본문으로 건너뛰기
cccskills
무료GitHub에 공개

qcsd-refinement-swarm

Use when running Sprint Refinement sessions with SFDIPOT product factors, generating BDD scenarios, or validating requirements in the QCSD Refinement phase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe스타 515(GitHub 515 + cccskills 0)

실행 점수 미검증

설치 방법 보기

포함된 파일(13)

  • SKILL.md5.7 KB
  • evals/qcsd-refinement-swarm.yaml3.1 KB
  • schemas/output.json18.6 KB
  • scripts/validate-config.json442 B
  • steps/01-flag-detection.md3.1 KB
  • steps/02-core-agents.md1.8 KB
  • steps/03-batch1-results.md1.1 KB
  • steps/04-conditional-agents.md1.3 KB
  • steps/05-decision-synthesis.md1.4 KB
  • steps/06-report-generation.md1.3 KB
  • steps/07-learning-persistence.md1.1 KB
  • steps/08-transformation.md1.1 KB
  • steps/09-final-output.md2.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

QCSD Refinement Swarm v1.0

Shift-left quality engineering swarm for Sprint Refinement sessions.


Overview

The Refinement Swarm takes user stories that passed Ideation and prepares them for Sprint commitment using SFDIPOT product factors, BDD scenarios, and INVEST validation. It renders a READY / CONDITIONAL / NOT-READY decision.

QCSD Phase Positioning

PhaseSwarmDecisionWhen
Ideationqcsd-ideation-swarmGO / CONDITIONAL / NO-GOPI/Sprint Planning
Refinementqcsd-refinement-swarmREADY / CONDITIONAL / NOT-READYSprint Refinement
Developmentqcsd-development-swarmSHIP / CONDITIONAL / HOLDDuring Sprint
Verificationqcsd-cicd-swarmRELEASE / REMEDIATE / BLOCKPre-Release / CI-CD
Productionqcsd-production-swarmHEALTHY / DEGRADED / CRITICALPost-Release

Parameters

  • STORY_CONTENT: User story with acceptance criteria (required)
  • OUTPUT_FOLDER: Where to save reports (default: ${PROJECT_ROOT}/Agentic QCSD/refinement/)

ENFORCEMENT RULES - READ FIRST

RuleEnforcement
E1MUST spawn ALL THREE core agents in Step 2.
E2MUST put all parallel Task calls in a SINGLE message.
E3MUST STOP and WAIT after each batch.
E4MUST spawn conditional agents if flags are TRUE.
E5MUST apply READY/CONDITIONAL/NOT-READY logic exactly.
E6MUST generate the full report structure.
E7Each agent MUST read its reference files before analysis.
E8MUST apply qe-test-idea-rewriter transformation in Step 8.
E9MUST execute Step 7 learning persistence.

Step Execution Protocol

Execute steps sequentially by reading each step file with the Read tool.

Steps

  1. Flag Detection -- steps/01-flag-detection.md -- Analyze story content, evaluate all 7 flags
  2. Core Agents -- steps/02-core-agents.md -- Spawn qe-product-factors-assessor, qe-bdd-generator, qe-requirements-validator
  3. Batch 1 Results -- steps/03-batch1-results.md -- Wait and extract metrics
  4. Conditional Agents -- steps/04-conditional-agents.md -- Spawn flagged agents
  5. Decision Synthesis -- steps/05-decision-synthesis.md -- Apply READY/CONDITIONAL/NOT-READY logic
  6. Report Generation -- steps/06-report-generation.md -- Generate refinement report
  7. Learning Persistence -- steps/07-learning-persistence.md -- Store findings to memory
  8. Transformation -- steps/08-transformation.md -- Run test idea rewriter on all test ideas
  9. Final Output -- steps/09-final-output.md -- Display completion summary

Execution Instructions

  1. Use the Read tool to load the current step file
  2. Execute the step's instructions completely
  3. Verify all success criteria are met
  4. Pass output as context to next step
  5. If a step fails, halt and report

Resume Support

To resume from a specific step: specify --from-step N.


Agent Inventory

AgentTypeDomainBatch
qe-product-factors-assessorCorerequirements-validation1
qe-bdd-generatorCorerequirements-validation1
qe-requirements-validatorCorerequirements-validation1
qe-contract-validatorConditional (HAS_API)contract-testing2
qe-impact-analyzerConditional (HAS_REFACTORING)code-intelligence2
qe-dependency-mapperConditional (HAS_DEPENDENCIES)code-intelligence2
qe-middleware-validatorConditional (HAS_MIDDLEWARE)enterprise-integration2
qe-odata-contract-testerConditional (HAS_SAP_INTEGRATION)enterprise-integration2
qe-sod-analyzerConditional (HAS_AUTHORIZATION)enterprise-integration2
qe-test-idea-rewriterTransformation (always)test-generation3

Total: 10 agents (3 core + 6 conditional + 1 transformation)


Key Principle

Refinement quality determines sprint success. This swarm ensures stories are testable, complete, and ready for development commitment.

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

a11y-ally

무료

Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

proffesor-for-testing/agentic-qe5152026년 10월 26일 업데이트

proffesor-for-testing의 스킬 모두 보기

이 스킬의 문제 신고