본문으로 건너뛰기
cccskills
무료GitHub에 공개

nw-shared-artifact-tracking

Shared artifact registry, common artifact patterns, and integration validation. Load when tracking data that flows across journey steps or validating horizontal coherence.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md3.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Shared Artifact Tracking

Purpose

Shared artifacts are data values appearing in multiple places across a journey. Every ${variable} must have a single source of truth and documented consumers. Untracked artifacts are the primary cause of horizontal integration failures.

Artifact Registry Schema

shared_artifacts:
  {artifact_name}:
    source_of_truth: "{canonical file path}"
    consumers: ["{list of places this value appears}"]
    owner: "{responsible feature/component}"
    integration_risk: "HIGH|MEDIUM|LOW - {explanation}"
    validation: "{How to verify consistency}"

Common Artifact Patterns

Version

Source: pyproject.toml | Consumers: CLI --version, about command, README, install output Risk: HIGH -- version mismatch breaks user trust

Install Path

Source: config/paths.yaml or constants.py | Consumers: install script, uninstall script, documentation Risk: HIGH -- path mismatch breaks installation

Repository URL

Source: pyproject.toml or config | Consumers: README, error messages, install docs Risk: MEDIUM -- URL mismatch breaks external links

Configuration Values

Source: config file or environment variable | Consumers: runtime behavior, documentation, defaults display Risk: MEDIUM -- inconsistency causes confusion

Command Names

Source: CLI argument parser definition | Consumers: help text, documentation, error messages, tutorials Risk: HIGH -- name mismatch makes features undiscoverable

Integration Validation

Consistency Check Process

  1. List all shared artifacts from journey schema
  2. For each artifact, verify source of truth exists
  3. For each consumer, verify it references correct source
  4. Flag any artifact without documented source
  5. Flag any consumer that hardcodes instead of referencing source

Validation Questions

  • "Does every ${variable} in TUI mockups have a documented source?"
  • "If the version changes, would all consumers automatically update?"
  • "Are there hardcoded values that should reference a shared artifact?"
  • "Do any two steps display the same data from different sources?"

Quality Gates

Journey completeness: all steps have clear goals | CLI commands/actions | emotional annotations | shared artifacts tracked | integration checkpoints defined

Emotional coherence: emotional arc defined (start/middle/end) | no jarring transitions | confidence builds progressively | error states guide to resolution

Horizontal integration: all shared artifacts have single source of truth | all consumers documented | integration checkpoints validate consistency | CLI vocabulary consistent

CLI UX compliance: command structure follows chosen pattern | help available on all commands | progressive disclosure implemented | error messages actionable

Handoff Specifications

To Requirements Crafting (internal handoff within Luna)

Artifacts: docs/feature/{feature-id}/discuss/journey-{name}.yaml (complete journey with emotional arc) | docs/feature/{feature-id}/discuss/shared-artifacts-registry.md (tracked artifacts with sources)

Validation: journey complete with all steps | emotional arc defined | shared artifacts documented | CLI vocabulary consistent

To Acceptance Designer (Quinn)

Deliverables: docs/feature/{feature-id}/discuss/journey-{name}.yaml (journey schema) | docs/feature/{feature-id}/discuss/journey-{name}.feature (Gherkin scenarios) | docs/feature/{feature-id}/discuss/shared-artifacts-registry.md (integration validation points)

Validation: all product-owner checks passed | Gherkin scenarios generated | integration checkpoints testable | peer review approved

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/nWave6212026년 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/nWave6212026년 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/nWave6212026년 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/nWave6212026년 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/nWave6212026년 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/nWave6212026년 9월 16일 업데이트

nWave-ai의 스킬 모두 보기

이 스킬의 문제 신고