Skills

from getpaperclipai/paperclip

from getpaperclipai/paperclip

Creates and configures a Salesforce Custom Application to host React UI bundles in Lightning Experience, generating the CustomApplication metadata for App Launcher visibility.

Provides expert guidance for implementing secure, efficient, and compliant Stripe payment integration best practices

An AI-powered video clipping skill that converts long videos into ranked vertical short clips via a managed API call, handling server-side transcription, virality ranking, deduplication, and face-tracked auto-cropping without requiring local Whisper or LLMs.

The official WooCommerce monorepo containing the core WordPress e-commerce plugin, extensions, packages, and development tools for building online stores.

A backend code review skill from the Dify project, an open-source LLM application development platform that enables building AI workflows, RAG pipelines, and agent capabilities with a visual canvas and hundreds of model integrations.

A skill for generating, auditing, and scoring design systems across 10 visual dimensions, detecting AI-generated design patterns ("AI slop"), and producing design tokens, preview pages, and consistency reports.

An auto-generated data engineering skill from ara.so that provides guidance for building ETL pipelines based on the Harvard Artifacts Collection Data Engineering Analytics App project. Part of a collection that scans GitHub every 30 minutes for trending data engineering repos and generates installable agent skills.

Generates quick statistical summaries for trading strategy backtests using VectorBT.

An official NVIDIA-verified skill that guides launching and managing TAO Toolkit training workflows on NVIDIA GPU infrastructure, covering job orchestration, monitoring, and pipeline execution.

A collection of 255+ universal agentic skills for AI coding assistants including Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, and Cursor.

`/hub:spawn` launches N parallel subagents in isolated git worktrees using a single message with multiple Agent tool calls for true parallelism. Supports `optimizer`, `refactorer`, `test-writer`, and `bug-fixer` templates from `references/agent-templates.md` and writes per-agent dispatch posts to `.agenthub/board/dispatch/`.

A collection of markdown-based AI agent skills covering CRO, copywriting, SEO, analytics, paid ads, email, and growth engineering, installable into Claude Code, Cursor, Codex, and other compatible coding agents.

A knowledge pack of agent skills for AI coding assistants providing framework-specific, best-practice guidance for Odoo development, including ORM usage, conventions, and module patterns.

Agent skills for financial analysis and trading using yfinance, covering earnings previews, estimate analysis, stock liquidity, ETF premiums, options payoff, and trading strategies. For educational and informational purposes only.

`/em:challenge` runs a pre-mortem on any plan by extracting core assumptions, rating each by confidence × impact, mapping dependency chains, and assessing reversibility. Outputs a structured Challenge Report with vulnerability map, kill switches at 30/60/90 days, and hardening actions tailored to product, GTM, hiring, or fundraising plans.

A Claude Code skill that transforms AI-generated academic text into natural, human-like scholarly writing, specifically designed for social science researchers and non-native English speakers.

Plans and executes semantic topic clusters using a hub-and-spoke model for SEO-optimized blog content. Part of the claude-blog skill suite, it maps related topics around a seed keyword and generates interlinked pillar and cluster articles.

Transforms UI codebases into fully internationalized systems by configuring i18n frameworks, replacing hard-coded strings, and ensuring comprehensive locale coverage.

Creates and validates Salesforce flows with 110-point scoring across 6 categories, following Winter '26 best practices for record-triggered, screen, autolaunched, and scheduled flows.

`/em:stress-test <assumption>` — the Executive Mentor command for breaking business assumptions (revenue projections, TAM, competitive moat, hiring velocity, retention) before the market does. Runs five steps: isolate the assumption in testable form, find counter-evidence from comparable failures, model bear/stress/catastrophic downsides, calculate sensitivity, then propose validation / contingency / early-warning hedges. Ends with a structured output of sources, downside scenarios, sensitivity, and specific hedges.

Fine-tunes NVIDIA Cosmos Reason models using TAO Toolkit's low-code microservices, enabling customization of this reasoning-capable vision foundation model with your own data for edge or cloud deployment.

An official NVIDIA-verified skill that guides porting Hugging Face models to NVIDIA TAO Toolkit format, covering model conversion, compatibility checks, and optimization for NVIDIA deployment pipelines.

Runs NVIDIA TAO Toolkit's AutoML pipeline to automatically search for optimal hyperparameters and model configurations, streamlining the training of vision AI models without manual tuning.

A CLI skill that calls Wind's Alice Agent via A2A protocol with SSE streaming to execute specialized financial analysis skills such as stock DD checklists, company one-pagers, fact verification, and thematic stock screening on the Wind AIFin Market platform.

A comprehensive developer toolkit providing Claude Code skills and plugins for software development workflows, code quality, and productivity.

Code quality skill for Turso's production database with correctness-first Rust patterns, exhaustive error handling, invariant assertions, and rules against workarounds or quick hacks

Ingests AI copilot conversation history into an LLM-maintained personal knowledge wiki, compiling persistent knowledge instead of repeated queries.

Rust mental model skill for learning Rust concepts like ownership, borrow checker, and memory layout through analogies and intuitive explanations.