Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Fix security claims per audit: clarify network behavior, add SSRF blocklist details, add supply-chain traceability
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.
User asks: Decompose this contract and show me which clauses are safety-critical and mandatory
- 1Call decompose_text with the contract text
- 2Receive units array with authority and risk fields per clause
- 3Filter units where authority is mandatory and risk is safety_critical
- 4Rank filtered units by attention score descending
- 5Return the prioritized list with heading_path context
A ranked list of mandatory safety-critical clauses with their document locations and attention scores