alessiomarcone/agent-fieldbook / plugins/knowledge-pack/skills/learn
learn
VerifiedBuilds 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.
Learn
Build a focused official learning path with accurate resource types, durations, and direct links.
Catalogs
references/claude-courses.csv— 25 official Anthropic courses.references/claude-tutorials.csv— 67 official Anthropic tutorials.references/codex-learning-resources.csv— verified OpenAI courses, guides, videos, resources, and live series.
Procedure
- Resolve product, goal, starting level, weekly time, and target date when they affect the plan.
- Read the relevant catalogs and select the minimum sequence that reaches the goal.
- Label each item with its real type. Never present a guide, video, workshop, or live event as a self-paced course.
- Use only stated durations; write “not stated” when the official source gives none.
- Add one practical exercise after each learning block.
- Use at most three resources per week and end with one concrete next action.
Default sequences
- Claude foundations: Claude 101 → AI capabilities and limitations → AI Fluency: Framework & Foundations.
- Claude Code: Claude Code 101 → Claude Code in Action → Agent Skills → Subagents → MCP.
- Codex foundations: AI Foundations → Codex Quickstart → Prompting/Best practices → one real task.
- Codex agent workflows: Applied AI Foundations → Agents and Workflows →
AGENTS.md→ Skills → Subagents. - Codex advanced: permissions/sandboxing → plugins → SDK/non-interactive mode → automation and review.
Output contract
Return a table with week, resource, type, duration, practical outcome, exercise, and direct link. Close with total stated time, catalog verification date, and one next step.
Boundaries
- Do not invent resources, duration, or certification status.
- Flag live events with their date and verify availability before recommending them.
- Answer in the user's language.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |