skills/ticket-workflow/SKILL.md
Internal helper called by /resolve. Provides state-machine and coordination logic across fetch-ticket, analyze-ticket, AEP, and Architect. Not intended for direct invocation.
npx skillsauth add nicolas-codemate/claudecodeconfig ticket-workflowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
NOTE: The authoritative resolution flow lives in
~/.claude/skills/resolve/steps/(steps 00-09)./resolveonly consumes this skill'sreferences/default-config.json. The state machine below is conceptual background; if it diverges from the resolve steps, the resolve steps win.
This skill provides the state machine and coordination logic for the complete ticket resolution workflow.
┌─────────┐ ┌─────────┐ ┌──────────┐ ┌─────────┐
│ pending │───►│ fetched │───►│ analyzed │───►│ planned │
└─────────┘ └─────────┘ └──────────┘ └─────────┘
│ │ │
▼ ▼ ▼
┌─────────────────────────────────────────┐
│ failed │
└─────────────────────────────────────────┘
│
│ (resume)
▼
┌─────────────────┐ ┌───────────────┐ ┌───────────┐
│ plan_validated │───►│ implementing │───►│ completed │
└─────────────────┘ └───────────────┘ └───────────┘
| State | Description | Next States |
|-------|-------------|-------------|
| pending | Workflow just started | fetched, failed |
| fetched | Ticket data retrieved | analyzed, failed |
| analyzed | Complexity determined | planned, failed |
| planned | Implementation plan ready | plan_validated, failed |
| plan_validated | Plan approved by user | implementing, failed |
| implementing | Auto-implementation in progress | completed, failed |
| completed | All phases finished | (terminal) |
| failed | Error occurred | (can resume) |
| State Transition | Phase | Skill Used | |------------------|-------|------------| | pending → fetched | fetch | fetch-ticket | | fetched → analyzed | analyze | analyze-ticket | | analyzed → analyzed | explore | (AEP agents) | | analyzed → planned | plan | (Architect) | | planned → plan_validated | validation | plan-validation | | plan_validated → implementing | implement | /resolve --continue |
.claude-work/{ticket-id}/status.json
{
"ticket_id": "PROJ-123",
"source": "youtrack",
"started_at": "2024-01-15T10:30:00Z",
"updated_at": "2024-01-15T10:30:00Z",
"state": "pending",
"phases": {
"fetch": "pending",
"analyze": "pending",
"explore": "pending",
"plan": "pending",
"implement": "pending"
},
"options": {}
}
After each phase completion:
{
"state": "fetched",
"updated_at": "2024-01-15T10:31:00Z",
"phases": {
"fetch": "completed",
"analyze": "pending",
...
}
}
On error:
{
"state": "failed",
"updated_at": "2024-01-15T10:32:00Z",
"phases": {
"fetch": "completed",
"analyze": "failed",
...
},
"error": {
"phase": "analyze",
"message": "Could not determine complexity",
"timestamp": "2024-01-15T10:32:00Z"
}
}
if [ -f ".claude-work/{ticket-id}/status.json" ]; then
# Load and check state
fi
def get_resume_point(status):
# Find last completed phase
phase_order = ['fetch', 'analyze', 'explore', 'plan', 'implement']
for phase in phase_order:
if status['phases'][phase] in ['pending', 'failed']:
return phase
return None # All completed
# Reprise du Workflow
**Ticket**: {ticket-id}
**Etat precedent**: {state}
**Derniere mise a jour**: {updated_at}
## Phases
| Phase | Statut |
|-------|--------|
| Fetch | completed |
| Analyze | completed |
| Explore | skipped |
| Plan | pending |
| Implement | pending |
## Point de Reprise
Reprise depuis: **plan**
Erreur precedente: {error.message}
Continuer ? [O/n]
state = "fetched", phases.fetch = "completed"state = "analyzed", phases.analyze = "completed", complexity = ...phases.explore = "skipped"phases.explore = "completed"state = "planned", phases.plan = "completed"AUTO mode: Auto-validate, continue to implement INTERACTIVE mode: Validation loop (Valider et implémenter / Valider et arrêter / Modifier / Régénérer)
state = "plan_validated", plan_validated_at = "{timestamp}"AUTO mode: Always executed after plan validation
INTERACTIVE mode: Via "Valider et implémenter" choice or --continue flag
/compact to clear contextstate = "implementing" → phases.implement = "completed"Read from project's .claude/ticket-config.json:
Priority order:
## Erreur Recuperable
L'erreur "{error.message}" peut etre resolue.
**Actions suggerees**:
1. {action 1}
2. {action 2}
**Pour reprendre**:
```bash
/resolve {ticket-id} # Reprend automatiquement
## Files Generated
.claude-work/{ticket-id}/ ├── status.json # Workflow state ├── ticket.md # Original ticket content ├── analysis.md # Complexity analysis + exploration findings └── plan.md # Implementation plan
## Integration Points
### With AEP Skill
- Used for COMPLEX tickets during explore phase
- Applies ANALYSE-EXPLORE-PLAN methodology
### With Architect Skill
- Used for COMPLEX tickets during plan phase
- Ensures plan follows best practices
### With /resolve --continue
- Plans saved in standard format
- Resumes implementation from validated plan
## Language
- Status file: English (machine-readable)
- User messages: French
- Technical output: English
development
Method to diagnose and raise the Lighthouse performance score of a public page (landing, marketing, home). Use when asked to improve Lighthouse/PageSpeed scores, when auditing the first uncached paint of a public page, or when a landing embedded in a SPA must reach a top score. Do NOT use for in-app screen performance (data loading, rendering). For a brand-new landing, the first recommendation is static HTML with no framework runtime — most of this skill exists for when that is not an option.
tools
Audits a project's Claude Code setup against real usage — mines the project's conversations (worktrees included), confronts the project's skills/agents/CLAUDE.md with best practices, and proposes adjustments or new skills/agents/rules. Use when the user asks to audit the project config, analyze project conversations, or find automation opportunities for the current project. Do NOT use for the global ~/.claude configuration (use /audit-config instead).
development
Coaching workflow orchestrator. Guides the developer through implementation without writing code.
development
Disciplined methodology for code architecture refactoring. Use when the user asks to refactor architecture, decouple code, restructure a family of classes, redesign an interface, or rename/reorganize a set of related components. Forces a big-picture analysis before any code is written. Do NOT use for simple bug fixes, feature additions, or single-file refactoring.