Testing & Debugging Skills

Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which phases run (PhaseAdvisor/router). Codifies Google's 4-phase adversarial-testing methodology mapped onto evolve-loop's eval, audit, routing, and red-team surfaces.

Use when reviewing code changes for quality, security, performance, or maintainability issues and identifying simplification opportunities in a single token-efficient…

Use after evolve-build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS verdict. Adversarial mode default-on per CLAUDE.md.

Use after evolve-tdd has written RED tests and the contract is in team-context.md. Implements the minimum code to turn RED tests GREEN. Runs in a worktree with single-writer invariant.

Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via EVOLVEREQUIREINTENT=1.

Use when the user invokes /evolve-loop or asks to run autonomous improvement cycles, self-evolving development, compound discovery, or multi-cycle code improvement with research, build, audit, and learning…

Use when scout-report.md exists and TDD/Build hasn't started yet. Runs four lenses (CEO, Eng, Design, Security) in parallel on the task list and produces a verdict (PROCEED, REVISE, ABORT) before code is written. Catches misaligned plans before they cost cycles.

Use after evolve-ship completes. Three sub-reflectors (instinct, gene, failure) run in parallel to extract lessons, update gene pool, and analyze any failures. Off the latency-critical path.

Use after evolve-audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.

Use when starting a new evolve-loop cycle and the cycle goal is ambiguous or only described as a one-line objective. Generates a structured specification before any code is written. Surfaces assumptions explicitly.

Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy. The mandatory hop before any implementation.

Use when reviewing Go test code (new or changed test.go files, test harnesses, fixtures, or test tooling) for a Go-test-expert pass — behavior-over-surface, determinism, parallel-safety, build-tag correctness, and harness reuse. Complements the general code-reviewer with test-specific rigor.

Use when the user invokes /inspirer or asks to brainstorm creatively, think outside the box, explore unconventional approaches, break out of stagnation, or generate research-backed ideas with provocation…

Use when the user (or the advisor) wants to design and register a NEW optional pipeline phase conversationally — "add a phase that does X". Interviews for goal-type, trigger signal, report sections, and verdict; synthesizes a phase.json + persona; registers them via evolve phases create; self-corrects from the command's JSON envelope. The Go binary is the single enforcement point, so this flow works from any LLM CLI.

Security-focused code review that emits a numeric composite score (0.0–1.0) suitable for the evolve-loop Builder self-review convergence…

Use when the user invokes /verify-release or asks to check whether a release has propagated, whether the marketplace is up to date, or whether installed plugins reflect the latest version. Wraps scripts/release/marketplace-poll.sh for standalone post-publish verification.