Aller au contenu
TakoAPI
Retour aux skills

decompose-mcp

par echology-io

AI & LLMs
468Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

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

Description

Ce que fait ce skill

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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: Decompose this contract and show me which clauses are safety-critical and mandatory

AGENT
  1. 1

    Call decompose_text with the contract text

  2. 2

    Receive units array with authority and risk fields per clause

  3. 3

    Filter units where authority is mandatory and risk is safety_critical

  4. 4

    Rank filtered units by attention score descending

  5. 5

    Return the prioritized list with heading_path context

SORTIE

A ranked list of mandatory safety-critical clauses with their document locations and attention scores

Installation

clawhub install echology-io/decompose-mcp

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens