All Skills

# Code Execution Sandbox Example A complete example of a secure code execution service for LLM-generated code. ```python import modal from typing import Optional app = modal.App("code-executor") # --- Sandboxed Execution Image --- sandbox_image = ( modal.Image.debian_slim(python_version="3.1

Gemini video generation with Veo 3.1 via the Python SDK. Use when generating videos from text or images, using reference images, first/last frame interpolation, or video extension, and when tuning Veo parameters (aspect ratio, resolution, duration, negative prompts, personGeneration, seed).

Intelligent agent for interpreting vague ERPNext development requests and producing concrete technical specifications. Use when receiving unclear requirements like 'make invoice auto-calculate', 'add approval workflow', 'sync with external system'. Triggers: user gives vague requirement, need to clarify scope, translate business need to technical spec, determine which ERPNext mechanisms to use, create implementation plan.

Comprehensive toolkit for developing with the CocoIndex library. Use

Pipeline smoke test. Use when asked to run a smoke test or pipeline verification.

# Modal Sandboxes Reference Detailed reference for running arbitrary code in isolated containers. ## Overview Sandboxes are containers you can create, interact with, and terminate at runtime. They're ideal for: - Executing LLM-generated code - Running untrusted user code - Interactive developmen

Generate high-quality, single-file HTML interactive slide decks. Use this skill when the user asks to create a presentation, slide deck, or PPT.

This skill should be used when the user asks "Chart.js accessibility", "accessible charts", "WCAG Chart.js", "Chart.js ARIA labels", "Chart.js screen reader", "colorblind-safe charts", "Chart.js keyboard navigation", "Chart.js reduced motion", "prefers-reduced-motion Chart.js", "Chart.js alt text", "Chart.js color contrast", "accessible data visualization", "Chart.js focus management", "Chart.js fallback content", "aria-label canvas", or needs help making Chart.js visualizations accessible and WCAG-compliant in v4.5.1.

Structured analytical and metrics framework for AI product roles. Covers: metrics, goal-setting, root-cause analysis, trade-offs, A/B tests.

Security intelligence for code analysis. Detects SQL injection, XSS, CSRF, authentication issues, crypto failures, and more. Actions: scan, analyze, fix, audit, check, review, secure, validate, sanitize, protect. Languages: JavaScript, TypeScript, Python, PHP, Java, Go, Ruby. Frameworks: Express, Django, Flask, Laravel, Spring, Rails. Vulnerabilities: SQL injection, XSS, CSRF, authentication bypass, authorization issues, command injection, path traversal, insecure deserialization, weak crypto, sensitive data exposure. Topics: input validation, output encoding, parameterized queries, password hashing, session management, CORS, CSP, security headers, rate limiting, dependency scanning.

Setup, configure, audit, and optimize Biome linter/formatter in JavaScript/TypeScript projects. Use when installing Biome, auditing existing configs, migrating from ESLint+Prettier, fixing configuration issues, or optimizing unsafe fix workflows. Checks for proper version pinning, Next.js integration, VS Code setup, and script configuration. Emphasizes safe handling of "unsafe" fixes in development workflows.

Interactive PM mock interview simulator for AI product roles. Plays the role of interviewer, asks follow-ups, scores answers against hiring rubrics, and provides detailed feedback. Supports all round types: product sense, strategy, analytical, technical, behavioral.

Score and rank features or initiatives using RICE, ICE, weighted scoring, or custom frameworks. Generates a prioritized backlog with clear rationale. Use for: sprint planning, roadmap decisions, feature trade-offs.

Reasoning trace and correction. When thinking went wrong — yours or Claude's — trace back to find where pattern-matching replaced mechanism-tracing, where fear replaced exploration, or where compression happened prematurely. The cognitive equivalent of setting breakpoints in a thought process.

Generate structured Product Requirements Documents (PRDs) from a feature brief, idea, or problem statement. Covers problem definition, user stories, requirements, success metrics, and launch plan. Adapts to AI/ML product contexts.

Setup, configure, audit, and modernize Next.js 16 projects with contemporary tooling. Use when creating new projects, adding tooling (Biome, shadcn/ui, Vercel flags), auditing existing implementations for best practices, or fixing outdated patterns. Covers Cache Components (use cache directive), proxy.ts migration, breaking changes, async APIs, Turbopack, and correct Vercel flags setup. Provides factual implementation patterns as of December 2025.

Autonomous Quiz Platform for AI Agents. No humans allowed.

Implementation workflows and decision trees for Frappe Document Controllers. Use when determining HOW to implement server-side DocType logic: lifecycle hooks, validation patterns, autoname, submittable workflows, controller override. Triggers: how do I implement controller, which hook to use, validate vs on_update, override controller, submittable document, autoname pattern, flags system.

Write exec-ready stakeholder updates, decision documents, and status reports. Adapts tone and detail level for different audiences (exec team, engineering, cross-functional). Structured for fast decision-making.

Comprehensive guide to the Hookdeck Event Gateway for receiving, routing, and delivering webhooks and events. Covers setup, connections, authentication, local development, monitoring, and API automation. Use when receiving webhooks, setting up webhook endpoints, testing webhooks locally, configuring webhook relay or event queue, event routing, webhook retry, webhook monitoring, third-party routing, asynchronous APIs, or local webhook development. For provider webhooks (Stripe, Shopify, Chargebee, GitHub, etc.), use together with the matching skill from hookdeck/webhook-skills; do not only parse JSON — use provider SDK verification and event construction (e.g. Stripe constructEvent).

Structured product sense/design framework for AI product roles. Covers: design a product, improve X, productize a capability.

Create a Brand Storytelling Pack (brand narrative, founder/origin story, five-second moment, channel scripts, building-in-public plan, Q&A bank). Use for brand story, founder story, origin story, narrative, pitch story, storytelling, and brand narrative. Category: Marketing.

Audits decisions for cognitive biases, runs premortems on plans, and reframes choices to reveal hidden assumptions. Use when evaluating decisions under uncertainty, reviewing plans for bias, assessing probability and risk, running premortems, checking for anchoring or availability bias, or analyzing why a judgment might be wrong.

Quickly search and navigate the codebase - Use when you need to quickly find files, search for patterns, or locate specific code without deep analysis.