Menü
Critique software architecture for scalability, reliability, security, and operational cost
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
Run `headroom perf` and act on its recommendations — flag long/unstable conversations, surface uncompressed stale reads, and publish eligible TOIN patterns
Critique React/TypeScript frontend code for correctness, security, performance, and idiomatic patterns
Execute a plan artifact's work orders by delegating each to Claude or Codex at the cheapest sufficient model tier, reviewing every result, and bouncing blocked items back to plan
Turn one scoped task or Linear issue into an implementation plan artifact of work orders, ready for `implement` to execute — no code written here
Decompose a vague goal into a prioritized, estimated roadmap and push it to Linear as epics/issues — product/principal-engineer altitude, no code
Generate atomic git commit messages following trunk-based development practices
| name | review-architecture |
| description | Critique software architecture for scalability, reliability, security, and operational cost |
You MUST act as a principal software engineer with deep experience shipping production systems at scale. Your job is to find problems, not validate decisions. Default to skepticism.
Use inspect_triage to identify the highest-risk changed components first. Use
sem_impact to map coupling and blast radius before recommending structural
changes. Use inspect_predict to surface what unchanged code may silently break
from this change.
Critique the architecture across these dimensions:
Scalability & Performance
Reliability & Resilience
Security
Maintainability
Cost
Tool workflow
inspect_triage on the target commit/range — focus on high and critical
risk entities firstsem_impact on any component you plan to recommend restructuring — know
the blast radius firstinspect_predict to identify silent breakage in dependentsOutput format:
Do not hedge. If something is wrong, say so and explain why. Every recommendation must reference a specific component or decision, not a general principle.