Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude Code
Implement a spec or delivery plan by dispatching each slice to a fresh sub-agent, verifying the result, and maintaining execution state. Use when the user chooses to implement from spec.html or an optional plan.md.
Skill Claude CodeCodex
Migrate Notion pages across different workspaces/accounts, preserving formatting, images, and content structure. Use when the user wants to copy, migrate, or transfer Notion documents between accounts, workspaces, or databases, or when they mention cross-account Notion migration.
Skill Claude CodeCodex
Helps engineers build and deliver executive decision briefs that drive alignment, secure funding, and close decisions in a single meeting. Use when preparing for executive presentations, sprint reviews reframed as strategy sessions, funding asks, technical recommendations to C-suite or VPs, or any situation where an…
Skill Codex
Clarify ambiguous ideas or implementation requests through an evidence-grounded Socratic interview and produce an execution-ready requirements specification before planning or coding. Use when the user invokes $spec-interview, asks to be interviewed, says not to assume, or provides a broad request without clear scope…
Skill Claude Code
A workflow for end-to-end UI testing, which checks complete user journeys across a web application in a browser.
Skill Claude CodeCodex
Genera una WBS (Work Breakdown Structure) dettagliata in Markdown dai documenti DESIGN e DEVELOPER di un progetto ENGenius su DocMind. Usa questa skill ogni volta che l'utente vuole: generare una WBS di progetto IT, stimare effort e risorse (GG/u con e senza AI), creare un cronoprogramma, dimensionare il team…
Skill Claude CodeCodex
AI Agent development assistant. Use when building autonomous agents, multi-agent systems, or LLM-powered applications. Covers Claude SDK, LangChain/LangGraph, and custom frameworks.
Skill Claude CodeCodex
Plan an OpenSpec change and sync it to the MCP Task Hub as tiered, chunked tasks. Use when the user wants to plan/queue work for the agent drain loop ("hub-plan", "sync tasks to the hub", "queue up this change"). Spec artifacts always come from the official OpenSpec (opsx) tooling — this skill layers reconciliation…
Skill Claude CodeCodex
A reporting workflow for analysing AI news for the TrendLife AI Taskforce. It produces daily, weekly, or monthly reports prepared for sharing with others.
Skill Claude CodeCodex
Performs a comprehensive code review by analyzing local changes or remote pull requests against Clean Code, SOLID principles, Design Patterns, and Test Code standards.
Skill Claude Code
Analyzes an entire codebase and generates a concise master index file named MASTER.md. The output is a fast-lookup reference — file names, class names, function names, data flow — designed for AI tools to locate the right symbol instantly without re-scanning the codebase. Triggers on phrases like "document this…
Skill Claude CodeCodex
Start implementing part or all of a designed software project.
Skill Claude CodeCodex
Build, migrate, maintain, and test Chef Infra cookbooks using modern custom resource patterns for the sous-chefs organization. Use when: building a new Chef cookbook with custom resources, migrating legacy library-based resources to modern resources/, fixing CI failures in a sous-chefs cookbook, adding ChefSpec or…
Skill Codex
A self-initializing report-writing workflow. Use this skill when the user wants Codex to create or use a standardized report project for homework reports, experiment reports, course reports, technical reports, or template-based answer files. On first use, the skill detects whether the current directory is initialized…
Skill Claude Code
React Hook Form patterns with Zod validation. Use when implementing forms, validation schemas, form state management, edit forms with unsaved changes, or array fields.
Skill Claude CodeCodex
A focused guide for implementing image generation with LLM Gateway's API, designed for AI agents and LLMs.
Skill Claude CodeCodex
Build complete Hyperterse MCP server projects from natural language. Use when the user asks to create an API, backend, MCP server, database-backed tools, or mentions Hyperterse.
Skill Claude CodeCodex
Comprehensive TRACE32 (T32) debugger skill for ARM64/AArch64 debugging on Exynos platforms. Use this skill whenever the user mentions T32, TRACE32, Lauterbach, JTAG debugging, CMM scripts, PRACTICE scripting, ARM64 register inspection, SFR dumps, breakpoint debugging, target control, core dumps, exception analysis…
Skill Claude CodeCodex
Create beautiful, elegant Excalidraw diagrams based on user intent. Use when user asks to draw, visualize, diagram, sketch, illustrate concepts, create flowcharts, architecture diagrams, mind maps, process flows, or any visual representation. Triggers on keywords like "draw", "diagram", "visualize", "sketch"…
Skill Codex
Prevent agent-generated code from introducing silent fallbacks, swallowed failures, speculative abstractions, premature shared architecture, and unnecessary complexity. Use when implementing new features, bug fixes, refactors, cleanup passes, or architecture decisions where Codex should keep changes explicit, local…
Skill Claude CodeCodex
Teach AI agents to call SERPHouse REST APIs with curl for web search, SERP data, and SEO intelligence.
Skill Claude CodeCodex
Generate a complete, single-file HTML landing page for any product, service, or physical store. Input: a URL / text description + optional module selection. Output: a white, clean, responsive landing page saved as .html on the user's desktop. Automatically detects industry type (SaaS/tech, food-beverage/store…
agenticstack-sh/agenticstack-skills
Skill Claude CodeCodex
Given what the user wants to add to their app, pick the right tool and explain how to get started — no comparison needed.
Skill Claude CodeCodex
Run a second model as a subagent without your repository's ambient context reaching it. A coding agent injects git branch, changed files and recent commit messages into every subprocess prompt, and that background text is scored alongside your actual question -- so a benign request can be declined because of what your…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: