Claude Skills by alessiomarcone

Selects and designs general Codex setup and operation across the ChatGPT desktop app, CLI, IDE, cloud, AGENTS.md, permissions, MCP, scheduled tasks, and SDK. Use for Codex surface choice, repository setup, or operating workflows; specialist prompt, subagent, skill, and plugin authoring routes to those narrower skills.

Designs safe, source-grounded Cowork workflows with folders, connectors, skills, schedules, approval gates, and human verification. Use when the user asks how to delegate operational work in Cowork, automate recurring briefs, customize Cowork, or design a multi-source legal, sales, marketing, finance, or small-business workflow.

Turns one course lesson, tutorial, documentation page, article, workshop, video, or transcript into a compact, structured, verifiable knowledge card. Use when the user asks to distill source material, create a knowledge card, summarize a source for reuse, or add grounded material to this pack.

Builds a sequenced learning path from verified official Anthropic and OpenAI course, tutorial, guide, video, and workshop catalogs. Use when the user asks where to start, which Claude or Codex course to take, how to learn prompting, skills, plugins, subagents, MCP, Cowork, or the API, or how long a study plan will take.

Routes ambiguous mechanism comparisons to the smallest appropriate agent mechanism and skill. Use when the user is unsure whether they need instructions, a prompt, skill, subagent, hook, scheduler, MCP, plugin, Claude workflow, or Codex workflow; if the artifact is already selected, its specialist skill wins.

Designs, packages, validates, and prepares distributable plugins containing skills and optional supported extensions. Use when the user asks to build, migrate, publish, install, distribute, or troubleshoot a Claude Code, Cowork, ChatGPT, or Codex plugin or marketplace; not for creating one standalone skill.

Improves, rewrites, or designs concise prompts with clear outcomes, context, boundaries, output requirements, and verification. Use for direct requests such as “improve this prompt,” for Claude or Codex task formulation, weak-response troubleshooting, or turning a rough objective into a ready-to-run task.

Turns a repeated workflow into one narrow, reusable, validated agent skill with reliable triggers and progressive disclosure. Use when the user asks to create, revise, split, review, or test a SKILL.md workflow for Claude, Codex, or another Agent Skills-compatible surface; not when the request is to distribute a bundle as a plugin.

Decides whether selected delegated work needs agents and designs a strict, product-correct subagent contract with isolated context, bounded tools, authority, deliverables, and tests. Use when the user asks to create, configure, delegate to, or troubleshoot Claude or Codex subagents, parallel agents, custom agents, or managed-agent workflows; not for open mechanism comparisons.

Fact-checks and stress-tests AI answers or artifacts with claim-level evidence, uncertainty, anti-hallucination, and anti-sycophancy checks. Use for brief or detailed requests to check, verify, or review an answer before sending or publishing, and for consequential legal, financial, technical, or customer-facing decisions.