🎯
Skills
Loading...
Showing 30 of 136605 results
Official AI agent skills from the Expo team, fine-tuned for building, deploying, and debugging Expo apps with Claude Code (optimized for Opus models) and other AI agents including Cursor.
Enables programmatic creation, editing, and manipulation of Microsoft Word (.docx) documents using python-docx, supporting paragraphs, tables, images, headers/footers, styles, and page setup.
Build a durable voice profile from 5–20 real samples — X posts, essays, launch notes, working emails, product docs — then reuse it across content and outreach instead of re-deriving style or defaulting to generic AI copy. Extracts rhythm, sentence length, capitalization norms, claim sharpness, and what the author never does.
A skill that provides Tavily AI search API integration for AI agents, enabling optimized web search directly from conversations using a simple script with environment variable configuration.
Helps navigate academic literature by formulating search queries, recommending databases (Google Scholar, PubMed, arXiv, etc.), analyzing paper abstracts, explaining research methodologies, and structuring literature reviews.
A collection of reusable agent skills for spec-driven software development workflows, including writing product and tech specs, implementing from approved specs, preparing PRs, diagnosing CI failures, and conducting structured code reviews.
Automates browser interactions via terminal using Playwright CLI, enabling web navigation, form filling, screenshots, and UI debugging.
PreToolUse-hook safety net that intercepts destructive Bash/Write/Edit operations (rm -rf, git push --force, DROP TABLE, kubectl delete, --no-verify, etc.) and optionally restricts edits to a specific directory tree. Three modes: Careful (warn on destructive commands), Freeze (lock edits to a dir), and Guard (both combined) for autonomous-agent safety.
Audits and remediates SEO across crawlability (`robots.txt`, canonicals, redirect chains), indexability (`hreflang`, sitemaps), Core Web Vitals targets (LCP < 2.5s, INP < 200ms, CLS < 0.1), structured data (`Article`, `Product`, `BreadcrumbList`, `FAQPage`), title/meta rules, and keyword-to-URL mapping. Outputs page-specific recommendations with severity tags rather than generic advice.
Official curated directory of high-quality plugins for Claude Code maintained by Anthropic, containing both internal plugins developed by Anthropic and vetted third-party external plugins.
EMR/EHR engineering patterns covering single-page encounter flow (complaint → exam → diagnosis → prescription), smart templates with red-flag alerts, medication safety, ICD-10/SNOMED search, lab-result reference-range highlighting, and tamper-proof audit trails. Every design decision is judged against "could this harm a patient?".
A cross-platform desktop app that lets you run multiple CLI AI agents (Claude Code, Codex, Gemini, and more) side-by-side across repositories, each in its own worktree, all tracked from a single unified interface.
An agent skill for automating WhatsApp Business communications including chatbot flows, order and shipping notifications, customer support automation, and broadcast messaging via the WhatsApp Business API.
Turn Claude Code into a persistent, self-directing agent system using only native features (crons, dispatch, built-in memory) and MCP servers, replacing standalone frameworks like Hermes and AutoGPT. Use when the user wants continuous autonomous operation, scheduled tasks, computer use, or an assistant that remembers context across sessions.
Discover, evaluate, and pick healthy Laravel packages through the LaraPlugins.io MCP server — `SearchPluginTool` for keyword / health-score / Laravel / PHP / vendor filtering, and `GetPluginDetailsTool` for per-package metrics, README, and version history. Free, no API key required.
An agent skill from Google's official skills repository providing guided workflows for Google Cloud network observability, part of a collection covering GKE, BigQuery, Cloud Run, Firebase, and other Google Cloud services.
A collection of skills that improve how AI tools write frontend code, generating modern, premium designs with proper animations, spacing, and visual quality instead of generic interfaces.
Multi-model OCR skills suite powered by Baidu PaddlePaddle, enabling intelligent text extraction and document parsing from images and documents.
Manage real-time OKX onchainos DEX WebSocket streams through the `onchainos ws` CLI (`start` / `poll` / `stop` / `list` / `channels` / `channel-info`) or a custom Python/Node/Rust client against `wss://wsdex.okx.com/ws/v6/dex` (HMAC-SHA256 login, 25s ping). Covers all 9 channels — `price`, `dex-token-candle{period}`, `price-info`, `trades`, smart-money / address / new-signal trackers, meme-pump new-token and metrics — including poll filters and per-channel params like `--token-pair`, `--chain-index`, `--idle-timeout`.
Give AI agents autonomous payment ability via the x402 HTTP 402 protocol and MCP tools — including per-task and per-session budgets, allowlisted recipients, rate limits, and non-custodial ERC-4337 wallets so agents can pay for APIs or other agents without custodial risk. Spending policy is set by the orchestrator, not the agent.
YC-office-hours-style product diagnostic that pressure-tests the "why" before any feature is built — asks who it's for, what the pain is, the 10-star version, the MVP, the anti-goal, and the success metric, then outputs a `PRODUCT-BRIEF.md` with go/no-go. Also runs founder review, user journey audit, and feature prioritization modes.
A CLI tool for UI automation and app observability on iOS, tvOS, macOS, Android, and AndroidTV, built for agent-driven workflows. Provides structured accessibility tree snapshots, deterministic interaction, session-aware replay, and debugging evidence collection including logs, network inspection, and performance monitoring.
Context Keeper — persistent per-project memory for Claude Code that auto-loads project context on session start, tracks sessions with git activity, and writes into Claude native memory via `/ck:*` commands backed by deterministic Node.js scripts for consistent behavior across models.
Post-deploy regression monitor that watches a deployed URL for HTTP status, console errors, network failures, Core Web Vitals (LCP/CLS/INP), missing key elements, and API SLA. Supports quick single-pass, sustained interval watches (`--interval 5m --duration 2h`), and staging-vs-prod diff mode with critical/warning/info alert tiers.
Guides advanced pandas usage for data analysis, including DataFrame manipulation, complex aggregations, performance optimization, and data visualization workflows.
Intercepts the response flow to offer the user an informed choice about answer depth *before* Claude answers — estimates input tokens, classifies prompt complexity (simple/medium/complex), and presents response-size options. Triggers on phrases like "short version", "tldr", "token budget", or Spanish equivalents; silently maintained once a level is chosen in a session.
Analyzes code naming conventions across variables, functions, classes, files, database tables, and API endpoints, identifying inconsistencies and suggesting improvements by language.
A curated awesome list of Claude Skills by Composio, covering a wide range of development skills and integrations for AI-assisted workflows.