autoskill

Analyze screen recording data to match workflows and propose new skills.

13|3|Updated Jun 10, 2026
One-click install
npx skills add https://github.com/tassiovale/claude-code-kit --skill autoskill-tassiovale
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoskill
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/autoskill
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill autoskill-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires screenpipe, sentence-transformers, httpx, pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the discovery of new skills for your Claude Code environment by analyzing your screen recording data, matching workflows to existing skills, and proposing new ones.

Core Features & Use Cases

  • Screen Recording Analysis: Analyzes screen recording data to detect repeated research workflows.
  • Skill Matching: Matches detected workflows against existing scientific-agent-skills.
  • Skill Proposals: Proposes new skills or composition recipes for unmatched workflows.
  • Use Case: If you often perform similar tasks but haven't yet created a skill for them, Autoskill can analyze your workflow and suggest a new skill or a recipe that chains existing skills.

Quick Start

Use the autoskill to analyze your workflow from the last 4 hours and propose new skills.

Frequently Asked Questions about autoskill

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

FAQPage Schema
How does screen recording analysis discover repeated workflow patterns?

Screen recording analysis discovers repeated workflow patterns by processing screenpipe data through clustering and semantic similarity techniques against an existing skills library, identifying unmatched routines to propose new skill compositions.

Can I use screenpipe data to suggest new skills automatically?

Yes, you can use screenpipe data to suggest new skills automatically. The system analyzes screen recording data using LLM-based classification to detect workflow patterns and proposes new skills or composition recipes for unmatched tasks.

What do I need to set up to analyze screen recordings for skill discovery?

To analyze screen recordings for skill discovery, you need the screenpipe daemon running for screen recording and access to an LLM backend. The system processes this data locally, transmitting only redacted information for analysis.

Does skill discovery with screen recording data keep sensitive content private?

Skill discovery with screen recording data keeps sensitive content private by ensuring raw data remains on the local machine. Only redacted data is transmitted externally for LLM-based classification and semantic similarity analysis.

How do I generate skill composition recipes from my workflow analysis?

You generate skill composition recipes from workflow analysis by running the system against your screen recording data. It matches detected workflows against existing skills and proposes composition recipes for tasks that remain unmatched.