sijiao-skill

Generates stateful tutor skills from 8-route research and learning-science curriculum distillation.

17|1|Updated Jun 16, 2026
One-click install
npx skills add https://github.com/swaylq/sijiao-skill --skill sijiao-skill-swaylq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sijiao-skill
Source: https://github.com/swaylq/sijiao-skill
Command: npx skills add https://github.com/swaylq/sijiao-skill --skill sijiao-skill-swaylq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Generic AI study plans are one-off, stateless documents that forget your progress. This Skill turns any skill you want to learn into a persistent private tutor that remembers where you are, adapts exercises to your level, and schedules spaced-repetition reviews. ## Core Features & Use Cases - 8-Route Research Pipeline: Runs parallel research on knowledge maps, canonical resources, expert learning paths, deliberate practice, common pitfalls, assessment rubrics, feedback communities, and motivation before building anything. - Three-Layer Tutor Generation: Produces a self-contained {skill}-learn directory with a Dreyfus-staged curriculum (curriculum.json/md), a tutor SKILL.md, and a private learner-state.json with SM-2-lite spaced repetition. - Quality Gates: Validates prerequisite DAGs for cycles, requires assessable exercises per module, enforces behavioral competence checks, and honestly caps the ceiling at "competent". - Use Case: Say "learn Rust" and receive a rust-learn tutor that loads your saved state each session, quizzes due review items, targets your known weak spots, and grades your exercises. ## Quick Start Tell your agent "learn rust" and confirm your current level, goal, weekly hours, and locale so it can research and generate a personalized tutor skill.

Frequently Asked Questions about sijiao-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a personalized AI tutor for learning a new skill?▼

Install the skill into your agent's skills directory, then say "learn X" for any skill. It confirms your level, goal, and weekly hours, runs 8 parallel research routes, and generates a self-contained tutor directory with curriculum, teaching protocol, and progress tracking.

What is the difference between this and asking ChatGPT for a study plan?▼

A study plan is a one-off static document. This generates a stateful tutor that loads your learner-state.json each session, surfaces due spaced-repetition items, targets your recorded weak spots, and grades exercises against your current mastery level.

Which AI agents and hosts does the generated tutor support?▼

Generated tutor skills work with any host that reads SKILL.md files, including Claude Code, OpenClaw, Codex, and Hermit. The included install.py script copies a generated skill into the target host's skills directory.

Can an AI tutor teach physical skills like fitness or skincare?▼

It generates the curriculum but applies honest degradation: modules requiring physical feedback, medical judgment, or hands-on correction are explicitly flagged and handed off to self-reporting, video review, or professionals rather than pretending the AI can grade them.

What are the limitations of an AI-generated learning path?▼

The ceiling is honestly capped at the Dreyfus "competent" stage, meaning independent handling of routine tasks; proficiency and expertise require years of real practice. Resources and tools decay within 3-6 months and need incremental refresh, while the prerequisite graph and pedagogy remain stable.