From nuclear-grade
Maps claims to evidence, statuses, gaps, and traces so no claim reaches past its evidence. Use when a change asserts something a reviewer must trust.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nuclear-grade:proving-claimsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Evidence should answer named claims. It should not just create a vague sense that the change is fine. This skill turns each claim into a proof you can trace. It keeps six things apart: a fact, an assumption, an unknown, a source claim (something a source says), local proof (something you checked yourself), and decision authority (who gets to decide).
Evidence should answer named claims. It should not just create a vague sense that the change is fine. This skill turns each claim into a proof you can trace. It keeps six things apart: a fact, an assumption, an unknown, a source claim (something a source says), local proof (something you checked yourself), and decision authority (who gets to decide).
basis.md, test, and review evidence -> claim-to-evidence rows with a status (pass/fail/gap/deferred/not applicable/planned) in trace.md/verification.md.ship.md decision weighs.fail/unowned gap carried as shippable).ship.md; a fail or unowned gap escalates to block.basis.md, trace.md, verification.md, and ship.md.pass, fail, gap, deferred, not applicable, or planned.trace.md or verification.md.python tools/ng.py validate .nuclear/changes/<slug> passes for Quick or Standard records.Prove the important Nuclear-grade claims in this packet.
Inputs:
- packet: .nuclear/changes/<slug>/
- claims: <list or source file>
- evidence available: <commands/links/reviews/logs>
- known gaps: <list>
Return:
- claim -> basis -> control/design feature -> support type -> verification type -> evidence -> status -> ship posture
- narrower wording for any claim that is too broad
- the gaps, deferrals, or blockers, stated plainly
- the validator command to run
This skill is an original claim-evidence workflow influenced by public software assurance, verification discipline, and secure development sources mapped in docs/00-standards-foundation/source-map.md. It is not formal verification.
npx claudepluginhub flyfission/nuclear-grade-context-engineering --plugin nuclear-gradeValidates AI agent claims against evidence trail in coding workflows. Catches unsubstantiated 'done', 'tests pass', 'fixed' without proof like outputs, diffs, or logs. Auto-triggers on completion keywords.
Enforces evidence-before-claims discipline: requires fresh verification (test, build, lint) before any completion claim. Prevents premature sign-offs.
Forces verification before claiming work is complete, fixed, or release-ready. Runs the exact command, reads output, and requires evidence slots (action, result, scope, risk, confidence).