Duolingo Learning OS

Name: Duolingo Learning OS
Author: ivangdavila

功能描述

Run a Duolingo-like multi-topic learning system with AGENTS routing, lesson loops, streaks, and spaced review.

使用说明 (SKILL.md)

Setup

On first use, read setup.md for routing, filesystem bootstrap, and topic activation.

When to Use

User wants to learn one or more subjects with short daily lessons, instant feedback, streak pressure, and ongoing review. Agent runs a Duolingo-style operating system (not just advice) with topic folders, per-topic curriculum, cross-topic planning, and optional AGENTS router integration.

Architecture

State lives in ~/duolingo/. See memory-template.md for global state and per-topic file templates.

~/duolingo/
|-- memory.md                    # Global status and active topic map
|-- router/
|   |-- topics.md                # Canonical list of active topics and trigger phrases
|   `-- agentsmd-snippet.md      # Snippet to keep AGENTS routing in sync
|-- topics/
|   |-- english/
|   |   |-- profile.md           # Goal, level, pace, constraints
|   |   |-- curriculum.md        # Skill tree and lesson units
|   |   |-- queue.md             # Next lessons and review backlog
|   |   |-- sessions.md          # Session history and outcomes
|   |   `-- checkpoints.md       # Weekly and milestone checks
|   `-- cooking/                 # Same structure for any other topic
`-- archive/                     # Retired topics and old curriculum versions

Quick Reference

Topic	File
Setup flow	`setup.md`
Global memory template	`memory-template.md`
Filesystem bootstrap	`blueprint.md`
AGENTS routing rules	`activation-routing.md`
Lesson runtime loop	`lesson-loop.md`
XP/hearts/streak economy	`progression.md`
Multi-topic retention ops	`retention-ops.md`
Topic namespace templates	`topic-template.md`
Weekly health review	`launch-scorecard.md`

Core Rules

1. Bootstrap the Learning OS Before First Lesson

If ~/duolingo/ is missing or empty, create the full scaffold from blueprint.md. Do not start teaching without:

global memory file
router files
at least one topic namespace

2. Offer Optional AGENTS Router Integration

If the user wants automatic routing, provide the AGENTS router snippet from activation-routing.md. Never auto-edit AGENTS from this skill. Generate snippet text only and let the user apply it. If the user skips router integration, keep the skill fully manual and user-invocable.

3. Keep Each Topic Isolated, Then Coordinate Globally

Every topic gets its own namespace under ~/duolingo/topics/\x3Ctopic-slug>/. Never mix files across topics. Global planning may schedule multiple topics in one day, but lesson state stays per-topic.

4. Run Lessons as Tight Interactive Loops

Use lesson-loop.md for every session:

micro-challenge
learner attempt
immediate correction
reinforcement challenge
queue update

One loop should finish in about 60-90 seconds.

5. Support Concurrent Tracks Without Context Loss

User can learn multiple topics at once (for example English and cooking). For each session, select one active topic, load only that namespace, then update global planner with:

completion result
next due lesson
next review date

6. Use a Transparent Progression Economy

Apply XP, hearts, streaks, and mastery rules from progression.md. Rewards must reflect demonstrated learning, not random activity. When motivation drops, adjust pacing before adding gamification complexity.

7. Prioritize Retention and Review Over New Content Volume

Follow retention-ops.md and launch-scorecard.md weekly. A healthy system always knows:

what to review now
what to practice next
why the learner did or did not return

Common Traps

Storing all subjects in one shared file -> topic collisions and broken continuity
Activating without AGENTS router update -> skill never triggers when user asks to learn
Adding many lessons before review queues exist -> fast forgetting and fake progress
Running long lectures instead of micro-loops -> weak engagement and poor retention
Using streak pressure without recovery path -> churn after one missed day
Tracking only XP and ignoring checkpoint quality -> progress appears good while skill depth is low

Security & Privacy

Data that stays local:

Learning state in ~/duolingo/
Topic curriculum, attempts, and review queues

This skill does NOT:

Send data to external services
Access files outside ~/duolingo/ unless user asks explicitly
Modify its own SKILL.md

Related Skills

Install with clawhub install \x3Cslug> if user confirms:

learning - Teaching and explanation tactics per learner profile
english - Language-specific practice patterns for one common track
course - Curriculum decomposition and sequence planning
retention - Habit systems and comeback mechanics
coach - Accountability prompts and progress reflection

Feedback

If useful: clawhub star duolingo
Stay updated: clawhub sync

安全使用建议

This skill is instruction-only and stores all data locally under ~/duolingo/. Before installing or using it: (1) confirm you are comfortable with a folder being created/updated in your home directory and inspect its contents after first run; (2) review the AGENTS router snippet before pasting it into any global routing config — the skill will not auto-edit AGENTS but will ask you to apply the snippet; (3) if you need absolute assurance about data flow, ask the publisher for a full source bundle or run the skill in a restricted account to inspect the files it creates; and (4) note the skill may be invoked by the agent automatically under platform defaults — if you prefer only manual runs, disable autonomous invocation on your agent or avoid applying automatic routing.

功能分析

Type: OpenClaw Skill Name: duolingo Version: 1.0.0 The Duolingo Learning OS skill is a well-structured framework for managing local learning tracks. It operates entirely within the `~/duolingo/` directory to maintain state, curriculum, and progress. The skill follows safe practices by requiring manual user intervention for integration with external routing systems (AGENTS.md) and lacks any indicators of data exfiltration, malicious command execution, or unauthorized persistence.

能力评估

✓ Purpose & Capability

Name, description, and all required artifacts line up: the skill declares and uses a local config path (~/duolingo/) for curriculum, queues, and memory and does not request unrelated credentials or binaries.

ℹ Instruction Scope

Runtime instructions are limited to creating and updating files under ~/duolingo/, composing an AGENTS router snippet (but explicitly not auto-editing AGENTS), and running short lesson loops. This is within scope, but note the skill instructs the agent to 'read setup.md silently' on first use and to create/modify files under the user's home directory — both are reasonable for persistence but worth auditing if you want full transparency over what is written.

✓ Install Mechanism

No install spec or downloaded executables — instruction-only skills carry minimal disk-install risk because no archives/binaries are fetched or executed.

✓ Credentials

No environment variables, credentials, or external endpoints are requested. The only required resource is a config path (~/duolingo/), which is proportional to the stated need to persist lessons and state.

✓ Persistence & Privilege

The skill requests persistent storage under its own directory only. It does not set always:true, does not request elevated privileges, and explicitly forbids auto-editing AGENTS (it only generates snippets). Autonomous invocation is allowed by default on the platform but is not combined here with broad credentials or network access.

版本历史

v1.0.0

Reworked into a full Duolingo-style learning system with topic routing, multi-topic tracks, and persistent lesson operations.

元数据

Slug duolingo

版本 1.0.0

许可证 —

累计安装 4

当前安装数 3

历史版本数 1

常见问题