Structured Extractor — Development agent for Claude Code
Parses unstructured text into a typed JSON or YAML schema.
How to install Structured Extractor
Installs to ~/.claude/agents/usrrname-agent-skills-structured-extractor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/usrrname/agent-skills/HEAD/agents/structured-extractor.md -o ~/.claude/agents/usrrname-agent-skills-structured-extractor.md Restart Claude Code, or start a new session, for it to be picked up.
What Structured Extractor does
name: structured-extractor description: Parses unstructured text into a typed JSON or YAML schema. tools: Read model: claude-sonnet-4-6
You extract structured data from unstructured text. Given raw input (emails, PDFs, logs, transcripts, scraped HTML) and a target JSON or YAML schema:
- Read the schema first. Note required vs optional fields, enums, and format constraints (dates, currencies, IDs). The schema is the contract — never emit a key it doesn't define.
- Scan the input f
Alternatives in Development
- Memory Extractor Agent — You extract perception changes from Claude Code session transcripts - the "aha moments" where understanding sh 3.6k ★
- OSS Investigator Ioc Extractor Agent 2.3k ★
- Knowledge Extractor 518 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Lit Extractor
Reads one paper's full text and produces a structured JSON extraction against a literature-survey's parameter
Legal Clause Extractor
Parses a contract or lease (TXT, DOCX, PDF with text layer) into a clause map JSON — clause_id, heading, verba
Guidelines Extractor
Given a URL or raw text of journal author guidelines, extracts structured requirements into a guidelines/jour
Jd Extractor
Fetch and normalize a job posting (URL or pasted text) into a structured JD brief. Use as the first stage of t
Doc Extractor
Transcribes one archival document image or PDF page. Produces verbatim original text, a Ukrainian translation,
Source Analyst
Read-only extraction from raw/. Parses raw source files and returns structured notes on entities, topics, and
Related Skills
Datachain
The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
Multi AI Session Data Extractor
Capture and preserve your own AI conversations locally before they vanish — 10 platforms, unified parquet sche
Yaak Plugin SSE Parser
A Yaak plugin that parses Server-Sent Events (SSE) streaming responses from LLM APIs into readable text, with