From nuclear-grade
Verifies that public citations of source families, standards, or borrowed ideas are honest and do not overclaim compliance. Use when reviewing docs, templates, or change records referencing outside sources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nuclear-grade:checking-source-claimsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
"Source lineage" means showing where an idea came from. Honest lineage keeps public claims clean. It links an idea to a real public source. At the same time, it keeps the repo from sounding like it formally meets that source's rules.
"Source lineage" means showing where an idea came from. Honest lineage keeps public claims clean. It links an idea to a real public source. At the same time, it keeps the repo from sounding like it formally meets that source's rules.
source-map.md, source-to-concept-crosswalk.md, and compliance-boundaries.md -> narrowed wording and updated source-map or crosswalk rows.docs/00-standards-foundation/source-map.md.docs/01-field-guide/source-to-concept-crosswalk.md.docs/00-standards-foundation/compliance-boundaries.md.source-map.md or to public URLs.Run a Nuclear-grade source-lineage check (where the ideas come from).
Inputs:
- changed public text: <paste/link>
- cited source families: <list>
- source-map rows: <links>
- source or vendor claims used as evidence: <list>
Return:
- a status for each source: verified-public, supporting-context, public-url-needed, or excluded-direct
- the difference between an influence, a source's claim, local proof, a requirement, and an authority
- the wording changes needed so you make no claim of compliance or approval
- the source-map or crosswalk updates
- the validation and scan commands
This skill is an original citation-safety workflow for public-source-inspired software methodology. It does not turn cited sources into requirements this repo satisfies.
npx claudepluginhub flyfission/nuclear-grade-context-engineering --plugin nuclear-gradeVerifies citations in agent-generated content against research corpus, blocks hallucinations, enforces GRADE-compliant hedging, and logs gaps.
Assigns reputation tiers to sources, cross-references claims for verification, detects biases, and standardizes citations with metadata.
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.