decompose-mcp

AI & LLMs
v0.1.2
Benign

Decompose any text into classified semantic units — authority, risk, attention, entities.

468 downloads468 installsby @echology-io

Setup & Installation

Install command

clawhub install echology-io/decompose-mcp

If the CLI is not installed:

Install command

npx clawhub@latest install echology-io/decompose-mcp

Or install with OpenClaw CLI:

Install command

openclaw skills install echology-io/decompose-mcp

or paste the repo link into your assistant's chat

Install command

https://github.com/openclaw/skills/tree/main/skills/echology-io/decompose-mcp

What This Skill Does

Decomposes text or URLs into classified semantic units with authority levels, risk categories, attention scores, and entity extraction. No LLM or API calls involved. Runs locally with deterministic output.

Unlike LLM-based parsing, it produces identical output on repeated runs, costs nothing, works offline, and processes over 1,000 characters per millisecond.

When to Use It

  • Pre-filtering a 200-page construction spec before sending to an LLM
  • Extracting all OSHA and ASTM references from a safety policy
  • Identifying mandatory vs. permissive clauses in a vendor contract
  • Routing high-attention compliance sections to specialized review
  • Building structured training datasets from raw regulatory documents

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Pre-filtering a 200-page construction spec before sending to an LLM

AGENT
  1. 1Pre-filtering a 200-page construction spec before sending to an LLM
  2. 2Extracting all OSHA and ASTM references from a safety policy
  3. 3Identifying mandatory vs. permissive clauses in a vendor contract
  4. 4Routing high-attention compliance sections to specialized review
  5. 5Building structured training datasets from raw regulatory documents
OUTPUT
Decompose any text into classified semantic units — authority, risk, attention, entities.

Share this skill

Security Audits

VirusTotalBenign
OpenClawBenign
View full report

These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.

Details

LanguageMarkdown
Last updatedFeb 25, 2026