From X2 Method
Derives fidelity ledger and acceptance scenarios from a locked prototype portion. Use only after a slice is locked, never before.
How this skill is triggered — by the user, by Claude, or both
Slash command
/x2:derive-testsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn the locked portion into its tests. Nothing here is authored from imagination: the locked
Turn the locked portion into its tests. Nothing here is authored from imagination: the locked prototype is the acceptance contract, and the tests are projections of it.
design/ledger/slice-NNN.md): the locked portion's visual
atoms, enumerated. The kernel tests it in both directions: every ledger atom renders
(exhaustiveness) and nothing renders beyond the ledger (de-fabrication). Until the
prototype-to-ledger exporter exists (owed on the claim), the hand-derived ledger is a known
second-source risk: derive it at lock time only, from the artifact on disk, never maintain it by
hand alongside a moving prototype.The ban is precise, per the record's wording fix:
Derivation should leave these satisfiable, because slice-exit reports them:
Prove a derived suite can fail: write one assertion wrong, watch it fail, fix it. A suite that cannot fail is not evidence.
implement.
npx claudepluginhub teklabsdigital/x2-method --plugin x2Autonomously builds a locked slice to green, enforcing contract fidelity and stopping only for record-gaps, green-but-wrong, or unconditional turns.
Generates tests from Allium specifications. Covers surface boundary tests and full spec test obligations including entity, value type, and state machine tests.
Generates Gherkin BDD feature files from structured use case flows using Clark's UC2.0-to-Gherkin algorithm. Analyzes test coverage completeness against use case steps.