Pulls structured data from unstructured text using LLM-powered extraction. You feed it messy content like emails, PDFs, or web pages along with a schema, and it returns clean JSON matching your spec. Handy when you're tired of writing brittle regex patterns or parsing logic for things like invoices, resumes, or customer support tickets. The approach is straightforward: it sends your content and desired output structure to an LLM, then validates the response. Works well for one-off extractions or when your input format varies too much for traditional parsers. Think of it as a flexible alternative to template-based scraping when you need semantic understanding over exact pattern matching.

skills.sh installs
1.6K
GitHub stars
29.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add alirezarezvani/claude-skills --skill extract --agent claude-code

Installs into .claude/skills of the current project.

Files

/si:extract — Create Skills from Patterns

Transforms a recurring pattern or debugging solution into a standalone, portable skill that can be installed in any project.

Usage

/si:extract <pattern description>                  # Interactive extraction
/si:extract <pattern> --name docker-m1-fixes       # Specify skill name
/si:extract <pattern> --output ./skills/            # Custom output directory
/si:extract <pattern> --dry-run                     # Preview without creating files

When to Extract

A learning qualifies for skill extraction when ANY of these are true:

CriterionSignal
RecurringSame issue across 2+ projects
Non-obviousRequired real debugging to discover
Broadly applicableNot tied to one specific codebase
Complex solutionMulti-step fix that's easy to forget
User-flagged"Save this as a skill", "I want to reuse this"

Workflow

Step 1: Identify the pattern

Read the user's description. Search auto-memory for related entries:

MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
grep -rni "<keywords>" "$MEMORY_DIR/"

Sponsors

Details

Repository
github.com/alirezarezvani/claude-skills
Categories
Documentation, Debugging
First seen
May 16, 2026

More from alirezarezvani/claude-skills

All 267
1yonatangross avatardevops-deploymentyonatangross/orchestkitUse when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub 1.6Kskills.sh installs
2getstream avatarstreamgetstream/agent-skillsStream router for Chat, Video, Feeds, and Moderation. Use when the user wants to build a new app with Stream, scaffold a project, add Chat/Video/Feeds/Moderatio1.6Kskills.sh installs
3jezweb avatarproject-healthjezweb/claude-skillsAll-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions1.6Kskills.sh installs
4emalorenzo avatarthree-best-practicesemalorenzo/three-agent-skillsThree.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes1.6Kskills.sh installs
5neo4j-contrib avatarneo4j-cypher-skillneo4j-contrib/neo4j-skillsGenerates, optimizes, and validates Cypher 25 queries for Neo4j 2025.x and 2026.x. Use when writing new Cypher queries, optimizing slow queries, graph pattern m1.6Kskills.sh installs
6daymade avatarfact-checkerdaymade/claude-code-skillsVerifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-che1.6Kskills.sh installs