Menü
Assess the Agent Adoption level of the current project across all 8 criteria (A1–A8) and produce a structured report with the achieved level, per-criterion scores, gaps, and recommendations.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Assess the Agent Readiness level of the current project across all 11 criteria (C1.1–C8.2) and produce a structured report with the achieved level, per-criterion scores, gaps, and recommendations.
Verify readiness criterion C1.1 (Codebase Accessibility) in the current project. Reports fulfillment level 0–2.
Verify readiness criterion C2.1 (Setup Automation) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C3.1 (Architecture Depth) in the current project. Reports fulfillment level 0–3.
Verify readiness criterion C5.1 (Runnability) in the current project. Reports fulfillment level 0–2.
Verify readiness criterion C5.2 (Unit Test Coverage) in the current project. Reports fulfillment level 0–3.
| name | assess-adoption |
| description | Assess the Agent Adoption level of the current project across all 8 criteria (A1–A8) and produce a structured report with the achieved level, per-criterion scores, gaps, and recommendations. |
| allowed-tools | Bash Read |
This skill runs all 8 criterion checks and produces a structured adoption report.
For each criterion, read the corresponding skill file and follow its evidence-gathering and scoring instructions. Record the score before moving to the next criterion.
/verify-a1 skill/verify-a2 skill/verify-a3 skill/verify-a4 skill/verify-a5 skill/verify-a6 skill/verify-a7 skill/verify-a8 skillAfter scoring all criteria, determine the highest adoption level where all thresholds are met:
| Criterion | Level 1 | Level 2 | Level 3 | Level 4 |
|---|---|---|---|---|
| A1 | ≥ 1 | ≥ 2 | ≥ 3 | ≥ 3 |
| A2 | ≥ 1 | ≥ 2 | ≥ 3 | ≥ 3 |
| A3 | — | ≥ 2 | ≥ 2 | ≥ 3 |
| A4 | ≥ 1 | ≥ 2 | ≥ 3 | ≥ 3 |
| A5 | — | ≥ 1 | ≥ 3 | ≥ 3 |
| A6 | — | — | ≥ 3 | ≥ 3 |
| A7 | — | — | — | ≥ 3 |
| A8 | — | — | — | ≥ 2 |
Check Level 1 first. If all Level 1 thresholds are met, check Level 2, and so on. The achieved level is the highest where all thresholds pass.
Produce a report in exactly this structure:
Project: [name from README or directory name] Date: [today's date]
Level names: 0 = Unassisted, 1 = Vibe Coding, 2 = Agentic Engineering, 3 = Software Factory, 4 = Sustainable Autonomy
| Criterion | Name | Score | Max |
|---|---|---|---|
| A1 | Agent Context Availability | [score] | 3 |
| A2 | Agent-Authored Contributions | [score] | 3 |
| A3 | Feedback Loop Closure | [score] | 3 |
| A4 | Task Scope | [score] | 3 |
| A5 | Workflow Integration | [score] | 3 |
| A6 | Autonomous Operation | [score] | 3 |
| A7 | Proactive Quality Management | [score] | 3 |
| A8 | Planning Integration | [score] | 3 |
[If the project is at Level 4, write "Maximum level reached."]
[Otherwise, list each criterion below threshold for Level N+1:]
To reach Level [N+1] ([Name]), improve:
[State the minimum recommended readiness level for the current adoption level:
If the project's readiness level is known, note whether it supports the adoption level. If readiness is unknown, recommend running /assess-readiness.]
[3–5 prioritised, actionable recommendations based on the gaps. Order by impact: criteria blocking a level increase first, then easiest wins.]