Archive completed workflows and update the `context/` wiki with learnings. This skill runs at the final step of any workflow or when explicitly requested by the user.
/plugin marketplace add marcel-Ngan/ai-dev-team/plugin install marcel-ngan-ai-dev-team@marcel-Ngan/ai-dev-teamThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Archive completed workflows and update the context/ wiki with learnings. This skill runs at the final step of any workflow or when explicitly requested by the user.
┌─────────────────────────────────────────────────────────────────┐
│ WORKFLOW ARCHIVAL │
└─────────────────────────────────────────────────────────────────┘
│
┌─────────────────────────┼─────────────────────────┐
▼ ▼ ▼
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ 1. Archive │ │ 2. Update │ │ 3. Sync to │
│ Workflow │ │ Context │ │ Jira │
│ │ │ Wiki │ │ │
│ Move folder │ │ Extract │ │ Batch sync │
│ to archive/ │ │ learnings │ │ final state │
└─────────────┘ └─────────────┘ └─────────────┘
Action: Move workflow folder from active/ to archive/
Naming: {date}-{workflow-type}-{identifier}/
Example:
workflow/active/development-EPIC-45/
↓
workflow/archive/2026-01-09-development-EPIC-45/
Preserved:
workflow.md - Final state of workflow manifeststate.json - Complete gate history and metricsstories/*.md - All story iteration historydecisions.md - All decisions madeThe context/ folder serves as the project wiki. After archiving, update it with learnings from the completed workflow.
workflow/archive/{date}-development-{id}/stories/*.md
↓ (copy)
context/stories/*.md
Note: Stories in context/stories/ serve as historical reference for future agents.
If the workflow introduced significant changes, update context/solution-summary.md:
If specific modules were affected, update relevant context/project/*.md:
From workflow/archive/{name}/state.json, extract:
Add significant learnings to appropriate context files.
Sync all pending items from state.json to Jira:
"pending_sync": {
"decisions": [...], → Add to Jira comments / Confluence decision log
"blockers": [...], → Update blocker status in Jira
"learnings": [...], → Add to Confluence documentation
"comments": [...] → Add to Jira ticket comments
}
For each story in the workflow:
Update sync_history in archived state.json:
{
"timestamp": "2026-01-09T18:00:00Z",
"trigger": "workflow_archival",
"items_synced": ["story_status", "decisions", "comments", "learnings"]
}
Orchestrator runs this skill:
archive/ with date prefixcontext/stories/ (for dev workflows)context/solution-summary.md updated (if needed)context/project/*.md updated (if needed)workflow/active/development-EPIC-45/
├── workflow.md # Status: Step 9 (Closure)
├── state.json # All gates passed
├── stories/
│ ├── PROJECT-123.md # Done, 2 iterations
│ ├── PROJECT-124.md # Done, 1 iteration
│ └── PROJECT-125.md # Done, 3 iterations
└── decisions.md # 3 decisions logged
Move folder:
→ workflow/archive/2026-01-09-development-EPIC-45/
Copy stories to context:
→ context/stories/PROJECT-123.md
→ context/stories/PROJECT-124.md
→ context/stories/PROJECT-125.md
Update solution summary:
## Current Focus
- Completed: EPIC-45 (User Dashboard Enhancements)
- Active: [next epic or "None"]
Sync to Jira:
Notify stakeholder:
✅ Workflow Complete: EPIC-45 - User Dashboard Enhancements
Stories Completed: 3
Total Iterations: 6
Time in Workflow: 4h 30m
All stories deployed and verified.
workflow/
├── active/ # Empty
└── archive/
└── 2026-01-09-development-EPIC-45/ # Preserved for history
context/
├── solution-summary.md # Updated
├── project/
│ └── ...
└── stories/
├── PROJECT-123.md # Copied from workflow
├── PROJECT-124.md
└── PROJECT-125.md
workflow/active/{name}/ (all files)workflow/archive/, context/For failed workflows, keep in active/ with status "Failed" until resolved or user requests archival.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.