local web applications, write native Python Playwright scripts.

Builds a comprehensive brand blueprint for any business — personal brand, founder brand, agency, product company, or service business. Produces a multi-document brand system covering identity, narrative, visual identity, messaging, services & revenue, content engine, and AI operating manual. Use when the user asks to 'build a brand blueprint', 'create a brand book', 'document our brand', 'set up brand foundation', 'do a brand audit and lock decisions', 'write our positioning', 'create brand guidelines', 'redo our brand strategy', or starts a new venture and needs a complete brand foundation. Walks through the work in eight ordered sections with explicit prompts; outputs both supporting documents AND a master blueprint that synthesizes them. Generic across personal vs. commercial brands.

Maps audience/customer awareness stages and recommends messaging angles, objections, and next-step content for each stage.

Analyzes how customers perceive a brand and identifies psychological cues that shape trust, relevance, differentiation, and recall.

Restores refactoring context by reconstructing goals, touched areas, risks, and next actions after a paused or interrupted code cleanup effort.

Runs a broad code or project review across correctness, maintainability, security, UX, tests, and release readiness.

Restores working context from notes, files, summaries, and prior decisions so an agent can continue without repeating discovery.

Captures durable context, decisions, open questions, and next steps so future agent sessions can resume accurately.

Improves persuasive copy using behavioral psychology, audience motivation, objection handling, and conversion-focused messaging principles.

Builds psychographic profiles from customer signals, motivations, anxieties, buying triggers, and decision-making patterns.

Guides structured debugging by isolating symptoms, reproducing failures, forming hypotheses, inspecting evidence, and choosing minimal fixes.

Designs the emotional progression of a page, campaign, onboarding flow, or narrative so users move from tension to trust and action.

Coordinates multi-perspective review of complex errors, comparing hypotheses and fix plans before implementation.

Diagnoses errors from logs, traces, stack output, and symptoms, then maps likely causes to targeted verification steps.

Orchestrates full-stack feature delivery across product requirements, backend, frontend, data, tests, and release checks.