Agent Skills › semantica-agi/semantica › extract

extract

GitHub

执行语义提取全流程，包括命名实体识别、关系抽取、事件检测、共指解析及三元组提取，并验证质量。支持文件路径、内联文本或当前编辑器内容作为输入，输出结构化Markdown表格及统计摘要。

plugins/skills/extract/SKILL.md semantica-agi/semantica

Trigger Scenarios

需要对文本进行深度语义分析需要抽取实体、关系或事件信息

Install

npx skills add semantica-agi/semantica --skill extract -g -y

More Options

Non-standard path

npx skills add https://github.com/semantica-agi/semantica/tree/main/plugins/skills/extract -g -y

Use without installing

npx skills use semantica-agi/semantica@extract

指定 Agent (Claude Code)

npx skills add semantica-agi/semantica --skill extract -a claude-code -g -y

安装 repo 全部 skill

npx skills add semantica-agi/semantica --all -g -y

预览 repo 内 skill

npx skills add semantica-agi/semantica --list

SKILL.md

Frontmatter

{
    "name": "extract",
    "description": "Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity\/relation\/event\/triplet results and inline validator warnings."
}

/semantica:extract

Run the full extraction pipeline. Usage: /semantica:extract [file_path | "inline text"]

$ARGUMENTS = file path, inline text in quotes, or blank (uses active editor file).

Steps

1. Resolve the source.

If $ARGUMENTS is a readable file path → text = open(path).read()
If it's quoted inline text → use directly
If blank → use the active editor file

2. Clear the result cache to prevent cross-invocation pollution:

from semantica.semantic_extract.cache import _result_cache
_result_cache.clear()

3. Run the full pipeline:

from semantica.semantic_extract import (
    NamedEntityRecognizer,
    RelationExtractor,
    EventDetector,
    CoreferenceResolver,
    TripletExtractor,
    ExtractionValidator,
)

# Named Entity Recognition
ner = NamedEntityRecognizer()
entities = ner.extract(text)

# Relation Extraction
rel = RelationExtractor()
relations = rel.extract(text)

# Event Detection
evt = EventDetector()
events = evt.extract(text)

# Coreference Resolution — resolve pronouns/aliases before extraction
coref = CoreferenceResolver()
resolved_text = coref.resolve(text)

# Triplet Extraction (subject–predicate–object)
triplet = TripletExtractor()
triplets = triplet.extract(resolved_text)

# Validate quality
validator = ExtractionValidator()
issues = validator.validate(entities, relations)

4. Report validator warnings above results:

⚠ ExtractionValidator: <warning message>

5. Return results as Markdown tables:

Entities (N total)

Label	Type	Confidence	Span

Relations (M total)

Source	Relation Type	Target	Confidence

Events (K total)

Label	Type	Participants	Confidence

Triplets (J total)

Subject	Predicate	Object	Confidence

6. Summary line:

Extracted: N entities, M relations, K events, J triplets — from <source>

For large files (>50KB), process in chunks and show a progress indicator. Highlight any entities appearing in the context graph already (ContextGraph.has_node(label)) with [in graph] tag.