Magnus HedemarkandGitHub
cc70502f79
Replace board-centric defaults with consequence-driven governance modes, feedback loops, exceptions, and clear ownership boundaries.\n\nAI-assisted: Jasper orchestrated implementation and verification with OpenCode. Signed-off-by: Magnus Hedemark <magnus919@pm.me>
2.5 KiB
Technology Radar
Turn scattered technology preferences into explicit, reviewable decisions with owners, evidence, and a clear adoption posture. Choose architecture-governance effort by consequence instead of routing every decision through a board.
Why Install This Skill
Turn scattered technology preferences into explicit, reviewable decisions with owners, evidence, and a clear adoption posture. It preserves a practical method, local reference material, and reusable templates so an agent can do more than produce a generic answer.
Use it when the work needs a repeatable process and an inspectable result. The governance method distinguishes automated policy, federated decisions, advice processes, and centralized review, then uses implementation and operational feedback to refine standards and radar entries. It is portable across Agent Skills-compatible clients and does not require a profile system or a particular task orchestrator.
What You Get
| Path | What it provides |
|---|---|
SKILL.md |
Trigger conditions, workflow, and guidance for loading deeper resources. |
references/ |
Reference material for radar decisions, proportional architecture governance, build-vs-buy analysis, and engineering metrics. |
Quick Start
Read references/technology-radar.md for a radar entry, or references/architecture-governance.md for a governance decision. Use the evidence and boundary guidance in SKILL.md to produce an inspectable result.
Install or expose this directory using your agent's standard Agent Skills loading mechanism, then ask for work that matches the triggers below.
Triggers
- Build and maintain technology radars for adoption, trial, assessment, and hold decisions.
- Choose or audit proportional architecture governance: automated policy, federated decision, advice process, or centralized review.
- Govern architecture standards, exceptions, review paths, and feedback from implementation or operations without turning technology-radar work into enterprise architecture.
- Requests involving the method, deliverables, or review process described in
SKILL.md. - Work where a reusable template or reference from this skill would reduce avoidable mistakes.
Requirements
No runtime dependency.
Source and maintenance
This skill was extracted from magnus919/hermes-profiles at commit 867a555. The portable methodology was retained; Hermes-specific profile, orchestration, and memory assumptions were removed.