> **⚠️ DEPRECATED:** This skill has been superseded by the consolidated workflow tracking approach.
/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.
state-schema.json⚠️ DEPRECATED: This skill has been superseded by the consolidated workflow tracking approach.
Use instead:
skills/workflow/workflow-tracking/State files now live in
workflow/active/{workflow-name}/state.jsoninstead of.ai-dev-team/workflow-state/.
.ai-dev-team/
└── workflow-state/
├── PROJECT-123.json # Per-story state
├── PROJECT-124.json
└── PROJECT-125.json
workflow/
└── active/
└── development-EPIC-45/
├── workflow.md # Workflow manifest
├── state.json # Consolidated state (replaces per-story files)
├── stories/ # Story details
│ ├── PROJECT-123.md
│ └── PROJECT-124.md
└── decisions.md # Decision log
| Aspect | Old | New |
|---|---|---|
| Location | .ai-dev-team/workflow-state/ | workflow/active/{name}/state.json |
| Scope | Per-story | Per-workflow (may contain multiple stories) |
| Related files | Scattered (context/, .ai-dev-team/) | Consolidated in workflow folder |
| Story details | Separate context/stories/*.md | workflow/active/{name}/stories/*.md |
| Cleanup | Manual | Automatic via archival skill |
The state.json schema is largely the same. See skills/workflow/workflow-tracking/SKILL.md for the current schema.
Key additions in new approach:
workflow_id - Workflow folder nameworkflow_type - Type of workflow (development, sprint-planning, etc.)skills/workflow/workflow-tracking/SKILL.md - Current workflow tracking approachskills/workflow/workflow-archival/SKILL.md - Archival and context updatesThe content below is preserved for reference. Do not use this approach for new workflows.
<details> <summary>Original Documentation (Archived)</summary>This skill enabled persistent workflow state tracking for individual stories. Each story had its own state file that tracked current position, gate history, and completed steps.
.ai-dev-team/
└── workflow-state/
├── PROJECT-123.json
├── PROJECT-124.json
└── PROJECT-125.json
See state-schema.json for the JSON schema (still applicable to new state.json format).
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 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 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.