From silver-bullet
Generates, repairs, audits, and optimizes test suites for SB-owned code. Supports write, e2e, repair, audit, performance, and mutation workflows. Use when adding tests or improving test quality.
How this skill is triggered — by the user, by Claude, or both
Slash command
/silver-bullet:silver-test <scope> [--mode write|e2e|repair|audit|performance|mutation]<scope> [--mode write|e2e|repair|audit|performance|mutation]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
SB-owned test engineering for creating, repairing, auditing, and proving tests.
SB-owned test engineering for creating, repairing, auditing, and proving tests.
It complements tdd, testability, verify-tests, and silver:verify; it
does not replace the final verification gate.
Use this skill when the user asks to add tests, generate browser tests, repair broken tests, audit test quality, speed up a test suite, or challenge a suite with mutation-style cases.
Write or update .planning/TEST-ENGINEERING.md or the current phase testing
section.
The report must include:
test-health rows from docs/evidence-schema.md;silver:add.| Mode | Purpose | Required evidence |
|---|---|---|
write | Add unit/integration tests for existing code | target classification, missing behavior list, RED/GREEN evidence, meaningful assertions |
e2e | Discover user flows and create browser tests | route/flow inventory, criticality score, Playwright/browser evidence when runnable |
repair | Fix failing or weak tests by anti-pattern family | triage report, selected pattern, production-context check, verification command |
audit | Audit tests against SB test-health gates | file/line evidence, critical gaps, flake/mock/oracle review |
performance | Baseline or improve test runtime | timing baseline, slowest tests, runner/config findings, verify comparison |
mutation | Challenge test effectiveness with meaningful changes | mutation plan, expected kill condition, result, surviving-mutant follow-up |
SILVER BULLET > TEST.audit before editing tests.testability before designing new tests.silver:domain-audit --pack test-health and include
api-contract, data-contract, ui-system, or performance-resource
where the tests exercise those surfaces.write and repair, require failing-test-first evidence unless the
work is pure harness/config cleanup; record the exception.e2e, discover routes and user flows from source, routing config, docs,
and rendered app behavior when available. Score flows by user/business risk.performance, save a baseline before optimization and compare after.mutation, choose behavior-relevant challenges: boundaries, permission
checks, null/error paths, async ordering, security bypasses, and state
transitions.verify-tests or the targeted runner after changes.silver:add.The test workflow passes only when:
BLOCK test-health finding remains;npx claudepluginhub alo-exp/silver-bullet --plugin silver-bulletGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.