Story Verification Skill

Purpose & Scope

• Validate Story plus child Tasks against industry standards and project patterns
• Calculate Penalty Points for violations, then auto-fix to reach 0 points
• Delegate to ln-002-best-practices-researcher for creating documentation (guides, manuals, ADRs, research)
• Support Plan Mode: show audit results, wait for approval, then fix
• Approve Story after fixes (Backlog -> Todo) with tabular output summary

When to Use

• Reviewing Stories before approval (Backlog -> Todo)
• Validating implementation path across Story and Tasks
• Ensuring standards, architecture, and solution fit
• Optimizing or correcting proposed approaches

Penalty Points System

1. Audit: Calculate penalty points for all 17 criteria
2. Fix: Auto-fix and zero out points
3. Report: Total Before -> 0 After

Mode Detection

• Phase 1-2: Full audit (discovery + research + penalty calculation)
• Phase 3: Show results + fix plan -> WAIT for user approval
• Phase 4-5: After approval -> execute fixes

• Phase 1-5: Standard workflow without stopping
• Automatically fix and approve

Workflow Overview

Phase 1: Discovery & Loading

• Auto-discover configuration: Team ID (

  docs/tasks/kanban_board.md

  ), project docs (

  CLAUDE.md

  ), epic from Story.project
• Load metadata only: Story ID/title/status/labels, child Task IDs/titles/status/labels
• Expect 3-8 implementation tasks; record parentId for filtering
• Rationale: keep loading light; full descriptions arrive in Phase 2

Phase 2: Research & Audit

• Extract technical domains from Story title + Technical Notes + Implementation Tasks
• Load pattern registry from

  references/domain_patterns.md

• Scan Story content for pattern matches via keyword detection
• Build list of detected domains requiring documentation

• For EACH detected pattern, delegate to ln-002:

  Skill(skill="ln-002-best-practices-researcher",
        args="doc_type=[guide|manual|adr] topic='[pattern]'")

• Receive file paths to created documentation (

  docs/guides/

  ,

  docs/manuals/

  ,

  docs/adrs/

  ,

  docs/research/

  )

• Query MCP Ref for industry standards:

  ref_search_documentation(query="[topic] RFC OWASP best practices 2025")

• Query Context7 for library versions:

  resolve-library-id

  +

  query-docs

• Extract: standards (RFC numbers, OWASP rules), library versions, patterns

• Scan Story/Tasks for technical claims (RFC references, library versions, security requirements)
• Verify each claim has MCP Ref/Context7 evidence
• Flag unverified claims for correction
• Status: VERIFIED (all sourced) or FLAGGED (list unverified)

• Evaluate all 17 criteria against Story/Tasks
• Assign penalty points per violation (CRITICAL=10, HIGH=5, MEDIUM=3, LOW=1)
• Calculate total penalty points
• Build fix plan for each violation

Phase 3: Audit Results & Fix Plan

• Penalty Points table (criterion, severity, points, description)
• Total: X penalty points
• Fix Plan: list of fixes for each criterion

• IF Plan Mode: Show results + "After your approval, changes will be applied" -> WAIT
• ELSE (Normal Mode): Proceed to Phase 4 immediately

Phase 4: Auto-Fix

• Execution order (7 groups):
  1. Structural (#1-#4) — Story/Tasks template compliance + AC completeness/specificity
  2. Standards (#5) — RFC/OWASP compliance FIRST (before YAGNI/KISS!)
  3. Solution (#6) — Library versions
  4. Workflow (#7-#13) — Test strategy, docs integration, size, cleanup, YAGNI, KISS, task order, Database Creation
  5. Quality (#14-#15) — Documentation complete, hardcoded values
  6. Dependencies (#18-#19) — Story/Task independence (no forward dependencies)
  7. Traceability (#16-#17) — Story-Task alignment, AC coverage quality (LAST, after all fixes)
• Use Auto-Fix Actions table below as authoritative checklist
• Zero out penalty points as fixes applied
• Test Strategy section must exist but remain empty (testing handled separately)

Phase 5: Approve & Notify

• Set Story + all Tasks to Todo (Linear); update

  kanban_board.md

  with APPROVED marker
• Add Linear comment with full validation summary:
  • Penalty Points table (Before -> After = 0)
  • Auto-Fixes Applied table
  • Documentation Created table (docs created via ln-002)
  • Standards Compliance Evidence table
• Display tabular output (Unicode box-drawing) to terminal
• Final: Total Penalty Points = 0
• Optional: If

  --execute

  flag provided, delegate to ln-400-story-executor to start execution immediately after approval

Auto-Fix Actions Reference

Structural (#1-#4)

Standards (#5)

Solution (#6)

Workflow (#7-#13)

Quality (#14-#15)

Traceability (#16-#17)

Dependencies (#18-#19)

Final Assessment Model

Readiness Score Calculation

Readiness Score = 10 - (Penalty Points / 5)

Anti-Hallucination Verification

Task-AC Coverage Matrix

| AC | Task(s) | Coverage |
|----|---------|----------|
| AC1: Given/When/Then | T-001, T-002 | ✅ |
| AC2: Given/When/Then | T-003 | ✅ |
| AC3: Given/When/Then | — | ❌ UNCOVERED |

{covered}/{total} ACs

Self-Audit Protocol (Mandatory)

Definition of Done

• Phase 1: Auto-discovery done; Story + Tasks metadata loaded; task count checked
• Phase 2: Domain extraction complete; ln-002 delegated for docs; MCP research done; Anti-Hallucination verification done; Penalty Points calculated
• Phase 3: Audit results shown; IF Plan Mode: user approved
• Phase 4: All 17 criteria auto-fixed; Penalty Points = 0; Test Strategy empty; test tasks removed
• Phase 5: Final Assessment output:
  yaml

  gate: GO | NO-GO
  readiness_score: {1-10}
  penalty_points: 0 (was {N})
  anti_hallucination: VERIFIED | FLAGGED
  ac_coverage: "{N}/{M} (100%)"
  ac_matrix:
    - ac: "AC1"
      tasks: ["T-001", "T-002"]
      status: covered

• Story/Tasks set to Todo;

  kanban_board.md

  updated; Linear comment with Final Assessment added
• Optional: If

  --execute

  flag, ln-400-story-executor invoked after approval

Example Workflow

1. Phase 1: Load metadata (5 Tasks, status Backlog)
2. Phase 2:
   • Domain extraction: REST API, Rate Limiting
   • Delegate ln-002: creates Guide-05 (REST patterns), Guide-06 (Rate Limiting)
   • MCP Ref: RFC 7231 compliance, OWASP API Security
   • Context7: Express v4.19 (current v4.17)
   • Penalty Points: 18 total (version=5, missing docs=5, structure=3, standards=5)
3. Phase 3:
   • Show Penalty Points table
   • IF Plan Mode: "18 penalty points found. Fix plan ready. Approve?"
4. Phase 4:
   • Fix #6: Update Express v4.17 -> v4.19
   • Fix #5: Add RFC 7231 compliance notes
   • Fix #13: Add Guide-05, Guide-06 references
   • Fix #17: Docs already created by ln-002
   • All fixes applied, Penalty Points = 0
5. Phase 5: Story -> Todo, tabular report

Template Loading

story_template.md

task_template_implementation.md

1. Check if

   docs/templates/{template}.md

   exists in target project
2. IF NOT EXISTS: a. Create

   docs/templates/

   directory if missing b. Copy

   shared/templates/{template}.md

   →

   docs/templates/{template}.md

   c. Replace placeholders in the LOCAL copy:

   • {{TEAM_ID}}

     → from

     docs/tasks/kanban_board.md

   • {{DOCS_PATH}}

     → "docs" (standard)
3. Use LOCAL copy (

   docs/templates/{template}.md

   ) for all validation operations

• Project independence (no dependency on skills repository)
• Customization possible (project can modify local templates)
• Placeholder replacement happens once at copy time

Reference Files

• AC validation rules:

  shared/references/ac_validation_rules.md

• Plan mode behavior:

  shared/references/plan_mode_pattern.md

• Final Assessment:

  references/readiness_scoring.md

  (GO/NO-GO rules, Readiness Score calculation)
• Templates (centralized):

  shared/templates/story_template.md

  ,

  shared/templates/task_template_implementation.md

• Local copies:

  docs/templates/

  (in target project)
• Validation Checklists (Progressive Disclosure):

  • references/verification_checklist_template.md

    (overview of 7 categories)

  • references/structural_validation.md

    (criteria #1-#4)

  • references/standards_validation.md

    (criterion #5)

  • references/solution_validation.md

    (criterion #6)

  • references/workflow_validation.md

    (criteria #7-#13)

  • references/quality_validation.md

    (criteria #14-#15)

  • references/dependency_validation.md

    (criteria #18-#19)

  • references/traceability_validation.md

    (criteria #16-#17)

  • references/domain_patterns.md

    (pattern registry for ln-002 delegation)

  • references/penalty_points.md

    (penalty system details)
• Linear integration:

  ../shared/templates/linear_integration.md