Skillget

skills

agent
Guvenlik Denetimi
Uyari
Health Uyari
  • License — License: NOASSERTION
  • No description — Repository has no description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Gecti
  • Code scan — Scanned 6 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool is a pipeline for converting raw course materials into optimized MarkdownFlow teaching scripts and deploying them as live courses on the AI-Shifu platform. It also includes a skill for providing course-direction advice with market and competitor analysis.

Security Assessment
The overall risk is Low. The light code scan checked 6 files and found no dangerous patterns. No dangerous permissions are requested, and no hardcoded secrets were detected. While the tool does interact with the AI-Shifu platform (requiring network requests for deployment, listing, and publishing courses), these are standard operational functions for this type of CLI. It does not appear to execute hidden or malicious shell commands.

Quality Assessment
The project is very new and has low community visibility, currently sitting at only 5 GitHub stars. However, it is actively maintained, with the most recent push occurring just today. The repository lacks a defined license (marked as NOASSERTION) and a description, which are standard indicators of project maturity. Users should be aware that the small community means fewer eyes have reviewed the code.

Verdict
Use with caution — the code appears safe, but the lack of a clear license and a small user base means you should verify compatibility with your commercial needs before integrating.
README.md

AI-Shifu Skills

中文 README

Reusable AI-Shifu skills for course production, from topic selection to deployment.

Included Skills

  • ai-shifu-course-creator: convert raw course material into optimized MarkdownFlow teaching scripts and deploy them as live AI-Shifu courses through a five-phase pipeline (segmentation, orchestration, generation, optimization, deployment).
  • course-direction-advisor: turn source materials into evidence-bound, market-fit course-topic decisions with competitor analysis, pricing guidance, and GO/HOLD/REWORK/NO-GO recommendations.

The course-creator skill includes runnable examples under skills/ai-shifu-course-creator/examples/.

Repository Layout

skills/
  ai-shifu-course-creator/
  course-direction-advisor/

Usage

The skill keeps SKILL.md as the behavior source of truth.
Core skill metadata lives in skills/ai-shifu-course-creator/skill.yaml.

Course Authoring & Deployment Paths

Choose one path based on control needs:

Path A: End-to-End (Recommended)

Use when you want the fastest route from raw material to a live deployed course.

  1. Prepare source material (transcript or course documents).
  2. Run Phase 1–4 to produce optimized MarkdownFlow lesson scripts.
  3. Run Phase 5 to build, import, and publish to the AI-Shifu platform.

Expected artifacts:

  • Structured segmentation
  • Lesson-by-lesson MarkdownFlow scripts
  • Course index and global variable table
  • Optimized lesson prompts and risk report
  • Live course on the AI-Shifu platform

Path B: Author Only

Use when you need optimized MarkdownFlow scripts without deploying. Sub-paths:

  • Segment only: Phase 1 for semantic segments and manual review.
  • Generate only: Phase 3 on pre-existing segments.
  • Optimize only: Phase 4 to audit and improve existing scripts.

Path C: Deploy Only

Use when you have pre-existing MarkdownFlow files ready to deploy:

  1. Organize MarkdownFlow files in a course directory.
  2. Run build --course-dir ./course-a/ to generate the import file.
  3. Run import --new --json-file ./course-a/shifu-import.json to create the course.
  4. Run publish <shifu_bid> to make it live.

Path D: Manage Existing

Use management commands (list, show, update, rename, reorder, delete, publish, archive) on courses already on the platform.

Validate Metadata

python3 scripts/validate_skill_quality.py

Language Policy

Skills are language-flexible for course generation. From a user perspective:

  • If you explicitly request an output language, that language is used.
  • If you provide target_language, it is used when no stronger explicit instruction exists.
  • If neither is provided, the system uses session preference and prompt language signals.
  • If language is still ambiguous, it falls back to en-US.
  • If you need bilingual output, set bilingual_output: true.

Recommended controls for predictable language output:

  • target_language (for example zh-CN, fr-FR, ja-JP)
  • bilingual_output (true|false)
  • term_policy (preserve|translate|mixed)
  • quote_policy (translate_only|original_plus_translation)

AI-Shifu

This suite is part of AI-Shifu's course authoring workflow: https://ai-shifu.com

Yorumlar (0)

Sonuc bulunamadi