From nuclear-grade
Scans public text for license, warranty, safety, and compliance claims that go too far, then rewrites them to stay within real limits. Use when editing READMEs, docs, or release copy.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nuclear-grade:checking-legal-and-safety-wordingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill keeps two things apart: what the MIT license lets people do, and what the repo proves. People may use the repo. But using it does not create formal verification and validation, compliance, certification, safety, security, or fitness for regulated use.
This skill keeps two things apart: what the MIT license lets people do, and what the repo proves. People may use the repo. But using it does not create formal verification and validation, compliance, certification, safety, security, or fitness for regulated use.
python tools/ng.py doctor . passes.LICENSE, DISCLAIMER.md, SECURITY.md, and compliance-boundaries.md -> bounded wording, updated docs/templates, and the scan results or list of gaps.LICENSE, DISCLAIMER.md, SECURITY.md, and docs/00-standards-foundation/compliance-boundaries.md.python tools/ng.py doctor . passes.Run a Nuclear-grade license and assurance-limit check.
Inputs:
- changed public text: <paste/link>
- license/disclaimer files: <links>
- target audience: <user/team/enterprise>
- public trust claims to self-check: <list>
Return:
- whether the MIT license permission stays clear
- wording that keeps the permission to use separate from any assurance claim
- whether each public trust claim is supported, narrowed, or removed
- the unsafe phrases and what to replace them with
- the scan commands to run
- the final limits note
This skill is an original public-use boundary workflow informed by the repo license, disclaimer, and source-foundation docs. It is not legal advice.
npx claudepluginhub flyfission/nuclear-grade-context-engineering --plugin nuclear-gradeValidates documentation for unsupported claims, made-up metrics, unverifiable statements, comparative hype, and unimplemented features. Generates classified reports with removal or citation recommendations.
Scans repository dependencies and assets for license compatibility, producing a per-package verdict table for commercial use readiness.
Checks dependency lists, SBOMs, or outbound code for open source license compliance. Classifies packages by license family, flags copyleft obligations and non-OSI licenses, and recommends actions.