Claude Skills by BenjaminChenLab

Use when a FUZZY requirement sits on a BLAST-RADIUS-CRITICAL surface (a silent bug would move money, change authorization, or irreversibly corrupt data — verbatim `spec-tdd-adversarial`'s predicate; money-adjacent display/reporting does NOT qualify) and a wrong grill decision or defective acceptance test would burn a full top-tier run — grill-spec-tdd upgraded with an independent grill-auditor dispatched TWICE: Part A attacks the grill's decisions BEFORE the spec gate, Part B attacks the fina...

Use when the user says "grill-spec-tdd", or wants to interrogate/grill requirements before a test-first delegated implementation — especially for fuzzy or high-stakes (money/auth/data) features. Triggers on requirement grilling before coding, spec-as-test, test-first-by-orchestrator, and avoiding wasted subagent runs on wrong-direction specs.

Use when implementing a BLAST-RADIUS-CRITICAL unit — a silent wrong result MOVES money, CHANGES authorization, or IRREVERSIBLY corrupts data (money movement, auth/permissions, data-loss/data-integrity logic itself), where a subtle bug means real loss and maximum rigor is worth the token cost. Money-adjacent is NOT money-movement — display/reporting/reference-data/internal tooling that READS the money system but cannot corrupt it routes to spec-tdd-coverage or spec-tdd instead; a pre-settlemen...

Use when delegating test-first feature work to a subagent and you need EVIDENCE the new code is fully branch-covered — not just passing tests. Use when "good coverage" / "high coverage" matters, when weak or incomplete unit tests are a risk, or when spec-tdd's green-tests-but-no-coverage-evidence gap matters.

Use when the user says "spec-tdd-escalate", or has a SETTLED requirement (plan/spec/design doc already locked — no grilling wanted) and wants the spec-tdd tier picked for them automatically. Triggers on requirement-already-decided, auto-pick tier, skip grilling, route to spec-tdd-lite / spec-tdd / spec-tdd-coverage / spec-tdd-adversarial.

Use when the user says "spec-tdd-lite", or wants test-first development WITHOUT delegating to a subagent — ONE small/medium non-critical unit (a single feature, bugfix, or refactor) in a session you'll clear after, where full spec-tdd is overkill but shallow same-context tests are still a risk. Triggers on in-session acceptance-test-first, "too small for spec-tdd", light tier, quick feature work with green-lie risk.

Use when the user says "spec-tdd" or wants acceptance-test-first development delegated to a subagent — one feature, or a multi-unit batch (bug list, task-split feature). Triggers on spec-as-test, test-first-by-orchestrator, preventing weak/green-lie AI tests, circular test+implementation reasoning.