Dashboard / Repos / Skill 0

Skill 0

C 68 completed
Ai Ml
monorepo / markdown · small
398
Files
84,901
LOC
6
Frameworks
12
Languages
OverviewFiles & MetricsGit ActivityCall GraphSecurityReports

Pipeline State

completed
Run ID
#370404
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
78.47
Framework unique
—
Isolation
—
Last stage change
2026-05-10 03:35:24
Deduplication group #65550
Member of a group with 2 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/

AI Prompt

Create a system, Skill-0, designed to parse and classify the internal structure of AI/Chatbot Skills, specifically targeting Claude Skills and MCP Tools. The core functionality should implement a ternary classification system: Action, Rule, and Directive. I need to model the various Directive Types like `completion`, `knowledge`, `principle`, `constraint`, `preference`, and `strategy`, including optional provenance tracking for both 'basic' and 'full' levels. Since it involves intelligent discovery, please incorporate semantic search using vector embeddings. The project should utilize FastAPI for the API and include components for testing using pytest and Vitest, and the frontend/UI should be styled with Tailwind CSS.
python fastapi react pytest vitest tailwind ai skill-parsing classification semantic-search
Generated by gemma4:latest

Catalog Information

Skill-0 is a ternary classification system for parsing the internal structure of Claude Skills and MCP Tools.

Description

Skill-0 is a classification system that parses AI/Chatbot Skills (especially Claude Skills and MCP Tools) into structured components. It includes semantic search powered by vector embeddings for intelligent skill discovery. The system organizes and defines the immutable parts of a Skill (or parts that change behavior when modified) into three categories: Action, Rule, and Directive.

الوصف

يعد Skill-0 نظام تصنيف ثنائي للتعرف على البنية الداخلية لتقنيات Claude و MCP. يحتوي على بحث semantics الموجهة بواسطة embeddings النصية للمعرفة الذكية. يقوم النظام بترتيب وتحديد الأجزاء غير المتغيرة من تقنية (أو الأجزاء التي تتغير سلوكها عند التعديل) في ثلاث فئات: Action، Rule، و Directive.

Novelty

7/10

Tags

skill-decomposition ternary-classification semantic-search vector-embeddings intelligent-skill-discovery

Technologies

fastapi huggingface numpy pydantic rich scikit-learn uvicorn

Claude Models

claude-sonnet-4.6 claude-opus-4.6

Quality Score

C
67.6/100
Structure
72
Code Quality
71
Documentation
66
Testing
75
Practices
51
Security
67
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (31% test-to-source ratio)
  • Code linting configured (eslint, ruff (possible))
  • Consistent naming conventions (snake_case)
  • Containerized deployment (Docker)
  • Properly licensed project

Weaknesses

  • 2 files with critical complexity need refactoring
  • 3 bare except/catch blocks swallowing errors
  • 2665 duplicate lines detected \u2014 consider DRY refactoring
  • 7 'god files' with >500 LOC need decomposition

Recommendations

  • Replace bare except/catch blocks with specific exception types

Security & Health

14.3h
Tech Debt (A)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (0)
About: code-quality intelligence by Repobility · https://repobility.com
MIT
License
22.8%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

markdown
58.7%
json
21.6%
python
15.9%
typescript
3.0%
shell
0.2%
yaml
0.2%
text
0.2%
javascript
0.1%
toml
0.1%
xml
0.0%
html
0.0%
css
0.0%

Frameworks

FastAPI React pytest Vitest Tailwind CSS Vite

Concepts (2)

Repobility · code-quality scanner for AI-generated software · https://repobility.com
CategoryNameDescriptionConfidence
Repobility · code-quality intelligence · https://repobility.com
auto_descriptionProject Description> A ternary classification system for parsing the internal structure of Claude Skills and MCP Tools80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/94609.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV