cash-verify

name	cash-verify
description	Verify implementation matches artifacts
context	fork
agent	Explore
disallowedTools	["Edit","Write"]
license	MIT
metadata	{"author":"cash","version":"1.0"}

Project-local Cash CLI bootstrap

執行任何 Cash artifact command 前，MUST 先從目前目錄解析並驗證 Git root，再使用該 root 下的 absolute launcher；不得依賴 PATH 或外部 runtime：

cash_root="$(git rev-parse --show-toplevel)" || exit 1
cash_cli="$cash_root/.cash-skills/bin/cash"
test -x "$cash_cli" || exit 1

同一段 workflow 後續每個 artifact command MUST 使用 "$cash_cli"。

Claude fork context

This generated Claude Code skill runs with context: fork. The rules in this section take precedence over the shared verify body below.

When no change name is provided, run "$cash_cli" list --json and consider only active changes with implementation tasks. Auto-select only when exactly one matching active change exists. If there are zero matching active changes or more than one matching active change, return the candidate list or empty-state message and ask the main thread to rerun /cash-verify <change-name>. Do NOT ask an interactive selection question inside the fork.

---

Verify that an implementation matches the change artifacts (specs, tasks, design).

Input: Optionally specify a change name after /cash-verify (e.g., /cash-verify add-auth). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.

Prerequisites: The project-local launcher initialized above is required. If root resolution, launcher validation, or a Cash command fails, report the exact error and STOP.

Response language: All user-facing responses in this workflow MUST be written in Traditional Chinese unless the user explicitly requests another language. Keep shell commands, file paths, code identifiers, schema field names, and quoted source text verbatim.

Steps

1. If no change name provided, prompt for selection

   Run "$cash_cli" list --json to get available changes. Use the AskUserQuestion tool to let the user select (if this tool is not available, ask as plain text and wait for the user's response).

   Show changes that have implementation tasks (tasks artifact exists). Include the schema used for each change if available. Mark changes with incomplete tasks as "(In Progress)".

   IMPORTANT: Do NOT guess or auto-select a change. Always let the user choose.

2. Check status to understand the schema

   "$cash_cli" status --change "<name>" --json
   

   Parse the JSON to understand:

   • schemaName: The workflow being used (e.g., "spec-driven")
   • Which artifacts exist for this change

3. Get the change directory and load artifacts

   "$cash_cli" instructions apply --change "<name>" --json
   

   This returns the complete apply consumer contract. Always read state, missingArtifacts, preflight, contextFiles, progress, and tasks.

   • state: "blocked": report the non-empty missingArtifacts list and stop verification.
   • state: "ready": inspect preflight, then verify the available implementation and report incomplete tasks normally.
   • state: "all_done": inspect preflight, then perform the complete verification.
   • For either non-blocked state, a missing preflight, missingFiles, driftedFiles, or staleness field is a contract error. Report critical missing files and stop, show warnings before continuing, and silently continue for clean.
   • Any other state or missing required field is a contract error; report it and stop.
   • Read all available artifacts from contextFiles.

4. Initialize verification report structure

   Create a report structure with three dimensions:

   • Completeness: Track tasks and spec coverage
   • Correctness: Track requirement implementation and scenario coverage
   • Coherence: Track design adherence and pattern consistency

   Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.

5. Verify Completeness

   Task Completion:

   • If tasks.md exists in contextFiles, read it
   • Parse checkboxes: - [ ] (incomplete) vs - [x] (complete)
   • Count complete vs total tasks
   • If incomplete tasks exist:
     • Add CRITICAL issue for each incomplete task
     • Recommendation: "Complete task: " or "Mark as done if already implemented"

   Spec Coverage:

   • If delta specs exist in openspec/changes/<name>/specs/:
     • Extract all requirements (marked with "### Requirement:")
     • For each requirement:
       • Search codebase for keywords related to the requirement
       • Assess if implementation likely exists
     • If requirements appear unimplemented:
       • Add CRITICAL issue: "Requirement not found: "
       • Recommendation: "Implement requirement X: "

6. Verify Correctness

   Requirement Implementation Mapping:

   • For each requirement from delta specs:
     • Search codebase for implementation evidence
     • If found, note file paths and line ranges
     • Assess if implementation matches requirement intent
     • If divergence detected:
       • Add WARNING: "Implementation may diverge from spec:
         "
       • Recommendation: "Review : against requirement X"

   Scenario Coverage:

   • For each scenario in delta specs (marked with "#### Scenario:"):
     • Check if conditions are handled in code
     • Check if tests exist covering the scenario
     • If scenario appears uncovered:
       • Add WARNING: "Scenario not covered: "
       • Recommendation: "Add test or implementation for scenario: "

   Example Traceability:

   • For each ##### Example: in delta specs:
     • Check if a test exists that uses the same input values from the example's GIVEN/WHEN/THEN
     • If the example has a table, check if parameterized tests cover all rows
     • If examples appear untested, add WARNING: "Spec example not covered by test: " with recommendation to add a test using the GIVEN/WHEN/THEN from the example

7. Verify Coherence

   Design Adherence:

   • If design.md exists in contextFiles:
     • Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
     • Verify implementation follows those decisions
     • If contradiction detected:
       • Add WARNING: "Design decision not followed: "
       • Recommendation: "Update implementation or revise design.md to match reality"
   • If no design.md: Skip design adherence check, note "No design.md to verify against"

   Code Pattern Consistency:

   • Review new code for consistency with project patterns
   • Check file naming, directory structure, coding style
   • If significant deviations found:
     • Add SUGGESTION: "Code pattern deviation:
       "
     • Recommendation: "Consider following project pattern: "

8. Generate Verification Report

   Summary Scorecard:

   ## Verification Report: <change-name>
   
   ### Summary
   | Dimension    | Status           |
   |--------------|------------------|
   | Completeness | X/Y tasks, N reqs|
   | Correctness  | M/N reqs covered |
   | Coherence    | Followed/Issues  |
   

   Issues by Priority:

   1. CRITICAL (Must fix before archive):

      • Incomplete tasks
      • Missing requirement implementations
      • Each with specific, actionable recommendation

   2. WARNING (Should fix):

      • Spec/design divergences
      • Missing scenario coverage
      • Each with specific recommendation

   3. SUGGESTION (Nice to fix):

      • Pattern inconsistencies
      • Minor improvements
      • Each with specific recommendation

   Final Assessment:

   • If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
   • If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
   • If all clear: "All checks passed. Ready for archive."

Verification Heuristics

• Completeness: Focus on objective checklist items (checkboxes, requirements list)
• Correctness: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
• Coherence: Look for glaring inconsistencies, don't nitpick style
• False Positives: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
• Actionability: Every issue must have a specific recommendation with file/line references where applicable

Graceful Degradation

• If only tasks.md exists: verify task completion only, skip spec/design checks
• If tasks + specs exist: verify completeness and correctness, skip design
• If full artifacts: verify all three dimensions
• Always note which checks were skipped and why

Output Format

Use clear markdown with:

• Table for summary scorecard
• Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
• Code references in format: file.ts:123
• Specific, actionable recommendations
• No vague suggestions like "consider reviewing"