Learning os

    1

    AI Learning OS is a portable AI skill that turns any subject into an approved learning roadmap, detailed source-grounded notes, structured study sessions, and evidence-based progress tracking inside your workspace.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    learning-os

    Example session with this skill installed

    I just finished 30 minutes studying AI tool calling. Review my understanding:

    The AI suggests a tool call; the application runs it.
    Valid arguments don’t automatically mean the action is authorized.
    If a request times out, keep retrying until it works.
    Tell me what I got right, correct my mistakes, and show my progress update before saving.

    • Read your context and instructions
    • Compiled the learning-os

    Good progress—one important gap
    You got 2 of 3 checks right:

    ✅ The application executes tool calls.
    ✅ Valid arguments still need permission checks.
    ⚠️ Retrying blindly can repeat an action that already succeeded.
    Remember: A timeout doesn’t always mean failure. Check the outcome or use duplicate protection before retrying.

    Proposed progress
    Study time: 30 minutes
    Outcome: Partially complete
    Mastery: Still learning—no upgrade yet
    Next step: Practice safely recovering from a timed-out request.

    Nothing saved yet. Confirm the update to record your session.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    AI Learning OS provides a reusable learning workflow for AI coding assistants. It defines how learning is organized; your subjects, notes, source files, and progress remain in your own workspace rather than inside the skill package.

    1. Builds a learning path before creating files

    You choose a subject, and the assistant drafts a beginner-to-advanced roadmap containing modules, topics, prerequisites, objectives, and a recommended sequence. You can revise it before approving the learning path and folder structure.

    1. Converts source material into connected, detailed notes

    The workflow accepts existing notes, text, PDFs, slides, screenshots, pasted material, and links. Instead of producing only short summaries, it processes long sources sequentially, tracks coverage, and routes content into the appropriate topic notes.

    Notes capture mental models, mechanisms, examples, implementation details, trade-offs, common mistakes, connections, source references, and mastery checks. Relevant material outside the approved roadmap goes into an extra/ area for possible inclusion later.

    1. Structures study sessions and tracks progress

    The skill prepares study sessions around a topic, source, and evidence goal. At session completion, it updates subject records and appends a canonical CSV study-log entry. Its documented workflows also cover subject status, weak-topic review, source refresh, and master-note exports.

    1. Keeps learning material organized and traceable

    Each subject has its own root-level folder containing notes and assets. Shared operational state lives separately in .learning/. Source provenance, deduplication, conflict tracking, and mastery evidence help make the knowledge base reviewable rather than just a collection of generated text.

    1. Supports controlled reorganization

    When you change a learning path, the skill previews affected topics, note moves, merges, splits, and link updates. It requires confirmation before applying the plan and preserves original images and uploads. Legacy-workspace migration also requires an explicit preview and approval.

    Main commands

    • Command: Purpose
    • /learn-new-start: Design and approve a subject’s learning path
    • /learn-day-start: Prepare a study session
    • /learn-note: Capture notes or integrate source material
    • /learn-day-end: Record session outcomes and update progress
    • /learn-learningpath-updated: Reconcile notes with an edited roadmap

    Portability It is designed for APM-compatible environments, including Windsurf, Claude Code, GitHub Copilot, and other supported targets. No particular model, database, API key, or cloud service is required; external integrations are optional.

    Design note: Separating reusable workflows from personal learning data is a sound choice. Push it further by judging progress through demonstrated understanding—not note volume or completed sessions alone.

    Requires pre-confirmed workspace root. No filesystem atomicity. Network refresh requires explicit config and per-use consent. Prevents arbitrary writes outside registry-approved folders.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a local architect for your knowledge, using a strict schema to prevent the broken links and fragmented notes that usually occur when using generic AI prompts for long-term study.

    The skill is designed to work with AI agents that have local filesystem access, as it manages a specific directory structure and uses transaction logic to safely move Markdown and YAML files.

    Yes, the skill includes a 'learn-migrate' command specifically designed to port legacy 1.x layouts and unstructured notes into the current 2.0.0 schema while maintaining data integrity.

    Unlike standard chat interactions, this skill uses staging and rollback directories to ensure that file operations are atomic, protecting your data from corruption if an error occurs.

    You receive the complete skill package including the 'learn-new-start', 'learn-note', and 'learn-day' command protocols, along with the schema documentation for the registry-approved folder structure.

    No, the skill operates on a 'local-first' principle; it processes your provided PDFs, code, and text files within your approved root folders and does not perform external network fetches without your consent.

    New in Agents & Orchestration