본문으로 건너뛰기
cccskills
무료GitHub에 공개

story-verify

Validate user stories — INVEST scoring, story-to-test coverage mapping, PRP completeness, and development-readiness assessment. Use after writing stories and before starting implementation. Trigger on "validate the stories", "are these stories ready", "INVEST check", "story coverage", "is this ready to build".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(4)

  • SKILL.md7.2 KB
  • templates/coverage-matrix.md1.7 KB
  • templates/invest-checklist.md3.2 KB
  • templates/readiness-checklist.md2.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Story Verification

Validate stories, check test coverage gaps, verify PRP completeness, and assess development readiness.

Usage

/story-verify                       # Auto: validate all stories in project
/story-verify invest <id|all>       # INVEST criteria scoring
/story-verify coverage              # Map stories -> tests, show gaps
/story-verify prp                   # Check PRP completeness against stories
/story-verify ready <id>            # Development readiness assessment

Workflow

Step 1: Determine Mode

Parse $ARGUMENTS for explicit subcommand. If no arguments, run invest all as default.

Detect project context:

PROJECT_INFO=$(bash "$HOME/.claude/skills/story/lib/project-detector.sh")

Step 2: Route to Subcommand


Subcommand: invest

INVEST criteria validation — no Python scripts, pure template-based inline logic.

Process

  1. Load story YAML from stories/yaml-source/US-XXXX.yaml (or all if "all")
  2. Read templates/invest-checklist.md for scoring rules
  3. Score each criterion (0-100):
CriterionScore 100Score 50Score 0
IndependentNo blocked_by, or only 1 external dep2-3 dependenciesCircular deps or >3 blockers
Negotiable"i_want" describes outcome/behaviorMentions specific tech but flexiblePrescribes exact implementation
ValuableClear "so_that" with measurable benefitVague benefit ("improve experience")Missing "so_that" entirely
EstimableHas story_points + >=3 acceptance_criteriaHas points OR criteria, not bothMissing both points and criteria
Small1-5 story points6-8 story points>8 points (must split)
TestableAll criteria have given/when/thenSome criteria missing partsNo given/when/then at all
  1. Overall score = average of 6 criteria
  2. Pass: overall >= 70 AND all criteria >= 50

Output

Story US-XXXX: "View financial dashboard"
  I: 100  N: 100  V: 75  E: 100  S: 100  T: 100
  Overall: 96 — PASS

  Issues:
  - [Medium] Valuable: "so_that" could be more specific about measurable outcome

Auto-Fix Suggestions

IssueFix
Missing "so_that"Suggest based on persona goals and feature context
Vague benefitAdd measurable outcome (number, percentage, time saved)
Missing story pointsEstimate from acceptance criteria count (1 criterion ≈ 1 point)
Too few criteriaSuggest additional Given/When/Then from feature scope
Implementation language in "i_want"Rewrite to describe behavior, not code
>8 pointsSuggest story splitting strategy

Subcommand: coverage

Map stories to test files and identify untested acceptance criteria.

Process

  1. Load all story YAML files
  2. For each story, search test directory for matching test file:
    • Pattern: test_US_XXXX* (pytest) or US_XXXX*.test.* (jest)
  3. For each acceptance criterion in the story:
    • Search test files for matching test function (by criterion slug or docstring)
  4. Build coverage matrix

Output

Read templates/coverage-matrix.md for output format.

Story Coverage Matrix
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

US-0001: View dashboard          [2/3 criteria covered]
  ✓ health score displayed       → test_dashboard_shows_health_score
  ✓ KPI pillars visible          → test_dashboard_shows_kpi_pillars
  ✗ color indicator correct      → NO TEST

US-0002: Upload document         [0/2 criteria covered]
  ✗ PDF accepted                 → NO TEST
  ✗ error on invalid file        → NO TEST

Summary: 2/5 criteria covered (40%)
Gap: 3 criteria need test stubs — run `/story tests US-0001 US-0002`

Subcommand: prp

Check PRP completeness against its source stories.

Process

  1. Scan PRP directory (detected by project-detector.sh) for PRP files
  2. For each PRP, extract referenced stories (look for US-XXXX patterns)
  3. Cross-reference with story YAML files:
    • Are all referenced stories defined?
    • Do all stories have sufficient acceptance criteria?
    • Are story dependencies resolvable?
  4. Check PRP sections against PRP completeness checklist:
    • Header with metadata
    • Executive summary
    • Requirements reference
    • Architecture design
    • Implementation plan (phased)
    • Testing strategy
    • Success criteria

Output

PRP-012: Financial Data Display
  Stories referenced: US-0010, US-0011, US-0012, US-0013
  ✓ All stories defined in YAML
  ✓ All stories have acceptance criteria
  ✗ US-0011 blocked_by US-0009 (not in scope — risk)
  ✓ PRP has all required sections
  ✗ Testing strategy missing E2E test plan

Subcommand: ready

Full readiness assessment for a story before implementation starts.

Process

  1. Run invest validation (must pass)
  2. Check dependencies: all blocked_by stories must be status done
  3. Check test stubs exist (from /story tests)
  4. Check PRP exists for the story's feature area
  5. Check technical context (has enough detail for implementation)

Output

Read templates/readiness-checklist.md for format.

US-0012: Display financial data tables
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

  ✓ INVEST validation: PASS (score: 92)
  ✓ Dependencies: US-0011 (done), US-0009 (done)
  ✗ Test stubs: NOT FOUND — run `/story tests US-0012`
  ✓ PRP: PRP-012 covers this story
  ✓ Technical context: FastAPI route + Jinja2 template

  Verdict: ALMOST READY — generate test stubs first

Template Locations

TemplatePurposeFile
INVEST checklistScoring rules and thresholdstemplates/invest-checklist.md
Coverage matrixStory-to-test mapping formattemplates/coverage-matrix.md
Readiness checklistDev readiness criteriatemplates/readiness-checklist.md

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

Validate WCAG 2.1 Level AA compliance and accessibility best practices. Use when performing accessibility audits and WCAG certification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

analysis

무료

Analyze feature requirements, dependencies, and security considerations. Use when starting feature implementation from GitHub issues to understand scope, technical feasibility, and risks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

analytics

무료

Run SQL queries against psql, BigQuery, or MySQL from the terminal, including natural-language-to-SQL and schema exploration. Use when analyzing data, inspecting DB state, or debugging tables. Trigger on "query the database", "SQL", "show me data from", "explore table".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

Design REST APIs or function contracts with clear request/response specifications, error handling patterns, authentication strategies, and comprehensive documentation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

Generate comprehensive API endpoint tests for REST and GraphQL APIs. Creates tests for all HTTP methods, status codes, authentication, and validation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

Design component architecture and module structure using established architectural patterns for clean, maintainable, and scalable systems.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

matteocervelli/llms252026년 5월 22일 업데이트

matteocervelli의 스킬 모두 보기

이 스킬의 문제 신고