Audit codebase for agentic layer coverage and identify gaps. Use when assessing agentic layer maturity, identifying investment opportunities, or evaluating primitive coverage.
Audits codebase for agentic layer components and coverage gaps. Use when assessing agentic maturity, identifying automation opportunities, or planning investments to increase agentic time above 50%.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install google-ecosystem@melodic-softwareThis skill is limited to using the following tools:
Evaluate a codebase's agentic layer maturity and identify investment opportunities.
"Am I working on the agentic layer or am I working on the application layer?"
This skill helps answer that question by auditing what exists.
Check for .claude/commands/ or equivalent:
Look for:
- chore.md # Chore planning template
- bug.md # Bug fix template
- feature.md # Feature planning template
- implement.md # Implementation HOP
- test.md # Test execution template
- review.md # Review template
Check for specs/ or equivalent:
Look for:
- Issue-based specs (issue-*.md)
- Generated plans (chore-*.md, feature-*.md)
- Deep specs (complex multi-file architectures)
Check for adws/ or equivalent:
Look for:
- adw_modules/agent.py # Core agent execution
- Gateway scripts (adw_prompt.py, adw_slash_command.py)
- Composed workflows (adw_*_*.py)
- Triggers (trigger_*.py)
Check for .claude/hooks/ or equivalent:
Look for:
- pre_tool_use hooks
- post_tool_use hooks
- user_prompt_submit hooks
Check for agents/ or equivalent:
Look for:
- ADW ID directories
- State files (adw_state.json)
- Output files (cc_*.jsonl, cc_*.json)
Check for trees/ or equivalent:
Look for:
- Git worktree setup
- Isolation configuration
- Port allocation patterns
| Component | Points | Present? |
|---|---|---|
| .claude/commands/ | 20 | |
| specs/ | 15 | |
| adws/ | 25 | |
| adw_modules/agent.py | 20 | |
| hooks/ | 10 | |
| agents/ | 5 | |
| trees/ | 5 |
Total: 100 points
| Score | Level | Recommendation |
|---|---|---|
| 0-20 | None | Start with minimum viable layer |
| 21-40 | Basic | Add composed workflows |
| 41-60 | Developing | Add hooks and triggers |
| 61-80 | Advanced | Add worktree isolation |
| 81-100 | Complete | Focus on optimization |
## Agentic Layer Audit Report
**Project:** {name}
**Audit Date:** {date}
**Coverage Score:** {score}/100
### Components Found
- [x] .claude/commands/ (5 templates)
- [x] specs/ (12 specs)
- [ ] adws/ (not found)
- [ ] hooks/ (not found)
### Maturity Level
{Level} - {Recommendation}
### Gaps Identified
1. No ADW scripts for workflow orchestration
2. No hooks for event-driven automation
3. No worktree isolation for parallelization
### Recommended Investments
1. Create adws/adw_modules/agent.py
2. Add gateway script (adw_prompt.py)
3. Create composed workflow for common tasks
### Time Investment Analysis
- Current: ~20% agentic layer
- Target: 50%+ agentic layer
- Gap: Need 30% more investment in agentic work
Date: 2025-12-26 Model: claude-opus-4-5-20251101
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.