菜单
Use in relational ambiguity to distinguish avoidance from real misalignment. Owns motive discrimination only.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the direct message or commitment handoff needs the right register. Owns tone and candor only.
Use when agency, obligation, and fear are tangled. Owns ownership sorting only.
Use to extend a live idea with one useful angle. Owns additive thinking only, not mode selection or action forcing.
Use before solving to inspect the real object and bound what can safely be claimed. Owns pre-solution contact only, not diagnosis or verification.
Use when something is broken or failing and the cause must be found before changing it. Owns failure diagnosis only.
Use when a canned frame would obscure the real object. Owns rejection of default scripts only.
| name | avoidance-vs-misalignment-discriminator |
| description | Use in relational ambiguity to distinguish avoidance from real misalignment. Owns motive discrimination only. |
| category | workflow |
| source_group | hermes-existential |
| compatibility | opencode |
Load this in relational or shared-agency ambiguity when it is unclear whether delay, hesitation, friction, or non-response is avoidance, genuine misalignment, insufficient agreement, or a missing request.
The skill owns motive discrimination in ambiguity. It helps decide what kind of relational move is honest before action is forced.
Do not use this for ordinary productivity delay, technical diagnosis, operator fit, tone polish, structural simplification, or post-change verification. If there is no relational or shared-agency stake, use another skill.
Return the discrimination: observed facts, possible readings, the most honest current read, and the clarifying move that would resolve it.
