| name | team-shinchan:verify-workflow |
| description | Use when you need to validate workflow state schema or error handling. |
| user-invocable | false |
⚠️ MANDATORY EXECUTION - DO NOT SKIP
When this skill is invoked, execute immediately. Do not explain.
Validators
| Validator | Command | What it checks |
|---|
| workflow-state-schema | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/workflow-state-schema.js | WORKFLOW_STATE.yaml template + stage/transition gates, plus the big-project layer (project-state.schema.json parses, bigproject PROJECT.yaml template present) |
| error-handling | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/error-handling.js | Error handling patterns are properly defined |
| part-numbering | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/part-numbering.js | Multi-part agent files have correct numbering |
| quick-fix-path | cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/quick-fix-path.js | Quick-fix (lite mode) workflow path is valid |
When to Run
- After modifying workflow-related files (
docs/workflow-guide.md, hooks/)
- After changing error handling patterns in agents
- After modifying multi-part agent files
- As part of verify-implementation workflow
Workflow
Check 1: Workflow State Schema
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/workflow-state-schema.js
Success criteria:
- Exit code 0
- WORKFLOW_STATE.yaml template + transition gates present
- Big-project layer intact:
schemas/project-state.schema.json parses and
skills/bigproject/SKILL.md contains a PROJECT.yaml template
schemas/workflow-state.schema.json declares current.completion_prompted as an OPTIONAL
boolean (main-076 FR-6 / HR-8: absent ⇒ false; NOT in required)
On failure:
- Issue: Invalid WORKFLOW_STATE.yaml structure
- Severity: HIGH
- Fix: Follow schema defined in docs/workflow-guide.md
Check 2: Error Handling
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/error-handling.js
Success criteria:
- Exit code 0
- Error handling patterns present in required locations
On failure:
- Issue: Missing error handling in agent definition
- Severity: MEDIUM
- Fix: Add error handling section per agent template
Check 3: Part Numbering
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/part-numbering.js
Success criteria:
- Exit code 0
- Multi-part files numbered sequentially
On failure:
- Issue: Gap or duplicate in part numbering
- Severity: MEDIUM
- Fix: Renumber parts sequentially (part-1, part-2, ...)
Check 4: Quick-Fix Path
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/quick-fix-path.js
Success criteria:
- Exit code 0
- Lite mode workflow path properly configured
On failure:
- Issue: Quick-fix path references invalid stage or agent
- Severity: HIGH
- Fix: Update lite mode workflow to match current agent structure
Check 5: DAG Executor Schema Coverage
The executing stage is driven by src/dag-executor.js over a task DAG. Each PLAN.md task MUST
carry the six DAG fields (id, depends_on, touches, verify, estimate, scope) and the
plan SHOULD declare integration_test metadata. The executor enforces a per-task verify gate and
a strict ALL-PASS completion gate before the executing → done transition.
cd "${CLAUDE_PLUGIN_ROOT}" && node --test tests/dag-executor.test.js
Success criteria:
- Exit code 0
- dag-executor unit suite passes (topological order, conflict serialization, verify gate,
recovery ladder, completion-gate blocking, counter persistence, cycle detection)
src/dag-executor.js exposes parsePlan, topoSort, buildConflictGraph,
connectedComponents, evaluateVerify, recoveryStep, evaluateCompletionGate,
runIntegration, executePlan
On failure:
- Issue: DAG schema or executor gate regressed
- Severity: HIGH
- Fix: Restore the six-field schema in PLAN.md and the dag-executor module contract (see
docs/dag-executor.md)