type-classifier

Classify Obsidian research notes by inferring missing `类型` frontmatter values.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/xingchen2202/obsidian-ai-knowledge-system --skill type-classifier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: type-classifier
Source: https://github.com/xingchen2202/obsidian-ai-knowledge-system/tree/main/skills/type-classifier
Command: npx skills add https://github.com/xingchen2202/obsidian-ai-knowledge-system --skill type-classifier

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents Obsidian notes from being misrouted by automatically detecting your note’s intended type and writing the correct 类型 value into frontmatter.

Core Features & Use Cases

  • Preemptive frontmatter classification: Detects whether 类型 already exists and is valid, and otherwise determines the correct type from content features.
  • Guardrails for weak or malformed notes: Forces classification: insufficient_content when正文内容少于 20 字, and warns about likely frontmatter field-name typos via Levenshtein distance (≤ 2).
  • Cross-validation for ambiguous cases: When features match both Tutorial and Method Study, outputs classification: tentative and asks the user to confirm before further formatting.

Quick Start

Ask the AI to classify the current Obsidian note by inferring its 类型 from its frontmatter and正文, then update the note’s frontmatter accordingly.

Frequently Asked Questions about type-classifier

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

FAQPage Schema
How do I automatically classify Obsidian notes and set the correct frontmatter type?

To automatically classify Obsidian notes, the Skill infers the correct `类型` value by analyzing frontmatter presence and content signals, then updates the note's frontmatter accordingly for research governance workflows.

What happens when an Obsidian note has insufficient content for metadata validation?

When an Obsidian note has insufficient content for metadata validation, specifically under 20 characters, the Skill forces a `classification: insufficient_content` result to prevent inaccurate type routing.

How does frontmatter typo detection work for research notes in Obsidian?

Frontmatter typo detection works by calculating the Levenshtein distance between existing field names and expected values, warning the user when the distance is 2 or less to ensure metadata validation accuracy.

Can I use this note classifier for ambiguous Method Study and Tutorial cases?

Yes, for ambiguous Method Study and Tutorial cases, the classifier applies cross-validation, outputs `classification: tentative`, and prompts the user to confirm the note type before further formatting.

What is the best way to manage falsification-driven workflow metadata in Obsidian?

The best way to manage falsification-driven workflow metadata is to preemptively detect missing or tentative `类型` fields and enforce deterministic validation rules to route Experiment Plans and Research Logs accurately.