Stats
Actions
Tags
From tac
Assesses agentic coding maturity across In-Loop, Out-Loop, and Zero-Touch Engineering levels. Identifies blockers, analyzes metrics, and recommends progression steps for autonomous workflows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tac:zte-progressionThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guide teams through the three levels of agentic coding: In-Loop, Out-Loop, and Zero-Touch Engineering.
Guide teams through the three levels of agentic coding: In-Loop, Out-Loop, and Zero-Touch Engineering.
| Level | Presence KPI | Description |
|---|---|---|
| In-Loop | Constant | Interactive prompting |
| Out-Loop | 2 (prompt + review) | AFK agents with review |
| Zero-Touch | 1 (prompt only) | Full automation |
In-Loop -> Out-Loop:
Out-Loop -> ZTE:
Search for agentic workflow indicators:
Look for:
- Manual prompting patterns (In-Loop)
- Automated workflows with review (Out-Loop)
- Fully automated shipping (ZTE)
Review KPI data if available:
Check @agentic-kpis.md or equivalent:
- Attempt counts
- Success streaks
- Review catch rates
Common blockers to progression:
| Blocker | Mitigation |
|---|---|
| Low test coverage | Improve tests before progressing |
| Inconsistent success | Analyze failures, improve prompts |
| Review catches issues | Tests need to catch these first |
| No rollback capability | Add before enabling ZTE |
Based on current level, recommend:
At In-Loop:
At Out-Loop:
Near ZTE:
Provide assessment:
## ZTE Assessment
**Current Level:** [In-Loop | Out-Loop | ZTE]
**Problem Classes Assessed:** [chores, bugs, features]
### Indicators Found
- [Evidence of current level]
### Blockers to Progression
- [Identified blockers]
### Recommendations
1. [Specific next step]
2. [Specific next step]
### Target Timeline
- [Realistic progression timeline]
Date: 2025-12-26 Model: claude-opus-4-5-20251101
npx claudepluginhub melodic-software/claude-code-plugins --plugin tacAssesses agentic layer maturity in Claude Codebases using 12-grade system (Classes 1-3). Scans .claude/ for agents, skills, workflows, webhooks to score level and next steps.
Guides agentic engineering workflows: eval-first loops, 15-min task decomposition, model routing (Haiku/Sonnet/Opus), AI code reviews, and cost tracking.
Plans v1→v2→v3 agency ladder for AI features: maps autonomy increases over time, defines promotion criteria, generates stakeholder artifacts. Uses CC/CD framework.