본문으로 건너뛰기
cccskills
무료GitHub에 공개

nw-optimize-tests

Minimizes test count while preserving coverage. Detects byte-identical pairs, parametrize-inflation, language-guarantee tests, AST-shape tests, stale migration nets. Approval gate before any change.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md3.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

NW-OPTIMIZE-TESTS: Test Suite Optimization

Wave: CROSS_WAVE Agent: Trim (nw-test-optimizer) Reviewer: Trim Review (nw-test-optimizer-reviewer)

Overview

Dispatches Trim to inventory a test scope, detect duplication and anti-patterns, propose a consolidation plan, and apply it after explicit approval. Coverage is preserved; production code is never modified. Use after a feature lands, when a suite feels slow or noisy, on weekly audit, or whenever overtesting is suspected.

Context Files Required

  • The scope path (passed as argument or auto-detected)
  • ~/.claude/skills/nw-test-optimization/SKILL.md — methodology (loaded by agent)

Timing Baseline

Trim compares against the wall-clock figures recorded in the execution-log.json.

Agent Invocation

@nw-test-optimizer

Execute test optimization for {scope}.

Configuration:

  • scope: <path | feature-id | empty for full unit suite>
  • approval_required: true # always; gate is non-negotiable
  • mutation_validation: false # set true for critical scopes (financial, safety, infra)
  • reviewer_chain: false # set true to dispatch nw-test-optimizer-reviewer after apply

Approval Gate

Trim presents the plan as a markdown table after Phase 3 (PLAN). The orchestrator (or invoking user) responds with one of:

  1. APPROVE — full plan, all rows
  2. APPROVE WITH EXCLUSIONS — list row IDs to skip
  3. REJECT — abort, return findings as deferred report
  4. REPLAN — provide new scope or constraint

No changes are applied without one of these responses. Trim never assumes approval.

Reviewer Chain (optional)

If reviewer_chain: true:

@nw-test-optimizer-reviewer

Validate the optimization output for {scope}.

Reviewer hard-blocks on: production drift, coverage drop without justification, unmapped removal, missing approval gate evidence.

Success Criteria

  • Baseline numbers recorded (passed count, coverage %)
  • Plan presented before any change
  • Explicit approval received
  • Production files in diff: 0
  • Coverage % preserved (or drop documented per skill 5.3)
  • Atomic commits per consolidation pattern
  • Final report with deltas and SHAs

Examples

Example 1: Full unit suite audit

/nw-optimize-tests

Trim inventories the unit suite, runs md5sum cross-check, scans for anti-patterns, produces a leverage-sorted plan covering byte-identical pairs and parametrize-inflated files.

Example 2: Scoped to a feature

/nw-optimize-tests lean-wave-documentation

Trim resolves to tests/<feature-id>/ paths from the execution-log.json if available, otherwise scopes to test files referencing the feature-id.

Example 3: Single fat file

/nw-optimize-tests tests/build/unit/test_skill_restructuring.py

Trim probes the single file (315 collected tests), checks migration-collapse lifecycle (skill 3.5), proposes collapse to ~3 tests.

Example 4: With reviewer

/nw-optimize-tests tests/des/unit/ --reviewer

Trim runs the workflow, then dispatches Trim Review for adversarial validation. Reviewer issues YAML verdict.

Out of Scope

  • Authoring new tests (crafter scope, DELIVER wave)
  • Production code refactoring (/nw-refactor, crafter scope)
  • Test infrastructure changes (platform-architect, troubleshooter)

Expected Outputs

git log --oneline {base}..HEAD                  (atomic commits per pattern)
<scope>                                          (test files modified or deleted)
report (returned inline by agent)                (baseline, after, deltas, SHAs)

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

nWave-ai/nWave6202026년 9월 16일 업데이트

nWave-ai의 스킬 모두 보기

이 스킬의 문제 신고